filter?

Ensure that a format selected with `-f ext` is a combined format unless format extraction is marked incomplete.

Resolves https://github.com/yt-dlp/yt-dlp/issues/5989#issuecomment-1374758043.

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.12.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2021.01.03**
+- [ ] I've verified that I'm running youtube-dl version **2021.12.17**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2021.01.03
+ [debug] youtube-dl version 2021.12.17
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.12.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2021.01.03**
+- [ ] I've verified that I'm running youtube-dl version **2021.12.17**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.12.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2021.01.03**
+- [ ] I've verified that I'm running youtube-dl version **2021.12.17**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.12.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2021.01.03**
+- [ ] I've verified that I'm running youtube-dl version **2021.12.17**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2021.01.03
+ [debug] youtube-dl version 2021.12.17
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.12.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2021.01.03**
+- [ ] I've verified that I'm running youtube-dl version **2021.12.17**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1 @@
+blank_issues_enabled: false

.github/workflows/ci.yml

@@ -1,5 +1,5 @@
 name: CI
-on: [push]
+on: [push, pull_request]
 jobs:
   tests:
     name: Tests
@@ -7,31 +7,62 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        os: [ubuntu-latest]
+        os: [ubuntu-18.04]
         # TODO: python 2.6
         python-version: [2.7, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, pypy-2.7, pypy-3.6, pypy-3.7]
+        python-impl: [cpython]
         ytdl-test-set: [core, download]
         run-tests-ext: [sh]
         include:
         # python 3.2 is only available on windows via setup-python
-        - os: windows-latest
+        - os: windows-2019
           python-version: 3.2
+          python-impl: cpython
           ytdl-test-set: core
           run-tests-ext: bat
-        - os: windows-latest
+        - os: windows-2019
           python-version: 3.2
+          python-impl: cpython
           ytdl-test-set: download
           run-tests-ext: bat
+        # jython
+        - os: ubuntu-18.04
+          python-impl: jython
+          ytdl-test-set: core
+          run-tests-ext: sh
+        - os: ubuntu-18.04
+          python-impl: jython
+          ytdl-test-set: download
+          run-tests-ext: sh
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2
+      if: ${{ matrix.python-impl == 'cpython' }}
       with:
         python-version: ${{ matrix.python-version }}
+    - name: Set up Java 8
+      if: ${{ matrix.python-impl == 'jython' }}
+      uses: actions/setup-java@v1
+      with:
+        java-version: 8
+    - name: Install Jython
+      if: ${{ matrix.python-impl == 'jython' }}
+      run: |
+        wget https://repo1.maven.org/maven2/org/python/jython-installer/2.7.1/jython-installer-2.7.1.jar -O jython-installer.jar
+        java -jar jython-installer.jar -s -d "$HOME/jython"
+        echo "$HOME/jython/bin" >> $GITHUB_PATH
     - name: Install nose
+      if: ${{ matrix.python-impl != 'jython' }}
       run: pip install nose
+    - name: Install nose (Jython)
+      if: ${{ matrix.python-impl == 'jython' }}
+      # Working around deprecation of support for non-SNI clients at PyPI CDN (see https://status.python.org/incidents/hzmjhqsdjqgb)
+      run: |
+        wget https://files.pythonhosted.org/packages/99/4f/13fb671119e65c4dce97c60e67d3fd9e6f7f809f2b307e2611f4701205cb/nose-1.3.7-py2-none-any.whl
+        pip install nose-1.3.7-py2-none-any.whl
     - name: Run tests
-      continue-on-error: ${{ matrix.ytdl-test-set == 'download' }}
+      continue-on-error: ${{ matrix.ytdl-test-set == 'download' || matrix.python-impl == 'jython' }}
       env:
         YTDL_TEST_SET: ${{ matrix.ytdl-test-set }}
       run: ./devscripts/run_tests.${{ matrix.run-tests-ext }}

.travis.yml

@@ -1,50 +0,0 @@
-language: python
-python:
-  - "2.6"
-  - "2.7"
-  - "3.2"
-  - "3.3"
-  - "3.4"
-  - "3.5"
-  - "3.6"
-  - "pypy"
-  - "pypy3"
-dist: trusty
-env:
-  - YTDL_TEST_SET=core
-#  - YTDL_TEST_SET=download
-jobs:
-  include:
-    - python: 3.7
-      dist: xenial
-      env: YTDL_TEST_SET=core
-#    - python: 3.7
-#      dist: xenial
-#      env: YTDL_TEST_SET=download
-    - python: 3.8
-      dist: xenial
-      env: YTDL_TEST_SET=core
-#    - python: 3.8
-#      dist: xenial
-#      env: YTDL_TEST_SET=download
-    - python: 3.8-dev
-      dist: xenial
-      env: YTDL_TEST_SET=core
-#    - python: 3.8-dev
-#      dist: xenial
-#      env: YTDL_TEST_SET=download
-    - env: JYTHON=true; YTDL_TEST_SET=core
-#    - env: JYTHON=true; YTDL_TEST_SET=download
-    - name: flake8
-      python: 3.8
-      dist: xenial
-      install: pip install flake8
-      script: flake8 .
-  fast_finish: true
-  allow_failures:
-#    - env: YTDL_TEST_SET=download
-    - env: JYTHON=true; YTDL_TEST_SET=core
-#    - env: JYTHON=true; YTDL_TEST_SET=download
-before_install:
-  - if [ "$JYTHON" == "true" ]; then ./devscripts/install_jython.sh; export PATH="$HOME/jython/bin:$PATH"; fi
-script: ./devscripts/run_tests.sh

AUTHORS

@@ -246,3 +246,4 @@ Enes Solak
 Nathan Rossi
 Thomas van der Berg
 Luca Cherubin
+Adrian Heine

CONTRIBUTING.md

@@ -150,7 +150,7 @@ After you have ensured this site is distributing its content legally, you can fo
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
-5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
+5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). This makes the extractor available for use, as long as the class ends with `IE`.
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
 8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://flake8.pycqa.org/en/latest/index.html#quickstart):

ChangeLog

@@ -1,3 +1,432 @@
+version 2021.12.17
+
+Core
+* [postprocessor/ffmpeg] Show ffmpeg output on error (#22680, #29336)
+
+Extractors
+* [youtube] Update signature function patterns (#30363, #30366)
+* [peertube] Only call description endpoint if necessary (#29383)
+* [periscope] Pass referer to HLS requests (#29419)
+- [liveleak] Remove extractor (#17625, #24222, #29331)
++ [pornhub] Add support for pornhubthbh7ap3u.onion
+* [pornhub] Detect geo restriction
+* [pornhub] Dismiss tbr extracted from download URLs (#28927)
+* [curiositystream:collection] Extend _VALID_URL (#26326, #29117)
+* [youtube] Make get_video_info processing more robust (#29333)
+* [youtube] Workaround for get_video_info request (#29333)
+* [bilibili] Strip uploader name (#29202)
+* [youtube] Update invidious instance list (#29281)
+* [umg:de] Update GraphQL API URL (#29304)
+* [nrk] Switch psapi URL to https (#29344)
++ [egghead] Add support for app.egghead.io (#28404, #29303)
+* [appleconnect] Fix extraction (#29208)
++ [orf:tvthek] Add support for MPD formats (#28672, #29236)
+
+
+version 2021.06.06
+
+Extractors
+* [facebook] Improve login required detection
+* [youporn] Fix formats and view count extraction (#29216)
+* [orf:tvthek] Fix thumbnails extraction (#29217)
+* [formula1] Fix extraction (#29206)
+* [ard] Relax URL regular expression and fix video ids (#22724, #29091)
++ [ustream] Detect https embeds (#29133)
+* [ted] Prefer own formats over external sources (#29142)
+* [twitch:clips] Improve extraction (#29149)
++ [twitch:clips] Add access token query to download URLs (#29136)
+* [youtube] Fix get_video_info request (#29086, #29165)
+* [vimeo] Fix vimeo pro embed extraction (#29126)
+* [redbulltv] Fix embed data extraction (#28770)
+* [shahid] Relax URL regular expression (#28772, #28930)
+
+
+version 2021.05.16
+
+Core
+* [options] Fix thumbnail option group name (#29042)
+* [YoutubeDL] Improve extract_info doc (#28946)
+
+Extractors
++ [playstuff] Add support for play.stuff.co.nz (#28901, #28931)
+* [eroprofile] Fix extraction (#23200, #23626, #29008)
++ [vivo] Add support for vivo.st (#29009)
++ [generic] Add support for og:audio (#28311, #29015)
+* [phoenix] Fix extraction (#29057)
++ [generic] Add support for sibnet embeds
++ [vk] Add support for sibnet embeds (#9500)
++ [generic] Add Referer header for direct videojs download URLs (#2879,
+  #20217, #29053)
+* [orf:radio] Switch download URLs to HTTPS (#29012, #29046)
+- [blinkx] Remove extractor (#28941)
+* [medaltv] Relax URL regular expression (#28884)
++ [funimation] Add support for optional lang code in URLs (#28950)
++ [gdcvault] Add support for HTML5 videos
+* [dispeak] Improve FLV extraction (#13513, #28970)
+* [kaltura] Improve iframe extraction (#28969)
+* [kaltura] Make embed code alternatives actually work
+* [cda] Improve extraction (#28709, #28937)
+* [twitter] Improve formats extraction from vmap URL (#28909)
+* [xtube] Fix formats extraction (#28870)
+* [svtplay] Improve extraction (#28507, #28876)
+* [tv2dk] Fix extraction (#28888)
+
+
+version 2021.04.26
+
+Extractors
++ [xfileshare] Add support for wolfstream.tv (#28858)
+* [francetvinfo] Improve video id extraction (#28792)
+* [medaltv] Fix extraction (#28807)
+* [tver] Redirect all downloads to Brightcove (#28849)
+* [go] Improve video id extraction (#25207, #25216, #26058)
+* [youtube] Fix lazy extractors (#28780)
++ [bbc] Extract description and timestamp from __INITIAL_DATA__ (#28774)
+* [cbsnews] Fix extraction for python <3.6 (#23359)
+
+
+version 2021.04.17
+
+Core
++ [utils] Add support for experimental HTTP response status code
+  308 Permanent Redirect (#27877, #28768)
+
+Extractors
++ [lbry] Add support for HLS videos (#27877, #28768)
+* [youtube] Fix stretched ratio calculation
+* [youtube] Improve stretch extraction (#28769)
+* [youtube:tab] Improve grid extraction (#28725)
++ [youtube:tab] Detect series playlist on playlists page (#28723)
++ [youtube] Add more invidious instances (#28706)
+* [pluralsight] Extend anti-throttling timeout (#28712)
+* [youtube] Improve URL to extractor routing (#27572, #28335, #28742)
++ [maoritv] Add support for maoritelevision.com (#24552)
++ [youtube:tab] Pass innertube context and x-goog-visitor-id header along with
+  continuation requests (#28702)
+* [mtv] Fix Viacom A/B Testing Video Player extraction (#28703)
++ [pornhub] Extract DASH and HLS formats from get_media end point (#28698)
+* [cbssports] Fix extraction (#28682)
+* [jamendo] Fix track extraction (#28686)
+* [curiositystream] Fix format extraction (#26845, #28668)
+
+
+version 2021.04.07
+
+Core
+* [extractor/common] Use compat_cookies_SimpleCookie for _get_cookies
++ [compat] Introduce compat_cookies_SimpleCookie
+* [extractor/common] Improve JSON-LD author extraction
+* [extractor/common] Fix _get_cookies on python 2 (#20673, #23256, #20326,
+  #28640)
+
+Extractors
+* [youtube] Fix extraction of videos with restricted location (#28685)
++ [line] Add support for live.line.me (#17205, #28658)
+* [vimeo] Improve extraction (#28591)
+* [youku] Update ccode (#17852, #28447, #28460, #28648)
+* [youtube] Prefer direct entry metadata over entry metadata from playlist
+  (#28619, #28636)
+* [screencastomatic] Fix extraction (#11976, #24489)
++ [palcomp3] Add support for palcomp3.com (#13120)
++ [arnes] Add support for video.arnes.si (#28483)
++ [youtube:tab] Add support for hashtags (#28308)
+
+
+version 2021.04.01
+
+Extractors
+* [youtube] Setup CONSENT cookie when needed (#28604)
+* [vimeo] Fix password protected review extraction (#27591)
+* [youtube] Improve age-restricted video extraction (#28578)
+
+
+version 2021.03.31
+
+Extractors
+* [vlive] Fix inkey request (#28589)
+* [francetvinfo] Improve video id extraction (#28584)
++ [instagram] Extract duration (#28469)
+* [instagram] Improve title extraction (#28469)
++ [sbs] Add support for ondemand watch URLs (#28566)
+* [youtube] Fix video's channel extraction (#28562)
+* [picarto] Fix live stream extraction (#28532)
+* [vimeo] Fix unlisted video extraction (#28414)
+* [youtube:tab] Fix playlist/community continuation items extraction (#28266)
+* [ard] Improve clip id extraction (#22724, #28528)
+
+
+version 2021.03.25
+
+Extractors
++ [zoom] Add support for zoom.us (#16597, #27002, #28531)
+* [bbc] Fix BBC IPlayer Episodes/Group extraction (#28360)
+* [youtube] Fix default value for youtube_include_dash_manifest (#28523)
+* [zingmp3] Fix extraction (#11589, #16409, #16968, #27205)
++ [vgtv] Add support for new tv.aftonbladet.se URL schema (#28514)
++ [tiktok] Detect private videos (#28453)
+* [vimeo:album] Fix extraction for albums with number of videos multiple
+  to page size (#28486)
+* [vvvvid] Fix kenc format extraction (#28473)
+* [mlb] Fix video extraction (#21241)
+* [svtplay] Improve extraction (#28448)
+* [applepodcasts] Fix extraction (#28445)
+* [rtve] Improve extraction
+    + Extract all formats
+    * Fix RTVE Infantil extraction (#24851)
+    + Extract is_live and series
+
+
+version 2021.03.14
+
+Core
++ Introduce release_timestamp meta field (#28386)
+
+Extractors
++ [southpark] Add support for southparkstudios.com (#28413)
+* [southpark] Fix extraction (#26763, #28413)
+* [sportdeutschland] Fix extraction (#21856, #28425)
+* [pinterest] Reduce the number of HLS format requests
+* [peertube] Improve thumbnail extraction (#28419)
+* [tver] Improve title extraction (#28418)
+* [fujitv] Fix HLS formats extension (#28416)
+* [shahid] Fix format extraction (#28383)
++ [lbry] Add support for channel filters (#28385)
++ [bandcamp] Extract release timestamp
++ [lbry] Extract release timestamp (#28386)
+* [pornhub] Detect flagged videos
++ [pornhub] Extract formats from get_media end point (#28395)
+* [bilibili] Fix video info extraction (#28341)
++ [cbs] Add support for Paramount+ (#28342)
++ [trovo] Add Origin header to VOD formats (#28346)
+* [voxmedia] Fix volume embed extraction (#28338)
+
+
+version 2021.03.03
+
+Extractors
+* [youtube:tab] Switch continuation to browse API (#28289, #28327)
+* [9c9media] Fix extraction for videos with multiple ContentPackages (#28309)
++ [bbc] Add support for BBC Reel videos (#21870, #23660, #28268)
+
+
+version 2021.03.02
+
+Extractors
+* [zdf] Rework extractors (#11606, #13473, #17354, #21185, #26711, #27068,
+  #27930, #28198, #28199, #28274)
+    * Generalize cross-extractor video ids for zdf based extractors
+    * Improve extraction
+    * Fix 3sat and phoenix
+* [stretchinternet] Fix extraction (#28297)
+* [urplay] Fix episode data extraction (#28292)
++ [bandaichannel] Add support for b-ch.com (#21404)
+* [srgssr] Improve extraction (#14717, #14725, #27231, #28238)
+    + Extract subtitle
+    * Fix extraction for new videos
+    * Update srf download domains
+* [vvvvid] Reduce season request payload size
++ [vvvvid] Extract series sublists playlist title (#27601, #27618)
++ [dplay] Extract Ad-Free uplynk URLs (#28160)
++ [wat] Detect DRM protected videos (#27958)
+* [tf1] Improve extraction (#27980, #28040)
+* [tmz] Fix and improve extraction (#24603, #24687, 28211)
++ [gedidigital] Add support for Gedi group sites (#7347, #26946)
+* [youtube] Fix get_video_info request
+
+
+version 2021.02.22
+
+Core
++ [postprocessor/embedthumbnail] Recognize atomicparsley binary in lowercase
+  (#28112)
+
+Extractors
+* [apa] Fix and improve extraction (#27750)
++ [youporn] Extract duration (#28019)
++ [peertube] Add support for canard.tube (#28190)
+* [youtube] Fixup m4a_dash formats (#28165)
++ [samplefocus] Add support for samplefocus.com (#27763)
++ [vimeo] Add support for unlisted video source format extraction
+* [viki] Improve extraction (#26522, #28203)
+    * Extract uploader URL and episode number
+    * Report login required error
+    + Extract 480p formats
+    * Fix API v4 calls
+* [ninegag] Unescape title (#28201)
+* [youtube] Improve URL regular expression (#28193)
++ [youtube] Add support for redirect.invidious.io (#28193)
++ [dplay] Add support for de.hgtv.com (#28182)
++ [dplay] Add support for discoveryplus.com (#24698)
++ [simplecast] Add support for simplecast.com (#24107)
+* [youtube] Fix uploader extraction in flat playlist mode (#28045)
+* [yandexmusic:playlist] Request missing tracks in chunks (#27355, #28184)
++ [storyfire] Add support for storyfire.com (#25628, #26349)
++ [zhihu] Add support for zhihu.com (#28177)
+* [youtube] Fix controversial videos when authenticated with cookies (#28174)
+* [ccma] Fix timestamp parsing in python 2
++ [videopress] Add support for video.wordpress.com
+* [kakao] Improve info extraction and detect geo restriction (#26577)
+* [xboxclips] Fix extraction (#27151)
+* [ard] Improve formats extraction (#28155)
++ [canvas] Add support for dagelijksekost.een.be (#28119)
+
+
+version 2021.02.10
+
+Extractors
+* [youtube:tab] Improve grid continuation extraction (#28130)
+* [ign] Fix extraction (#24771)
++ [xhamster] Extract format filesize
++ [xhamster] Extract formats from xplayer settings (#28114)
++ [youtube] Add support phone/tablet JS player (#26424)
+* [archiveorg] Fix and improve extraction (#21330, #23586, #25277, #26780,
+  #27109, #27236, #28063)
++ [cda] Detect geo restricted videos (#28106)
+* [urplay] Fix extraction (#28073, #28074)
+* [youtube] Fix release date extraction (#28094)
++ [youtube] Extract abr and vbr (#28100)
+* [youtube] Skip OTF formats (#28070)
+
+
+version 2021.02.04.1
+
+Extractors
+* [youtube] Prefer DASH formats (#28070)
+* [azmedien] Fix extraction (#28064)
+
+
+version 2021.02.04
+
+Extractors
+* [pornhub] Implement lazy playlist extraction
+* [svtplay] Fix video id extraction (#28058)
++ [pornhub] Add support for authentication (#18797, #21416, #24294)
+* [pornhub:user] Improve paging
++ [pornhub:user] Add support for URLs unavailable via /videos page (#27853)
++ [bravotv] Add support for oxygen.com (#13357, #22500)
++ [youtube] Pass embed URL to get_video_info request
+* [ccma] Improve metadata extraction (#27994)
+    + Extract age limit, alt title, categories, series and episode number
+    * Fix timestamp multiple subtitles extraction
+* [egghead] Update API domain (#28038)
+- [vidzi] Remove extractor (#12629)
+* [vidio] Improve metadata extraction
+* [youtube] Improve subtitles extraction
+* [youtube] Fix chapter extraction fallback
+* [youtube] Rewrite extractor
+    * Improve format sorting
+    * Remove unused code
+    * Fix series metadata extraction
+    * Fix trailer video extraction
+    * Improve error reporting
+    + Extract video location
++ [vvvvid] Add support for youtube embeds (#27825)
+* [googledrive] Report download page errors (#28005)
+* [vlive] Fix error message decoding for python 2 (#28004)
+* [youtube] Improve DASH formats file size extraction
+* [cda] Improve birth validation detection (#14022, #27929)
++ [awaan] Extract uploader id (#27963)
++ [medialaan] Add support DPG Media MyChannels based websites (#14871, #15597,
+  #16106, #16489)
+* [abcnews] Fix extraction (#12394, #27920)
+* [AMP] Fix upload date and timestamp extraction (#27970)
+* [tv4] Relax URL regular expression (#27964)
++ [tv2] Add support for mtvuutiset.fi (#27744)
+* [adn] Improve login warning reporting
+* [zype] Fix uplynk id extraction (#27956)
++ [adn] Add support for authentication (#17091, #27841, #27937)
+
+
+version 2021.01.24.1
+
+Core
+* Introduce --output-na-placeholder (#27896)
+
+Extractors
+* [franceculture] Make thumbnail optional (#18807)
+* [franceculture] Fix extraction (#27891, #27903)
+* [njpwworld] Fix extraction (#27890)
+* [comedycentral] Fix extraction (#27905)
+* [wat] Fix format extraction (#27901)
++ [americastestkitchen:season] Add support for seasons (#27861)
++ [trovo] Add support for trovo.live (#26125)
++ [aol] Add support for yahoo videos (#26650)
+* [yahoo] Fix single video extraction
+* [lbry] Unescape lbry URI (#27872)
+* [9gag] Fix and improve extraction (#23022)
+* [americastestkitchen] Improve metadata extraction for ATK episodes (#27860)
+* [aljazeera] Fix extraction (#20911, #27779)
++ [minds] Add support for minds.com (#17934)
+* [ard] Fix title and description extraction (#27761)
++ [spotify] Add support for Spotify Podcasts (#27443)
+
+
+version 2021.01.16
+
+Core
+* [YoutubeDL] Protect from infinite recursion due to recursively nested
+  playlists (#27833)
+* [YoutubeDL] Ignore failure to create existing directory (#27811)
+* [YoutubeDL] Raise syntax error for format selection expressions with multiple
+  + operators (#27803)
+
+Extractors
++ [animeondemand] Add support for lazy playlist extraction (#27829)
+* [youporn] Restrict fallback download URL (#27822)
+* [youporn] Improve height and tbr extraction (#20425, #23659)
+* [youporn] Fix extraction (#27822)
++ [twitter] Add support for unified cards (#27826)
++ [twitch] Add Authorization header with OAuth token for GraphQL requests
+  (#27790)
+* [mixcloud:playlist:base] Extract video id in flat playlist mode (#27787)
+* [cspan] Improve info extraction (#27791)
+* [adn] Improve info extraction
+* [adn] Fix extraction (#26963, #27732)
+* [youtube:search] Extract from all sections (#27604)
+* [youtube:search] fix viewcount and try to extract all video sections (#27604)
+* [twitch] Improve login error extraction
+* [twitch] Fix authentication (#27743)
+* [3qsdn] Improve extraction (#21058)
+* [peertube] Extract formats from streamingPlaylists (#26002, #27586, #27728)
+* [khanacademy] Fix extraction (#2887, #26803)
+* [spike] Update Paramount Network feed URL (#27715)
+
+
+version 2021.01.08
+
+Core
+* [downloader/hls] Disable decryption in tests (#27660)
++ [utils] Add a function to clean podcast URLs
+
+Extractors
+* [rai] Improve subtitles extraction (#27698, #27705)
+* [canvas] Match only supported VRT NU URLs (#27707)
++ [bibeltv] Add support for bibeltv.de (#14361)
++ [bfmtv] Add support for bfmtv.com (#16053, #26615)
++ [sbs] Add support for ondemand play and news embed URLs (#17650, #27629)
+* [twitch] Drop legacy kraken API v5 code altogether and refactor
+* [twitch:vod] Switch to GraphQL for video metadata
+* [canvas] Fix VRT NU extraction (#26957, #27053)
+* [twitch] Switch access token to GraphQL and refactor (#27646)
++ [rai] Detect ContentItem in iframe (#12652, #27673)
+* [ketnet] Fix extraction (#27662)
++ [dplay] Add suport Discovery+ domains (#27680)
+* [motherless] Improve extraction (#26495, #27450)
+* [motherless] Fix recent videos upload date extraction (#27661)
+* [nrk] Fix extraction for videos without a legalAge rating
+- [googleplus] Remove extractor (#4955, #7400)
++ [applepodcasts] Add support for podcasts.apple.com (#25918)
++ [googlepodcasts] Add support for podcasts.google.com
++ [iheart] Add support for iheart.com (#27037)
+* [acast] Clean podcast URLs
+* [stitcher] Clean podcast URLs
++ [xfileshare] Add support for aparat.cam (#27651)
++ [twitter] Add support for summary card (#25121)
+* [twitter] Try to use a Generic fallback for unknown twitter cards (#25982)
++ [stitcher] Add support for shows and show metadata extraction (#20510)
+* [stv] Improve episode id extraction (#23083)
+
+
 version 2021.01.03
 
 Extractors

README.md

@@ -54,126 +54,139 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
 # OPTIONS
     -h, --help                           Print this help text and exit
     --version                            Print program version and exit
-    -U, --update                     Update this program to latest version. Make
-                                     sure that you have sufficient permissions
-                                     (run with sudo if needed)
-    -i, --ignore-errors              Continue on download errors, for example to
-                                     skip unavailable videos in a playlist
-    --abort-on-error                 Abort downloading of further videos (in the
-                                     playlist or the command line) if an error
-                                     occurs
-    --dump-user-agent                Display the current browser identification
+    -U, --update                         Update this program to latest version.
+                                         Make sure that you have sufficient
+                                         permissions (run with sudo if needed)
+    -i, --ignore-errors                  Continue on download errors, for
+                                         example to skip unavailable videos in a
+                                         playlist
+    --abort-on-error                     Abort downloading of further videos (in
+                                         the playlist or the command line) if an
+                                         error occurs
+    --dump-user-agent                    Display the current browser
+                                         identification
     --list-extractors                    List all supported extractors
     --extractor-descriptions             Output descriptions of all supported
                                          extractors
     --force-generic-extractor            Force extraction to use the generic
                                          extractor
-    --default-search PREFIX          Use this prefix for unqualified URLs. For
-                                     example "gvsearch2:" downloads two videos
-                                     from google videos for youtube-dl "large
-                                     apple". Use the value "auto" to let
-                                     youtube-dl guess ("auto_warning" to emit a
-                                     warning when guessing). "error" just throws
-                                     an error. The default value "fixup_error"
-                                     repairs broken URLs, but emits an error if
-                                     this is not possible instead of searching.
-    --ignore-config                  Do not read configuration files. When given
-                                     in the global configuration file
-                                     /etc/youtube-dl.conf: Do not read the user
-                                     configuration in ~/.config/youtube-
-                                     dl/config (%APPDATA%/youtube-dl/config.txt
-                                     on Windows)
-    --config-location PATH           Location of the configuration file; either
-                                     the path to the config or its containing
-                                     directory.
-    --flat-playlist                  Do not extract the videos of a playlist,
-                                     only list them.
+    --default-search PREFIX              Use this prefix for unqualified URLs.
+                                         For example "gvsearch2:" downloads two
+                                         videos from google videos for youtube-
+                                         dl "large apple". Use the value "auto"
+                                         to let youtube-dl guess ("auto_warning"
+                                         to emit a warning when guessing).
+                                         "error" just throws an error. The
+                                         default value "fixup_error" repairs
+                                         broken URLs, but emits an error if this
+                                         is not possible instead of searching.
+    --ignore-config                      Do not read configuration files. When
+                                         given in the global configuration file
+                                         /etc/youtube-dl.conf: Do not read the
+                                         user configuration in
+                                         ~/.config/youtube-dl/config
+                                         (%APPDATA%/youtube-dl/config.txt on
+                                         Windows)
+    --config-location PATH               Location of the configuration file;
+                                         either the path to the config or its
+                                         containing directory.
+    --flat-playlist                      Do not extract the videos of a
+                                         playlist, only list them.
     --mark-watched                       Mark videos watched (YouTube only)
-    --no-mark-watched                Do not mark videos watched (YouTube only)
+    --no-mark-watched                    Do not mark videos watched (YouTube
+                                         only)
     --no-color                           Do not emit color codes in output
 
 ## Network Options:
-    --proxy URL                      Use the specified HTTP/HTTPS/SOCKS proxy.
-                                     To enable SOCKS proxy, specify a proper
-                                     scheme. For example
-                                     socks5://127.0.0.1:1080/. Pass in an empty
-                                     string (--proxy "") for direct connection
-    --socket-timeout SECONDS         Time to wait before giving up, in seconds
+    --proxy URL                          Use the specified HTTP/HTTPS/SOCKS
+                                         proxy. To enable SOCKS proxy, specify a
+                                         proper scheme. For example
+                                         socks5://127.0.0.1:1080/. Pass in an
+                                         empty string (--proxy "") for direct
+                                         connection
+    --socket-timeout SECONDS             Time to wait before giving up, in
+                                         seconds
     --source-address IP                  Client-side IP address to bind to
     -4, --force-ipv4                     Make all connections via IPv4
     -6, --force-ipv6                     Make all connections via IPv6
 
 ## Geo Restriction:
-    --geo-verification-proxy URL     Use this proxy to verify the IP address for
-                                     some geo-restricted sites. The default
-                                     proxy specified by --proxy (or none, if the
-                                     option is not present) is used for the
-                                     actual downloading.
-    --geo-bypass                     Bypass geographic restriction via faking
-                                     X-Forwarded-For HTTP header
-    --no-geo-bypass                  Do not bypass geographic restriction via
+    --geo-verification-proxy URL         Use this proxy to verify the IP address
+                                         for some geo-restricted sites. The
+                                         default proxy specified by --proxy (or
+                                         none, if the option is not present) is
+                                         used for the actual downloading.
+    --geo-bypass                         Bypass geographic restriction via
                                          faking X-Forwarded-For HTTP header
-    --geo-bypass-country CODE        Force bypass geographic restriction with
-                                     explicitly provided two-letter ISO 3166-2
-                                     country code
-    --geo-bypass-ip-block IP_BLOCK   Force bypass geographic restriction with
-                                     explicitly provided IP block in CIDR
-                                     notation
+    --no-geo-bypass                      Do not bypass geographic restriction
+                                         via faking X-Forwarded-For HTTP header
+    --geo-bypass-country CODE            Force bypass geographic restriction
+                                         with explicitly provided two-letter ISO
+                                         3166-2 country code
+    --geo-bypass-ip-block IP_BLOCK       Force bypass geographic restriction
+                                         with explicitly provided IP block in
+                                         CIDR notation
 
 ## Video Selection:
-    --playlist-start NUMBER          Playlist video to start at (default is 1)
-    --playlist-end NUMBER            Playlist video to end at (default is last)
-    --playlist-items ITEM_SPEC       Playlist video items to download. Specify
-                                     indices of the videos in the playlist
-                                     separated by commas like: "--playlist-items
-                                     1,2,5,8" if you want to download videos
-                                     indexed 1, 2, 5, 8 in the playlist. You can
-                                     specify range: "--playlist-items
-                                     1-3,7,10-13", it will download the videos
-                                     at index 1, 2, 3, 7, 10, 11, 12 and 13.
+    --playlist-start NUMBER              Playlist video to start at (default is
+                                         1)
+    --playlist-end NUMBER                Playlist video to end at (default is
+                                         last)
+    --playlist-items ITEM_SPEC           Playlist video items to download.
+                                         Specify indices of the videos in the
+                                         playlist separated by commas like: "--
+                                         playlist-items 1,2,5,8" if you want to
+                                         download videos indexed 1, 2, 5, 8 in
+                                         the playlist. You can specify range: "
+                                         --playlist-items 1-3,7,10-13", it will
+                                         download the videos at index 1, 2, 3,
+                                         7, 10, 11, 12 and 13.
     --match-title REGEX                  Download only matching titles (regex or
                                          caseless sub-string)
-    --reject-title REGEX             Skip download for matching titles (regex or
-                                     caseless sub-string)
+    --reject-title REGEX                 Skip download for matching titles
+                                         (regex or caseless sub-string)
     --max-downloads NUMBER               Abort after downloading NUMBER files
     --min-filesize SIZE                  Do not download any videos smaller than
                                          SIZE (e.g. 50k or 44.6m)
-    --max-filesize SIZE              Do not download any videos larger than SIZE
-                                     (e.g. 50k or 44.6m)
-    --date DATE                      Download only videos uploaded in this date
-    --datebefore DATE                Download only videos uploaded on or before
-                                     this date (i.e. inclusive)
-    --dateafter DATE                 Download only videos uploaded on or after
-                                     this date (i.e. inclusive)
-    --min-views COUNT                Do not download any videos with less than
-                                     COUNT views
-    --max-views COUNT                Do not download any videos with more than
-                                     COUNT views
-    --match-filter FILTER            Generic video filter. Specify any key (see
-                                     the "OUTPUT TEMPLATE" for a list of
-                                     available keys) to match if the key is
-                                     present, !key to check if the key is not
-                                     present, key > NUMBER (like "comment_count
-                                     > 12", also works with >=, <, <=, !=, =) to
-                                     compare against a number, key = 'LITERAL'
-                                     (like "uploader = 'Mike Smith'", also works
-                                     with !=) to match against a string literal
-                                     and & to require multiple matches. Values
-                                     which are not known are excluded unless you
-                                     put a question mark (?) after the operator.
-                                     For example, to only match videos that have
-                                     been liked more than 100 times and disliked
-                                     less than 50 times (or the dislike
-                                     functionality is not available at the given
-                                     service), but who also have a description,
-                                     use --match-filter "like_count > 100 &
+    --max-filesize SIZE                  Do not download any videos larger than
+                                         SIZE (e.g. 50k or 44.6m)
+    --date DATE                          Download only videos uploaded in this
+                                         date
+    --datebefore DATE                    Download only videos uploaded on or
+                                         before this date (i.e. inclusive)
+    --dateafter DATE                     Download only videos uploaded on or
+                                         after this date (i.e. inclusive)
+    --min-views COUNT                    Do not download any videos with less
+                                         than COUNT views
+    --max-views COUNT                    Do not download any videos with more
+                                         than COUNT views
+    --match-filter FILTER                Generic video filter. Specify any key
+                                         (see the "OUTPUT TEMPLATE" for a list
+                                         of available keys) to match if the key
+                                         is present, !key to check if the key is
+                                         not present, key > NUMBER (like
+                                         "comment_count > 12", also works with
+                                         >=, <, <=, !=, =) to compare against a
+                                         number, key = 'LITERAL' (like "uploader
+                                         = 'Mike Smith'", also works with !=) to
+                                         match against a string literal and & to
+                                         require multiple matches. Values which
+                                         are not known are excluded unless you
+                                         put a question mark (?) after the
+                                         operator. For example, to only match
+                                         videos that have been liked more than
+                                         100 times and disliked less than 50
+                                         times (or the dislike functionality is
+                                         not available at the given service),
+                                         but who also have a description, use
+                                         --match-filter "like_count > 100 &
                                          dislike_count <? 50 & description" .
-    --no-playlist                    Download only the video, if the URL refers
-                                     to a video and a playlist.
-    --yes-playlist                   Download the playlist, if the URL refers to
-                                     a video and a playlist.
-    --age-limit YEARS                Download only videos suitable for the given
-                                     age
+    --no-playlist                        Download only the video, if the URL
+                                         refers to a video and a playlist.
+    --yes-playlist                       Download the playlist, if the URL
+                                         refers to a video and a playlist.
+    --age-limit YEARS                    Download only videos suitable for the
+                                         given age
     --download-archive FILE              Download only videos not listed in the
                                          archive file. Record the IDs of all
                                          downloaded videos in it.
@@ -181,168 +194,183 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                          (experimental)
 
 ## Download Options:
-    -r, --limit-rate RATE            Maximum download rate in bytes per second
-                                     (e.g. 50K or 4.2M)
+    -r, --limit-rate RATE                Maximum download rate in bytes per
+                                         second (e.g. 50K or 4.2M)
     -R, --retries RETRIES                Number of retries (default is 10), or
                                          "infinite".
-    --fragment-retries RETRIES       Number of retries for a fragment (default
-                                     is 10), or "infinite" (DASH, hlsnative and
-                                     ISM)
-    --skip-unavailable-fragments     Skip unavailable fragments (DASH, hlsnative
-                                     and ISM)
-    --abort-on-unavailable-fragment  Abort downloading when some fragment is not
-                                     available
+    --fragment-retries RETRIES           Number of retries for a fragment
+                                         (default is 10), or "infinite" (DASH,
+                                         hlsnative and ISM)
+    --skip-unavailable-fragments         Skip unavailable fragments (DASH,
+                                         hlsnative and ISM)
+    --abort-on-unavailable-fragment      Abort downloading when some fragment is
+                                         not available
     --keep-fragments                     Keep downloaded fragments on disk after
                                          downloading is finished; fragments are
                                          erased by default
-    --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)
-                                     (default is 1024)
+    --buffer-size SIZE                   Size of download buffer (e.g. 1024 or
+                                         16K) (default is 1024)
     --no-resize-buffer                   Do not automatically adjust the buffer
                                          size. By default, the buffer size is
-                                     automatically resized from an initial value
-                                     of SIZE.
+                                         automatically resized from an initial
+                                         value of SIZE.
     --http-chunk-size SIZE               Size of a chunk for chunk-based HTTP
-                                     downloading (e.g. 10485760 or 10M) (default
-                                     is disabled). May be useful for bypassing
-                                     bandwidth throttling imposed by a webserver
-                                     (experimental)
-    --playlist-reverse               Download playlist videos in reverse order
-    --playlist-random                Download playlist videos in random order
+                                         downloading (e.g. 10485760 or 10M)
+                                         (default is disabled). May be useful
+                                         for bypassing bandwidth throttling
+                                         imposed by a webserver (experimental)
+    --playlist-reverse                   Download playlist videos in reverse
+                                         order
+    --playlist-random                    Download playlist videos in random
+                                         order
     --xattr-set-filesize                 Set file xattribute ytdl.filesize with
                                          expected file size
-    --hls-prefer-native              Use the native HLS downloader instead of
-                                     ffmpeg
+    --hls-prefer-native                  Use the native HLS downloader instead
+                                         of ffmpeg
     --hls-prefer-ffmpeg                  Use ffmpeg instead of the native HLS
                                          downloader
-    --hls-use-mpegts                 Use the mpegts container for HLS videos,
-                                     allowing to play the video while
-                                     downloading (some players may not be able
-                                     to play it)
+    --hls-use-mpegts                     Use the mpegts container for HLS
+                                         videos, allowing to play the video
+                                         while downloading (some players may not
+                                         be able to play it)
     --external-downloader COMMAND        Use the specified external downloader.
-                                     Currently supports
-                                     aria2c,avconv,axel,curl,ffmpeg,httpie,wget
+                                         Currently supports aria2c,avconv,axel,c
+                                         url,ffmpeg,httpie,wget
     --external-downloader-args ARGS      Give these arguments to the external
                                          downloader
 
 ## Filesystem Options:
-    -a, --batch-file FILE            File containing URLs to download ('-' for
-                                     stdin), one URL per line. Lines starting
-                                     with '#', ';' or ']' are considered as
-                                     comments and ignored.
+    -a, --batch-file FILE                File containing URLs to download ('-'
+                                         for stdin), one URL per line. Lines
+                                         starting with '#', ';' or ']' are
+                                         considered as comments and ignored.
     --id                                 Use only video ID in file name
-    -o, --output TEMPLATE            Output filename template, see the "OUTPUT
-                                     TEMPLATE" for all the info
-    --autonumber-start NUMBER        Specify the start value for %(autonumber)s
-                                     (default is 1)
+    -o, --output TEMPLATE                Output filename template, see the
+                                         "OUTPUT TEMPLATE" for all the info
+    --output-na-placeholder PLACEHOLDER  Placeholder value for unavailable meta
+                                         fields in output filename template
+                                         (default is "NA")
+    --autonumber-start NUMBER            Specify the start value for
+                                         %(autonumber)s (default is 1)
     --restrict-filenames                 Restrict filenames to only ASCII
                                          characters, and avoid "&" and spaces in
                                          filenames
     -w, --no-overwrites                  Do not overwrite files
-    -c, --continue                   Force resume of partially downloaded files.
-                                     By default, youtube-dl will resume
-                                     downloads if possible.
-    --no-continue                    Do not resume partially downloaded files
-                                     (restart from beginning)
+    -c, --continue                       Force resume of partially downloaded
+                                         files. By default, youtube-dl will
+                                         resume downloads if possible.
+    --no-continue                        Do not resume partially downloaded
+                                         files (restart from beginning)
     --no-part                            Do not use .part files - write directly
                                          into output file
-    --no-mtime                       Do not use the Last-modified header to set
-                                     the file modification time
-    --write-description              Write video description to a .description
+    --no-mtime                           Do not use the Last-modified header to
+                                         set the file modification time
+    --write-description                  Write video description to a
+                                         .description file
+    --write-info-json                    Write video metadata to a .info.json
                                          file
-    --write-info-json                Write video metadata to a .info.json file
     --write-annotations                  Write video annotations to a
                                          .annotations.xml file
-    --load-info-json FILE            JSON file containing the video information
-                                     (created with the "--write-info-json"
-                                     option)
-    --cookies FILE                   File to read cookies from and dump cookie
-                                     jar in
-    --cache-dir DIR                  Location in the filesystem where youtube-dl
-                                     can store some downloaded information
-                                     permanently. By default
+    --load-info-json FILE                JSON file containing the video
+                                         information (created with the "--write-
+                                         info-json" option)
+    --cookies FILE                       File to read cookies from and dump
+                                         cookie jar in
+    --cache-dir DIR                      Location in the filesystem where
+                                         youtube-dl can store some downloaded
+                                         information permanently. By default
                                          $XDG_CACHE_HOME/youtube-dl or
-                                     ~/.cache/youtube-dl . At the moment, only
-                                     YouTube player files (for videos with
-                                     obfuscated signatures) are cached, but that
-                                     may change.
+                                         ~/.cache/youtube-dl . At the moment,
+                                         only YouTube player files (for videos
+                                         with obfuscated signatures) are cached,
+                                         but that may change.
     --no-cache-dir                       Disable filesystem caching
     --rm-cache-dir                       Delete all filesystem cache files
 
-## Thumbnail images:
+## Thumbnail Options:
     --write-thumbnail                    Write thumbnail image to disk
-    --write-all-thumbnails           Write all thumbnail image formats to disk
-    --list-thumbnails                Simulate and list all available thumbnail
-                                     formats
+    --write-all-thumbnails               Write all thumbnail image formats to
+                                         disk
+    --list-thumbnails                    Simulate and list all available
+                                         thumbnail formats
 
 ## Verbosity / Simulation Options:
     -q, --quiet                          Activate quiet mode
     --no-warnings                        Ignore warnings
-    -s, --simulate                   Do not download the video and do not write
-                                     anything to disk
+    -s, --simulate                       Do not download the video and do not
+                                         write anything to disk
     --skip-download                      Do not download the video
     -g, --get-url                        Simulate, quiet but print URL
     -e, --get-title                      Simulate, quiet but print title
     --get-id                             Simulate, quiet but print id
     --get-thumbnail                      Simulate, quiet but print thumbnail URL
-    --get-description                Simulate, quiet but print video description
+    --get-description                    Simulate, quiet but print video
+                                         description
     --get-duration                       Simulate, quiet but print video length
-    --get-filename                   Simulate, quiet but print output filename
+    --get-filename                       Simulate, quiet but print output
+                                         filename
     --get-format                         Simulate, quiet but print output format
-    -j, --dump-json                  Simulate, quiet but print JSON information.
-                                     See the "OUTPUT TEMPLATE" for a description
-                                     of available keys.
-    -J, --dump-single-json           Simulate, quiet but print JSON information
-                                     for each command-line argument. If the URL
-                                     refers to a playlist, dump the whole
-                                     playlist information in a single line.
-    --print-json                     Be quiet and print the video information as
-                                     JSON (video is still being downloaded).
+    -j, --dump-json                      Simulate, quiet but print JSON
+                                         information. See the "OUTPUT TEMPLATE"
+                                         for a description of available keys.
+    -J, --dump-single-json               Simulate, quiet but print JSON
+                                         information for each command-line
+                                         argument. If the URL refers to a
+                                         playlist, dump the whole playlist
+                                         information in a single line.
+    --print-json                         Be quiet and print the video
+                                         information as JSON (video is still
+                                         being downloaded).
     --newline                            Output progress bar as new lines
     --no-progress                        Do not print progress bar
     --console-title                      Display progress in console titlebar
     -v, --verbose                        Print various debugging information
-    --dump-pages                     Print downloaded pages encoded using base64
-                                     to debug problems (very verbose)
+    --dump-pages                         Print downloaded pages encoded using
+                                         base64 to debug problems (very verbose)
     --write-pages                        Write downloaded intermediary pages to
                                          files in the current directory to debug
                                          problems
     --print-traffic                      Display sent and read HTTP traffic
-    -C, --call-home                  Contact the youtube-dl server for debugging
-    --no-call-home                   Do NOT contact the youtube-dl server for
+    -C, --call-home                      Contact the youtube-dl server for
                                          debugging
+    --no-call-home                       Do NOT contact the youtube-dl server
+                                         for debugging
 
 ## Workarounds:
-    --encoding ENCODING              Force the specified encoding (experimental)
+    --encoding ENCODING                  Force the specified encoding
+                                         (experimental)
     --no-check-certificate               Suppress HTTPS certificate validation
-    --prefer-insecure                Use an unencrypted connection to retrieve
-                                     information about the video. (Currently
-                                     supported only for YouTube)
+    --prefer-insecure                    Use an unencrypted connection to
+                                         retrieve information about the video.
+                                         (Currently supported only for YouTube)
     --user-agent UA                      Specify a custom user agent
-    --referer URL                    Specify a custom referer, use if the video
-                                     access is restricted to one domain
-    --add-header FIELD:VALUE         Specify a custom HTTP header and its value,
-                                     separated by a colon ':'. You can use this
-                                     option multiple times
+    --referer URL                        Specify a custom referer, use if the
+                                         video access is restricted to one
+                                         domain
+    --add-header FIELD:VALUE             Specify a custom HTTP header and its
+                                         value, separated by a colon ':'. You
+                                         can use this option multiple times
     --bidi-workaround                    Work around terminals that lack
-                                     bidirectional text support. Requires bidiv
-                                     or fribidi executable in PATH
+                                         bidirectional text support. Requires
+                                         bidiv or fribidi executable in PATH
     --sleep-interval SECONDS             Number of seconds to sleep before each
-                                     download when used alone or a lower bound
-                                     of a range for randomized sleep before each
-                                     download (minimum possible number of
-                                     seconds to sleep) when used along with
-                                     --max-sleep-interval.
-    --max-sleep-interval SECONDS     Upper bound of a range for randomized sleep
-                                     before each download (maximum possible
-                                     number of seconds to sleep). Must only be
-                                     used along with --min-sleep-interval.
+                                         download when used alone or a lower
+                                         bound of a range for randomized sleep
+                                         before each download (minimum possible
+                                         number of seconds to sleep) when used
+                                         along with --max-sleep-interval.
+    --max-sleep-interval SECONDS         Upper bound of a range for randomized
+                                         sleep before each download (maximum
+                                         possible number of seconds to sleep).
+                                         Must only be used along with --min-
+                                         sleep-interval.
 
 ## Video Format Options:
     -f, --format FORMAT                  Video format code, see the "FORMAT
                                          SELECTION" for all the info
     --all-formats                        Download all available video formats
-    --prefer-free-formats            Prefer free video formats unless a specific
-                                     one is requested
+    --prefer-free-formats                Prefer free video formats unless a
+                                         specific one is requested
     -F, --list-formats                   List all available formats of requested
                                          videos
     --youtube-skip-dash-manifest         Do not download the DASH manifests and
@@ -350,94 +378,103 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
     --merge-output-format FORMAT         If a merge is required (e.g.
                                          bestvideo+bestaudio), output to given
                                          container format. One of mkv, mp4, ogg,
-                                     webm, flv. Ignored if no merge is required
+                                         webm, flv. Ignored if no merge is
+                                         required
 
 ## Subtitle Options:
     --write-sub                          Write subtitle file
-    --write-auto-sub                 Write automatically generated subtitle file
-                                     (YouTube only)
-    --all-subs                       Download all the available subtitles of the
+    --write-auto-sub                     Write automatically generated subtitle
+                                         file (YouTube only)
+    --all-subs                           Download all the available subtitles of
+                                         the video
+    --list-subs                          List all available subtitles for the
                                          video
-    --list-subs                      List all available subtitles for the video
     --sub-format FORMAT                  Subtitle format, accepts formats
                                          preference, for example: "srt" or
                                          "ass/srt/best"
     --sub-lang LANGS                     Languages of the subtitles to download
-                                     (optional) separated by commas, use --list-
-                                     subs for available language tags
+                                         (optional) separated by commas, use
+                                         --list-subs for available language tags
 
 ## Authentication Options:
     -u, --username USERNAME              Login with this account ID
-    -p, --password PASSWORD          Account password. If this option is left
-                                     out, youtube-dl will ask interactively.
+    -p, --password PASSWORD              Account password. If this option is
+                                         left out, youtube-dl will ask
+                                         interactively.
     -2, --twofactor TWOFACTOR            Two-factor authentication code
     -n, --netrc                          Use .netrc authentication data
     --video-password PASSWORD            Video password (vimeo, youku)
 
 ## Adobe Pass Options:
     --ap-mso MSO                         Adobe Pass multiple-system operator (TV
-                                     provider) identifier, use --ap-list-mso for
-                                     a list of available MSOs
+                                         provider) identifier, use --ap-list-mso
+                                         for a list of available MSOs
     --ap-username USERNAME               Multiple-system operator account login
-    --ap-password PASSWORD           Multiple-system operator account password.
-                                     If this option is left out, youtube-dl will
-                                     ask interactively.
+    --ap-password PASSWORD               Multiple-system operator account
+                                         password. If this option is left out,
+                                         youtube-dl will ask interactively.
     --ap-list-mso                        List all supported multiple-system
                                          operators
 
 ## Post-processing Options:
     -x, --extract-audio                  Convert video files to audio-only files
-                                     (requires ffmpeg or avconv and ffprobe or
-                                     avprobe)
+                                         (requires ffmpeg/avconv and
+                                         ffprobe/avprobe)
     --audio-format FORMAT                Specify audio format: "best", "aac",
-                                     "flac", "mp3", "m4a", "opus", "vorbis", or
-                                     "wav"; "best" by default; No effect without
-                                     -x
-    --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert
-                                     a value between 0 (better) and 9 (worse)
-                                     for VBR or a specific bitrate like 128K
-                                     (default 5)
+                                         "flac", "mp3", "m4a", "opus", "vorbis",
+                                         or "wav"; "best" by default; No effect
+                                         without -x
+    --audio-quality QUALITY              Specify ffmpeg/avconv audio quality,
+                                         insert a value between 0 (better) and 9
+                                         (worse) for VBR or a specific bitrate
+                                         like 128K (default 5)
     --recode-video FORMAT                Encode the video to another format if
                                          necessary (currently supported:
                                          mp4|flv|ogg|webm|mkv|avi)
-    --postprocessor-args ARGS        Give these arguments to the postprocessor
-    -k, --keep-video                 Keep the video file on disk after the post-
-                                     processing; the video is erased by default
-    --no-post-overwrites             Do not overwrite post-processed files; the
-                                     post-processed files are overwritten by
+    --postprocessor-args ARGS            Give these arguments to the
+                                         postprocessor
+    -k, --keep-video                     Keep the video file on disk after the
+                                         post-processing; the video is erased by
                                          default
-    --embed-subs                     Embed subtitles in the video (only for mp4,
-                                     webm and mkv videos)
-    --embed-thumbnail                Embed thumbnail in the audio as cover art
+    --no-post-overwrites                 Do not overwrite post-processed files;
+                                         the post-processed files are
+                                         overwritten by default
+    --embed-subs                         Embed subtitles in the video (only for
+                                         mp4, webm and mkv videos)
+    --embed-thumbnail                    Embed thumbnail in the audio as cover
+                                         art
     --add-metadata                       Write metadata to the video file
-    --metadata-from-title FORMAT     Parse additional metadata like song title /
-                                     artist from the video title. The format
-                                     syntax is the same as --output. Regular
-                                     expression with named capture groups may
-                                     also be used. The parsed parameters replace
-                                     existing values. Example: --metadata-from-
-                                     title "%(artist)s - %(title)s" matches a
-                                     title like "Coldplay - Paradise". Example
-                                     (regex): --metadata-from-title
+    --metadata-from-title FORMAT         Parse additional metadata like song
+                                         title / artist from the video title.
+                                         The format syntax is the same as
+                                         --output. Regular expression with named
+                                         capture groups may also be used. The
+                                         parsed parameters replace existing
+                                         values. Example: --metadata-from-title
+                                         "%(artist)s - %(title)s" matches a
+                                         title like "Coldplay - Paradise".
+                                         Example (regex): --metadata-from-title
                                          "(?P<artist>.+?) - (?P<title>.+)"
-    --xattrs                         Write metadata to the video file's xattrs
-                                     (using dublin core and xdg standards)
-    --fixup POLICY                   Automatically correct known faults of the
-                                     file. One of never (do nothing), warn (only
-                                     emit a warning), detect_or_warn (the
-                                     default; fix file if we can, warn
-                                     otherwise)
-    --prefer-avconv                  Prefer avconv over ffmpeg for running the
-                                     postprocessors
-    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
-                                     postprocessors (default)
+    --xattrs                             Write metadata to the video file's
+                                         xattrs (using dublin core and xdg
+                                         standards)
+    --fixup POLICY                       Automatically correct known faults of
+                                         the file. One of never (do nothing),
+                                         warn (only emit a warning),
+                                         detect_or_warn (the default; fix file
+                                         if we can, warn otherwise)
+    --prefer-avconv                      Prefer avconv over ffmpeg for running
+                                         the postprocessors
+    --prefer-ffmpeg                      Prefer ffmpeg over avconv for running
+                                         the postprocessors (default)
     --ffmpeg-location PATH               Location of the ffmpeg/avconv binary;
                                          either the path to the binary or its
                                          containing directory.
     --exec CMD                           Execute a command on the file after
-                                     downloading and post-processing, similar to
-                                     find's -exec syntax. Example: --exec 'adb
-                                     push {} /sdcard/Music/ && rm {}'
+                                         downloading and post-processing,
+                                         similar to find's -exec syntax.
+                                         Example: --exec 'adb push {}
+                                         /sdcard/Music/ && rm {}'
     --convert-subs FORMAT                Convert the subtitles to other format
                                          (currently supported: srt|ass|vtt|lrc)
 
@@ -583,7 +620,7 @@ Available for the media that is a track or a part of a music album:
  - `disc_number` (numeric): Number of the disc or other physical medium the track belongs to
  - `release_year` (numeric): Year (YYYY) when the album was released
 
-Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with `NA`.
+Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default).
 
 For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj`, this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory.
 
@@ -856,7 +893,7 @@ Since June 2012 ([#342](https://github.com/ytdl-org/youtube-dl/issues/342)) yout
 
 ### The exe throws an error due to missing `MSVCR100.dll`
 
-To run the exe you need to install first the [Microsoft Visual C++ 2010 Redistributable Package (x86)](https://www.microsoft.com/en-US/download/details.aspx?id=5555).
+To run the exe you need to install first the [Microsoft Visual C++ 2010 Service Pack 1 Redistributable Package (x86)](https://download.microsoft.com/download/1/6/5/165255E7-1014-4D0A-B094-B6A430A6BFFC/vcredist_x86.exe).
 
 ### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files?
 
@@ -1032,9 +1069,11 @@ After you have ensured this site is distributing its content legally, you can fo
             }
     ```
 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
-6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
-7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
-8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://flake8.pycqa.org/en/latest/index.html#quickstart):
+6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test (actually, test case) then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note:
+    * the test names use the extractor class name **without the trailing `IE`**
+    * tests with `only_matching` key in test's dict are not counted.
+8. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
+9. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://flake8.pycqa.org/en/latest/index.html#quickstart):
 
         $ flake8 youtube_dl/extractor/yourextractor.py
 

devscripts/install_jython.sh

@@ -1,5 +0,0 @@
-#!/bin/bash
-
-wget http://central.maven.org/maven2/org/python/jython-installer/2.7.1/jython-installer-2.7.1.jar
-java -jar jython-installer-2.7.1.jar -s -d "$HOME/jython"
-$HOME/jython/bin/jython -m pip install nose

docs/supportedsites.md

@@ -1,9 +1,9 @@
 # Supported sites
  - **1tv**: Первый канал
- - **1up.com**
  - **20min**
  - **220.ro**
  - **23video**
+ - **247sports**
  - **24video**
  - **3qsdn**: 3Q SDN
  - **3sat**
@@ -46,14 +46,16 @@
  - **Amara**
  - **AMCNetworks**
  - **AmericasTestKitchen**
+ - **AmericasTestKitchenSeason**
  - **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
  - **AnimeOnDemand**
  - **Anvato**
- - **aol.com**
+ - **aol.com**: Yahoo screen and movies
  - **APA**
  - **Aparat**
  - **AppleConnect**
  - **AppleDaily**: 臺灣蘋果日報
+ - **ApplePodcasts**
  - **appletrailers**
  - **appletrailers:section**
  - **archive.org**: archive.org videos
@@ -81,6 +83,7 @@
  - **awaan:video**
  - **AZMedien**: AZ Medien videos
  - **BaiduVideo**: 百度视频
+ - **bandaichannel**
  - **Bandcamp**
  - **Bandcamp:album**
  - **Bandcamp:weekly**
@@ -88,7 +91,8 @@
  - **bbc**: BBC
  - **bbc.co.uk**: BBC iPlayer
  - **bbc.co.uk:article**: BBC articles
- - **bbc.co.uk:iplayer:playlist**
+ - **bbc.co.uk:iplayer:episodes**
+ - **bbc.co.uk:iplayer:group**
  - **bbc.co.uk:playlist**
  - **BBVTV**
  - **Beatport**
@@ -98,6 +102,10 @@
  - **BellMedia**
  - **Bet**
  - **bfi:player**
+ - **bfmtv**
+ - **bfmtv:article**
+ - **bfmtv:live**
+ - **BibelTV**
  - **Bigflix**
  - **Bild**: Bild.de
  - **BiliBili**
@@ -111,7 +119,6 @@
  - **BitChuteChannel**
  - **BleacherReport**
  - **BleacherReportCMS**
- - **blinkx**
  - **Bloomberg**
  - **BokeCC**
  - **BongaCams**
@@ -153,7 +160,8 @@
  - **cbsnews**: CBS News
  - **cbsnews:embed**
  - **cbsnews:livevideo**: CBS News Live Videos
- - **CBSSports**
+ - **cbssports**
+ - **cbssports:embed**
  - **CCMA**
  - **CCTV**: 央视网
  - **CDA**
@@ -187,8 +195,6 @@
  - **CNNArticle**
  - **CNNBlogs**
  - **ComedyCentral**
- - **ComedyCentralFullEpisodes**
- - **ComedyCentralShortname**
  - **ComedyCentralTV**
  - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
  - **CONtv**
@@ -209,6 +215,7 @@
  - **curiositystream**
  - **curiositystream:collection**
  - **CWTV**
+ - **DagelijkseKost**: dagelijksekost.een.be
  - **DailyMail**
  - **dailymotion**
  - **dailymotion:playlist**
@@ -230,6 +237,7 @@
  - **DiscoveryGo**
  - **DiscoveryGoPlaylist**
  - **DiscoveryNetworksDe**
+ - **DiscoveryPlus**
  - **DiscoveryVR**
  - **Disney**
  - **dlive:stream**
@@ -325,6 +333,7 @@
  - **Gaskrank**
  - **Gazeta**
  - **GDCVault**
+ - **GediDigital**
  - **generic**: Generic downloader that works on some sites
  - **Gfycat**
  - **GiantBomb**
@@ -336,6 +345,8 @@
  - **Go**
  - **GodTube**
  - **Golem**
+ - **google:podcasts**
+ - **google:podcasts:feed**
  - **GoogleDrive**
  - **Goshgay**
  - **GPUTechConf**
@@ -348,6 +359,7 @@
  - **HentaiStigma**
  - **hetklokhuis**
  - **hgtv.com:show**
+ - **HGTVDe**
  - **HiDive**
  - **HistoricFilms**
  - **history:player**
@@ -370,6 +382,10 @@
  - **HungamaSong**
  - **Hypem**
  - **ign.com**
+ - **IGNArticle**
+ - **IGNVideo**
+ - **IHeartRadio**
+ - **iheartradio:podcast**
  - **imdb**: Internet Movie Database trailers
  - **imdb:list**: Internet Movie Database lists
  - **Imgur**
@@ -409,7 +425,8 @@
  - **Katsomo**
  - **KeezMovies**
  - **Ketnet**
- - **KhanAcademy**
+ - **khanacademy**
+ - **khanacademy:unit**
  - **KickStarter**
  - **KinjaEmbed**
  - **KinoPoisk**
@@ -447,14 +464,14 @@
  - **limelight**
  - **limelight:channel**
  - **limelight:channel_list**
+ - **LineLive**
+ - **LineLiveChannel**
  - **LineTV**
  - **linkedin:learning**
  - **linkedin:learning:course**
  - **LinuxAcademy**
  - **LiTV**
  - **LiveJournal**
- - **LiveLeak**
- - **LiveLeakEmbed**
  - **livestream**
  - **livestream:original**
  - **LnkGo**
@@ -472,6 +489,7 @@
  - **mangomolo:live**
  - **mangomolo:video**
  - **ManyVids**
+ - **MaoriTV**
  - **Markiza**
  - **MarkizaPage**
  - **massengeschmack.tv**
@@ -496,6 +514,9 @@
  - **Mgoon**
  - **MGTV**: 芒果TV
  - **MiaoPai**
+ - **minds**
+ - **minds:channel**
+ - **minds:group**
  - **MinistryGrid**
  - **Minoto**
  - **miomio.tv**
@@ -504,6 +525,7 @@
  - **mixcloud:playlist**
  - **mixcloud:user**
  - **MLB**
+ - **MLBVideo**
  - **Mnet**
  - **MNetTV**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
@@ -525,6 +547,7 @@
  - **mtv:video**
  - **mtvjapan**
  - **mtvservices:embedded**
+ - **MTVUutisetArticle**
  - **MuenchenTV**: münchen.tv
  - **mva**: Microsoft Virtual Academy videos
  - **mva:course**: Microsoft Virtual Academy courses
@@ -658,12 +681,14 @@
  - **OutsideTV**
  - **PacktPub**
  - **PacktPubCourse**
+ - **PalcoMP3:artist**
+ - **PalcoMP3:song**
+ - **PalcoMP3:video**
  - **pandora.tv**: 판도라TV
  - **ParamountNetwork**
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
  - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET  (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
- - **pcmag**
  - **PearVideo**
  - **PeerTube**
  - **People**
@@ -685,13 +710,13 @@
  - **play.fm**
  - **player.sky.it**
  - **PlayPlusTV**
+ - **PlayStuff**
  - **PlaysTV**
  - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
  - **Playvid**
  - **Playwire**
  - **pluralsight**
  - **pluralsight:course**
- - **plus.google**: Google Plus
  - **podomatic**
  - **Pokemon**
  - **PolskieRadio**
@@ -791,6 +816,7 @@
  - **safari:course**: safaribooksonline.com online courses
  - **SAKTV**
  - **SaltTV**
+ - **SampleFocus**
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
  - **SBS**: sbs.com.au
@@ -813,6 +839,9 @@
  - **ShahidShow**
  - **Shared**: shared.sx
  - **ShowRoomLive**
+ - **simplecast**
+ - **simplecast:episode**
+ - **simplecast:podcast**
  - **Sina**
  - **sky.it**
  - **sky:news**
@@ -850,6 +879,8 @@
  - **Sport5**
  - **SportBox**
  - **SportDeutschland**
+ - **spotify**
+ - **spotify:show**
  - **Spreaker**
  - **SpreakerPage**
  - **SpreakerShow**
@@ -862,6 +893,10 @@
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **Stitcher**
+ - **StitcherShow**
+ - **StoryFire**
+ - **StoryFireSeries**
+ - **StoryFireUser**
  - **Streamable**
  - **streamcloud.eu**
  - **StreamCZ**
@@ -930,12 +965,13 @@
  - **TNAFlixNetworkEmbed**
  - **toggle**
  - **ToonGoggles**
- - **Tosh**: Tosh.0
  - **tou.tv**
  - **Toypics**: Toypics video
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
+ - **Trovo**
+ - **TrovoVod**
  - **TruNews**
  - **TruTV**
  - **Tube8**
@@ -1029,6 +1065,7 @@
  - **Vidbit**
  - **Viddler**
  - **Videa**
+ - **video.arnes.si**: Arnes Video
  - **video.google:search**: Google Video search
  - **video.sky.it**
  - **video.sky.it:live**
@@ -1043,7 +1080,6 @@
  - **vidme**
  - **vidme:user**
  - **vidme:user:likes**
- - **Vidzi**
  - **vier**: vier.be and vijf.be
  - **vier:videos**
  - **viewlift**
@@ -1088,6 +1124,7 @@
  - **vrv**
  - **vrv:series**
  - **VShare**
+ - **VTM**
  - **VTXTV**
  - **vube**: Vube.com
  - **VuClip**
@@ -1123,7 +1160,7 @@
  - **WWE**
  - **XBef**
  - **XboxClips**
- - **XFileShare**: XFileShare based sites: ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing
+ - **XFileShare**: XFileShare based sites: Aparat, ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, WolfStream, XVideoSharing
  - **XHamster**
  - **XHamsterEmbed**
  - **XHamsterUser**
@@ -1182,5 +1219,8 @@
  - **ZattooLive**
  - **ZDF**
  - **ZDFChannel**
+ - **Zhihu**
  - **zingmp3**: mp3.zing.vn
+ - **zingmp3:album**
+ - **zoom**
  - **Zype**

test/helper.py

@@ -128,6 +128,12 @@ def expect_value(self, got, expected, field):
         self.assertTrue(
             contains_str in got,
             'field %s (value: %r) should contain %r' % (field, got, contains_str))
+    elif isinstance(expected, compat_str) and re.match(r'^lambda \w+:', expected):
+        fn = eval(expected)
+        suite = expected.split(':', 1)[1].strip()
+        self.assertTrue(
+            fn(got),
+            'Expected field %s to meet condition %s, but value %r failed ' % (field, suite, got))
     elif isinstance(expected, type):
         self.assertTrue(
             isinstance(got, expected),
@@ -137,7 +143,7 @@ def expect_value(self, got, expected, field):
     elif isinstance(expected, list) and isinstance(got, list):
         self.assertEqual(
             len(expected), len(got),
-            'Expect a list of length %d, but got a list of length %d for field %s' % (
+            'Expected a list of length %d, but got a list of length %d for field %s' % (
                 len(expected), len(got), field))
         for index, (item_got, item_expected) in enumerate(zip(got, expected)):
             type_got = type(item_got)

test/parameters.json

@@ -18,7 +18,6 @@
     "noprogress": false, 
     "outtmpl": "%(id)s.%(ext)s", 
     "password": null, 
-    "playlistend": -1, 
     "playliststart": 1, 
     "prefer_free_formats": false, 
     "quiet": false, 

test/test_YoutubeDL.py

@@ -464,6 +464,7 @@ class TestFormatSelection(unittest.TestCase):
         assert_syntax_error('+bestaudio')
         assert_syntax_error('bestvideo+')
         assert_syntax_error('/')
+        assert_syntax_error('bestvideo+bestvideo+bestaudio')
 
     def test_format_filtering(self):
         formats = [
@@ -632,13 +633,20 @@ class TestYoutubeDL(unittest.TestCase):
             'title2': '%PATH%',
         }
 
-        def fname(templ):
-            ydl = YoutubeDL({'outtmpl': templ})
+        def fname(templ, na_placeholder='NA'):
+            params = {'outtmpl': templ}
+            if na_placeholder != 'NA':
+                params['outtmpl_na_placeholder'] = na_placeholder
+            ydl = YoutubeDL(params)
             return ydl.prepare_filename(info)
         self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4')
         self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
-        # Replace missing fields with 'NA'
-        self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
+        NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(id)s.%(ext)s'
+        # Replace missing fields with 'NA' by default
+        self.assertEqual(fname(NA_TEST_OUTTMPL), 'NA-NA-1234.mp4')
+        # Or by provided placeholder
+        self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder='none'), 'none-none-1234.mp4')
+        self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder=''), '--1234.mp4')
         self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4')
         self.assertEqual(fname('%(height)6d.%(ext)s'), '  1080.mp4')
         self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080  .mp4')
@@ -989,6 +997,25 @@ class TestYoutubeDL(unittest.TestCase):
         self.assertEqual(downloaded['extractor'], 'Video')
         self.assertEqual(downloaded['extractor_key'], 'Video')
 
+    def test_default_times(self):
+        """Test addition of missing upload/release/_date from /release_/timestamp"""
+        info = {
+            'id': '1234',
+            'url': TEST_URL,
+            'title': 'Title',
+            'ext': 'mp4',
+            'timestamp': 1631352900,
+            'release_timestamp': 1632995931,
+        }
+
+        params = {'simulate': True, }
+        ydl = FakeYDL(params)
+        out_info = ydl.process_ie_result(info)
+        self.assertTrue(isinstance(out_info['upload_date'], compat_str))
+        self.assertEqual(out_info['upload_date'], '20210911')
+        self.assertTrue(isinstance(out_info['release_date'], compat_str))
+        self.assertEqual(out_info['release_date'], '20210930')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_aes.py

@@ -8,7 +8,7 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_cbc_encrypt, aes_decrypt_text
+from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_cbc_encrypt, aes_decrypt_text, aes_ecb_encrypt
 from youtube_dl.utils import bytes_to_intlist, intlist_to_bytes
 import base64
 
@@ -58,6 +58,13 @@ class TestAES(unittest.TestCase):
         decrypted = (aes_decrypt_text(encrypted, password, 32))
         self.assertEqual(decrypted, self.secret_msg)
 
+    def test_ecb_encrypt(self):
+        data = bytes_to_intlist(self.secret_msg)
+        encrypted = intlist_to_bytes(aes_ecb_encrypt(data, self.key))
+        self.assertEqual(
+            encrypted,
+            b'\xaa\x86]\x81\x97>\x02\x92\x9d\x1bR[[L/u\xd3&\xd1(h\xde{\x81\x94\xba\x02\xae\xbd\xa6\xd0:')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_all_urls.py

@@ -66,18 +66,9 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:tab'])
         self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:tab'])
 
-    # def test_youtube_search_matching(self):
-    #     self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
-    #     self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
-
-    def test_youtube_extract(self):
-        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
-        assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
-        assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
-        assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
-        assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
-        assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
-        assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
+    def test_youtube_search_matching(self):
+        self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
+        self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
 
     def test_facebook_matching(self):
         self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))

test/test_cache.py

@@ -3,17 +3,18 @@
 
 from __future__ import unicode_literals
 
-import shutil
-
 # Allow direct execution
 import os
 import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
+import shutil
 
 from test.helper import FakeYDL
 from youtube_dl.cache import Cache
+from youtube_dl.utils import version_tuple
+from youtube_dl.version import __version__
 
 
 def _is_empty(d):
@@ -54,6 +55,17 @@ class TestCache(unittest.TestCase):
         self.assertFalse(os.path.exists(self.test_dir))
         self.assertEqual(c.load('test_cache', 'k.'), None)
 
+    def test_cache_validation(self):
+        ydl = FakeYDL({
+            'cachedir': self.test_dir,
+        })
+        c = Cache(ydl)
+        obj = {'x': 1, 'y': ['ä', '\\a', True]}
+        c.store('test_cache', 'k.', obj)
+        self.assertEqual(c.load('test_cache', 'k.', min_ver='1970.01.01'), obj)
+        new_version = '.'.join(('%d' % ((v + 1) if i == 0 else v, )) for i, v in enumerate(version_tuple(__version__)))
+        self.assertIs(c.load('test_cache', 'k.', min_ver=new_version), None)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_compat.py

@@ -11,6 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
 from youtube_dl.compat import (
+    compat_casefold,
     compat_getenv,
     compat_setenv,
     compat_etree_Element,
@@ -118,9 +119,21 @@ class TestCompat(unittest.TestCase):
 <smil xmlns="http://www.w3.org/2001/SMIL20/Language"></smil>'''
         compat_etree_fromstring(xml)
 
-    def test_struct_unpack(self):
+    def test_compat_struct_unpack(self):
         self.assertEqual(compat_struct_unpack('!B', b'\x00'), (0,))
 
+    def test_compat_casefold(self):
+        if hasattr(compat_str, 'casefold'):
+            # don't bother to test str.casefold() (again)
+            return
+        # thanks https://bugs.python.org/file24232/casefolding.patch
+        self.assertEqual(compat_casefold('hello'), 'hello')
+        self.assertEqual(compat_casefold('hELlo'), 'hello')
+        self.assertEqual(compat_casefold('ß'), 'ss')
+        self.assertEqual(compat_casefold('fi'), 'fi')
+        self.assertEqual(compat_casefold('\u03a3'), '\u03c3')
+        self.assertEqual(compat_casefold('A\u0345\u03a3'), 'a\u03b9\u03c3')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -33,6 +33,7 @@ from youtube_dl.compat import (
 from youtube_dl.utils import (
     DownloadError,
     ExtractorError,
+    error_to_compat_str,
     format_bytes,
     UnavailableVideoError,
 )
@@ -100,27 +101,28 @@ def generator(test_case, tname):
 
         def print_skipping(reason):
             print('Skipping %s: %s' % (test_case['name'], reason))
+            self.skipTest(reason)
+
         if not ie.working():
             print_skipping('IE marked as not _WORKING')
-            return
 
         for tc in test_cases:
             info_dict = tc.get('info_dict', {})
             if not (info_dict.get('id') and info_dict.get('ext')):
-                raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
+                raise Exception('Test definition (%s) requires both \'id\' and \'ext\' keys present to define the output file' % (tname, ))
 
         if 'skip' in test_case:
             print_skipping(test_case['skip'])
-            return
+
         for other_ie in other_ies:
             if not other_ie.working():
                 print_skipping('test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
-                return
 
         params = get_params(test_case.get('params', {}))
         params['outtmpl'] = tname + '_' + params['outtmpl']
         if is_playlist and 'playlist' not in test_case:
             params.setdefault('extract_flat', 'in_playlist')
+            params.setdefault('playlistend', test_case.get('playlist_mincount'))
             params.setdefault('skip_download', True)
 
         ydl = YoutubeDL(params, auto_init=False)
@@ -160,7 +162,9 @@ def generator(test_case, tname):
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
                     if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
-                        raise
+                        msg = getattr(err, 'msg', error_to_compat_str(err))
+                        err.msg = '%s (%s)' % (msg, tname, )
+                        raise err
 
                     if try_num == RETRIES:
                         report_warning('%s failed due to network errors, skipping...' % tname)

test/test_execution.py

@@ -39,6 +39,16 @@ class TestExecution(unittest.TestCase):
         _, stderr = p.communicate()
         self.assertFalse(stderr)
 
+    def test_lazy_extractors(self):
+        try:
+            subprocess.check_call([sys.executable, 'devscripts/make_lazy_extractors.py', 'youtube_dl/extractor/lazy_extractors.py'], cwd=rootDir, stdout=_DEV_NULL)
+            subprocess.check_call([sys.executable, 'test/test_all_urls.py'], cwd=rootDir, stdout=_DEV_NULL)
+        finally:
+            try:
+                os.remove('youtube_dl/extractor/lazy_extractors.py')
+            except (IOError, OSError):
+                pass
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_jsinterp.py

@@ -8,7 +8,12 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from youtube_dl.jsinterp import JSInterpreter
+import math
+import re
+
+from youtube_dl.compat import compat_re_Pattern
+
+from youtube_dl.jsinterp import JS_Undefined, JSInterpreter
 
 
 class TestJSInterpreter(unittest.TestCase):
@@ -19,6 +24,9 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function x3(){return 42;}')
         self.assertEqual(jsi.call_function('x3'), 42)
 
+        jsi = JSInterpreter('function x3(){42}')
+        self.assertEqual(jsi.call_function('x3'), None)
+
         jsi = JSInterpreter('var x5 = function(){return 42;}')
         self.assertEqual(jsi.call_function('x5'), 42)
 
@@ -45,14 +53,32 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function f(){return 1 << 5;}')
         self.assertEqual(jsi.call_function('f'), 32)
 
+        jsi = JSInterpreter('function f(){return 2 ** 5}')
+        self.assertEqual(jsi.call_function('f'), 32)
+
         jsi = JSInterpreter('function f(){return 19 & 21;}')
         self.assertEqual(jsi.call_function('f'), 17)
 
         jsi = JSInterpreter('function f(){return 11 >> 2;}')
         self.assertEqual(jsi.call_function('f'), 2)
 
+        jsi = JSInterpreter('function f(){return []? 2+3: 4;}')
+        self.assertEqual(jsi.call_function('f'), 5)
+
+        jsi = JSInterpreter('function f(){return 1 == 2}')
+        self.assertEqual(jsi.call_function('f'), False)
+
+        jsi = JSInterpreter('function f(){return 0 && 1 || 2;}')
+        self.assertEqual(jsi.call_function('f'), 2)
+
+        jsi = JSInterpreter('function f(){return 0 ?? 42;}')
+        self.assertEqual(jsi.call_function('f'), 0)
+
+        jsi = JSInterpreter('function f(){return "life, the universe and everything" < 42;}')
+        self.assertFalse(jsi.call_function('f'))
+
     def test_array_access(self):
-        jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
+        jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2.0] = 7; return x;}')
         self.assertEqual(jsi.call_function('f'), [5, 2, 7])
 
     def test_parens(self):
@@ -62,6 +88,10 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
         self.assertEqual(jsi.call_function('f'), 9)
 
+    def test_quotes(self):
+        jsi = JSInterpreter(r'function f(){return "a\"\\("}')
+        self.assertEqual(jsi.call_function('f'), r'a"\(')
+
     def test_assignments(self):
         jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
         self.assertEqual(jsi.call_function('f'), 31)
@@ -104,13 +134,277 @@ class TestJSInterpreter(unittest.TestCase):
         }''')
         self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
 
+    def test_builtins(self):
+        jsi = JSInterpreter('''
+        function x() { return NaN }
+        ''')
+        self.assertTrue(math.isnan(jsi.call_function('x')))
+
+        jsi = JSInterpreter('''
+        function x() { return new Date('Wednesday 31 December 1969 18:01:26 MDT') - 0; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 86000)
+        jsi = JSInterpreter('''
+        function x(dt) { return new Date(dt) - 0; }
+        ''')
+        self.assertEqual(jsi.call_function('x', 'Wednesday 31 December 1969 18:01:26 MDT'), 86000)
+
     def test_call(self):
         jsi = JSInterpreter('''
         function x() { return 2; }
-        function y(a) { return x() + a; }
+        function y(a) { return x() + (a?a:0); }
         function z() { return y(3); }
         ''')
         self.assertEqual(jsi.call_function('z'), 5)
+        self.assertEqual(jsi.call_function('y'), 2)
+
+    def test_for_loop(self):
+        # function x() { a=0; for (i=0; i-10; i++) {a++} a }
+        jsi = JSInterpreter('''
+        function x() { a=0; for (i=0; i-10; i++) {a++} return a }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 10)
+
+    def test_switch(self):
+        jsi = JSInterpreter('''
+        function x(f) { switch(f){
+            case 1:f+=1;
+            case 2:f+=2;
+            case 3:f+=3;break;
+            case 4:f+=4;
+            default:f=0;
+        } return f }
+        ''')
+        self.assertEqual(jsi.call_function('x', 1), 7)
+        self.assertEqual(jsi.call_function('x', 3), 6)
+        self.assertEqual(jsi.call_function('x', 5), 0)
+
+    def test_switch_default(self):
+        jsi = JSInterpreter('''
+        function x(f) { switch(f){
+            case 2: f+=2;
+            default: f-=1;
+            case 5:
+            case 6: f+=6;
+            case 0: break;
+            case 1: f+=1;
+        } return f }
+        ''')
+        self.assertEqual(jsi.call_function('x', 1), 2)
+        self.assertEqual(jsi.call_function('x', 5), 11)
+        self.assertEqual(jsi.call_function('x', 9), 14)
+
+    def test_try(self):
+        jsi = JSInterpreter('''
+        function x() { try{return 10} catch(e){return 5} }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 10)
+
+    def test_catch(self):
+        jsi = JSInterpreter('''
+        function x() { try{throw 10} catch(e){return 5} }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 5)
+
+    def test_finally(self):
+        jsi = JSInterpreter('''
+        function x() { try{throw 10} finally {return 42} }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 42)
+        jsi = JSInterpreter('''
+        function x() { try{throw 10} catch(e){return 5} finally {return 42} }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 42)
+
+    def test_nested_try(self):
+        jsi = JSInterpreter('''
+        function x() {try {
+            try{throw 10} finally {throw 42}
+            } catch(e){return 5} }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 5)
+
+    def test_for_loop_continue(self):
+        jsi = JSInterpreter('''
+        function x() { a=0; for (i=0; i-10; i++) { continue; a++ } return a }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 0)
+
+    def test_for_loop_break(self):
+        jsi = JSInterpreter('''
+        function x() { a=0; for (i=0; i-10; i++) { break; a++ } return a }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 0)
+
+    def test_for_loop_try(self):
+        jsi = JSInterpreter('''
+        function x() {
+            for (i=0; i-10; i++) { try { if (i == 5) throw i} catch {return 10} finally {break} };
+            return 42 }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 42)
+
+    def test_literal_list(self):
+        jsi = JSInterpreter('''
+        function x() { return [1, 2, "asdf", [5, 6, 7]][3] }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [5, 6, 7])
+
+    def test_comma(self):
+        jsi = JSInterpreter('''
+        function x() { a=5; a -= 1, a+=3; return a }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 7)
+        jsi = JSInterpreter('''
+        function x() { a=5; return (a -= 1, a+=3, a); }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 7)
+
+        jsi = JSInterpreter('''
+        function x() { return (l=[0,1,2,3], function(a, b){return a+b})((l[1], l[2]), l[3]) }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 5)
+
+    def test_void(self):
+        jsi = JSInterpreter('''
+        function x() { return void 42; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), None)
+
+    def test_return_function(self):
+        jsi = JSInterpreter('''
+        function x() { return [1, function(){return 1}][1] }
+        ''')
+        self.assertEqual(jsi.call_function('x')([]), 1)
+
+    def test_null(self):
+        jsi = JSInterpreter('''
+        function x() { return null; }
+        ''')
+        self.assertIs(jsi.call_function('x'), None)
+
+        jsi = JSInterpreter('''
+        function x() { return [null > 0, null < 0, null == 0, null === 0]; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [False, False, False, False])
+
+        jsi = JSInterpreter('''
+        function x() { return [null >= 0, null <= 0]; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [True, True])
+
+    def test_undefined(self):
+        jsi = JSInterpreter('''
+        function x() { return undefined === undefined; }
+        ''')
+        self.assertTrue(jsi.call_function('x'))
+
+        jsi = JSInterpreter('''
+        function x() { return undefined; }
+        ''')
+        self.assertIs(jsi.call_function('x'), JS_Undefined)
+
+        jsi = JSInterpreter('''
+        function x() { let v; return v; }
+        ''')
+        self.assertIs(jsi.call_function('x'), JS_Undefined)
+
+        jsi = JSInterpreter('''
+        function x() { return [undefined === undefined, undefined == undefined, undefined < undefined, undefined > undefined]; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [True, True, False, False])
+
+        jsi = JSInterpreter('''
+        function x() { return [undefined === 0, undefined == 0, undefined < 0, undefined > 0]; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [False, False, False, False])
+
+        jsi = JSInterpreter('''
+        function x() { return [undefined >= 0, undefined <= 0]; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [False, False])
+
+        jsi = JSInterpreter('''
+        function x() { return [undefined > null, undefined < null, undefined == null, undefined === null]; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [False, False, True, False])
+
+        jsi = JSInterpreter('''
+        function x() { return [undefined === null, undefined == null, undefined < null, undefined > null]; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [False, True, False, False])
+
+        jsi = JSInterpreter('''
+        function x() { let v; return [42+v, v+42, v**42, 42**v, 0**v]; }
+        ''')
+        for y in jsi.call_function('x'):
+            self.assertTrue(math.isnan(y))
+
+        jsi = JSInterpreter('''
+        function x() { let v; return v**0; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 1)
+
+        jsi = JSInterpreter('''
+        function x() { let v; return [v>42, v<=42, v&&42, 42&&v]; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [False, False, JS_Undefined, JS_Undefined])
+
+        jsi = JSInterpreter('function x(){return undefined ?? 42; }')
+        self.assertEqual(jsi.call_function('x'), 42)
+
+    def test_object(self):
+        jsi = JSInterpreter('''
+        function x() { return {}; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), {})
+
+        jsi = JSInterpreter('''
+        function x() { let a = {m1: 42, m2: 0 }; return [a["m1"], a.m2]; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), [42, 0])
+
+        jsi = JSInterpreter('''
+        function x() { let a; return a?.qq; }
+        ''')
+        self.assertIs(jsi.call_function('x'), JS_Undefined)
+
+        jsi = JSInterpreter('''
+        function x() { let a = {m1: 42, m2: 0 }; return a?.qq; }
+        ''')
+        self.assertIs(jsi.call_function('x'), JS_Undefined)
+
+    def test_regex(self):
+        jsi = JSInterpreter('''
+        function x() { let a=/,,[/,913,/](,)}/; }
+        ''')
+        self.assertIs(jsi.call_function('x'), None)
+
+        jsi = JSInterpreter('''
+        function x() { let a=/,,[/,913,/](,)}/; return a; }
+        ''')
+        self.assertIsInstance(jsi.call_function('x'), compat_re_Pattern)
+
+        jsi = JSInterpreter('''
+        function x() { let a=/,,[/,913,/](,)}/i; return a; }
+        ''')
+        self.assertEqual(jsi.call_function('x').flags & ~re.U, re.I)
+
+    def test_char_code_at(self):
+        jsi = JSInterpreter('function x(i){return "test".charCodeAt(i)}')
+        self.assertEqual(jsi.call_function('x', 0), 116)
+        self.assertEqual(jsi.call_function('x', 1), 101)
+        self.assertEqual(jsi.call_function('x', 2), 115)
+        self.assertEqual(jsi.call_function('x', 3), 116)
+        self.assertEqual(jsi.call_function('x', 4), None)
+        self.assertEqual(jsi.call_function('x', 'not_a_number'), 116)
+
+    def test_bitwise_operators_overflow(self):
+        jsi = JSInterpreter('function x(){return -524999584 << 5}')
+        self.assertEqual(jsi.call_function('x'), 379882496)
+
+        jsi = JSInterpreter('function x(){return 1236566549 << 5}')
+        self.assertEqual(jsi.call_function('x'), 915423904)
 
 
 if __name__ == '__main__':

test/test_subtitles.py

@@ -38,6 +38,9 @@ class BaseTestSubtitles(unittest.TestCase):
         self.DL = FakeYDL()
         self.ie = self.IE()
         self.DL.add_info_extractor(self.ie)
+        if not self.IE.working():
+            print('Skipping: %s marked as not _WORKING' % self.IE.ie_key())
+            self.skipTest('IE marked as not _WORKING')
 
     def getInfoDict(self):
         info_dict = self.DL.extract_info(self.url, download=False)
@@ -56,6 +59,21 @@ class BaseTestSubtitles(unittest.TestCase):
 
 
 class TestYoutubeSubtitles(BaseTestSubtitles):
+    # Available subtitles for QRS8MkLhQmM:
+    # Language formats
+    # ru       vtt, ttml, srv3, srv2, srv1, json3
+    # fr       vtt, ttml, srv3, srv2, srv1, json3
+    # en       vtt, ttml, srv3, srv2, srv1, json3
+    # nl       vtt, ttml, srv3, srv2, srv1, json3
+    # de       vtt, ttml, srv3, srv2, srv1, json3
+    # ko       vtt, ttml, srv3, srv2, srv1, json3
+    # it       vtt, ttml, srv3, srv2, srv1, json3
+    # zh-Hant  vtt, ttml, srv3, srv2, srv1, json3
+    # hi       vtt, ttml, srv3, srv2, srv1, json3
+    # pt-BR    vtt, ttml, srv3, srv2, srv1, json3
+    # es-MX    vtt, ttml, srv3, srv2, srv1, json3
+    # ja       vtt, ttml, srv3, srv2, srv1, json3
+    # pl       vtt, ttml, srv3, srv2, srv1, json3
     url = 'QRS8MkLhQmM'
     IE = YoutubeIE
 
@@ -64,41 +82,60 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(len(subtitles.keys()), 13)
-        self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
-        self.assertEqual(md5(subtitles['it']), '6d752b98c31f1cf8d597050c7a2cb4b5')
+        self.assertEqual(md5(subtitles['en']), 'ae1bd34126571a77aabd4d276b28044d')
+        self.assertEqual(md5(subtitles['it']), '0e0b667ba68411d88fd1c5f4f4eab2f9')
         for lang in ['fr', 'de']:
             self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
 
-    def test_youtube_subtitles_ttml_format(self):
+    def _test_subtitles_format(self, fmt, md5_hash, lang='en'):
         self.DL.params['writesubtitles'] = True
-        self.DL.params['subtitlesformat'] = 'ttml'
+        self.DL.params['subtitlesformat'] = fmt
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), 'e306f8c42842f723447d9f63ad65df54')
+        self.assertEqual(md5(subtitles[lang]), md5_hash)
+
+    def test_youtube_subtitles_ttml_format(self):
+        self._test_subtitles_format('ttml', 'c97ddf1217390906fa9fbd34901f3da2')
 
     def test_youtube_subtitles_vtt_format(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['subtitlesformat'] = 'vtt'
+        self._test_subtitles_format('vtt', 'ae1bd34126571a77aabd4d276b28044d')
+
+    def test_youtube_subtitles_json3_format(self):
+        self._test_subtitles_format('json3', '688dd1ce0981683867e7fe6fde2a224b')
+
+    def _test_automatic_captions(self, url, lang):
+        self.url = url
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslangs'] = [lang]
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
+        self.assertTrue(subtitles[lang] is not None)
 
     def test_youtube_automatic_captions(self):
-        self.url = '8YoUxe5ncPo'
-        self.DL.params['writeautomaticsub'] = True
-        self.DL.params['subtitleslangs'] = ['it']
-        subtitles = self.getSubtitles()
-        self.assertTrue(subtitles['it'] is not None)
+        # Available automatic captions for 8YoUxe5ncPo:
+        # Language formats (all in vtt, ttml, srv3, srv2, srv1, json3)
+        # gu, zh-Hans, zh-Hant, gd, ga, gl, lb, la, lo, tt, tr,
+        # lv, lt, tk, th, tg, te, fil, haw, yi, ceb, yo, de, da,
+        # el, eo, en, eu, et, es, ru, rw, ro, bn, be, bg, uk, jv,
+        # bs, ja, or, xh, co, ca, cy, cs, ps, pt, pa, vi, pl, hy,
+        # hr, ht, hu, hmn, hi, ha, mg, uz, ml, mn, mi, mk, ur,
+        # mt, ms, mr, ug, ta, my, af, sw, is, am,
+        #                                         *it*, iw, sv, ar,
+        # su, zu, az, id, ig, nl, no, ne, ny, fr, ku, fy, fa, fi,
+        # ka, kk, sr, sq, ko, kn, km, st, sk, si, so, sn, sm, sl,
+        # ky, sd
+        # ...
+        self._test_automatic_captions('8YoUxe5ncPo', 'it')
 
+    @unittest.skip('ASR subs all in all supported langs now')
     def test_youtube_translated_subtitles(self):
-        # This video has a subtitles track, which can be translated
-        self.url = 'Ky9eprVWzlI'
-        self.DL.params['writeautomaticsub'] = True
-        self.DL.params['subtitleslangs'] = ['it']
-        subtitles = self.getSubtitles()
-        self.assertTrue(subtitles['it'] is not None)
+        # This video has a subtitles track, which can be translated (#4555)
+        self._test_automatic_captions('Ky9eprVWzlI', 'it')
 
     def test_youtube_nosubtitles(self):
         self.DL.expect_warning('video doesn\'t have subtitles')
-        self.url = 'n5BB19UTcdA'
+        # Available automatic captions for 8YoUxe5ncPo:
+        # ...
+        # 8YoUxe5ncPo has no subtitles
+        self.url = '8YoUxe5ncPo'
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
@@ -128,6 +165,7 @@ class TestDailymotionSubtitles(BaseTestSubtitles):
         self.assertFalse(subtitles)
 
 
+@unittest.skip('IE broken')
 class TestTedSubtitles(BaseTestSubtitles):
     url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html'
     IE = TEDIE
@@ -152,18 +190,19 @@ class TestVimeoSubtitles(BaseTestSubtitles):
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
-        self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
-        self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
+        self.assertEqual(md5(subtitles['en']), '386cbc9320b94e25cb364b97935e5dd1')
+        self.assertEqual(md5(subtitles['fr']), 'c9b69eef35bc6641c0d4da8a04f9dfac')
 
     def test_nosubtitles(self):
         self.DL.expect_warning('video doesn\'t have subtitles')
-        self.url = 'http://vimeo.com/56015672'
+        self.url = 'http://vimeo.com/68093876'
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertFalse(subtitles)
 
 
+@unittest.skip('IE broken')
 class TestWallaSubtitles(BaseTestSubtitles):
     url = 'http://vod.walla.co.il/movie/2705958/the-yes-men'
     IE = WallaIE
@@ -185,6 +224,7 @@ class TestWallaSubtitles(BaseTestSubtitles):
         self.assertFalse(subtitles)
 
 
+@unittest.skip('IE broken')
 class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
     url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
     IE = CeskaTelevizeIE
@@ -206,6 +246,7 @@ class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
         self.assertFalse(subtitles)
 
 
+@unittest.skip('IE broken')
 class TestLyndaSubtitles(BaseTestSubtitles):
     url = 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html'
     IE = LyndaIE
@@ -218,6 +259,7 @@ class TestLyndaSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['en']), '09bbe67222259bed60deaa26997d73a7')
 
 
+@unittest.skip('IE broken')
 class TestNPOSubtitles(BaseTestSubtitles):
     url = 'http://www.npo.nl/nos-journaal/28-08-2014/POW_00722860'
     IE = NPOIE
@@ -230,6 +272,7 @@ class TestNPOSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['nl']), 'fc6435027572b63fb4ab143abd5ad3f4')
 
 
+@unittest.skip('IE broken')
 class TestMTVSubtitles(BaseTestSubtitles):
     url = 'http://www.cc.com/video-clips/p63lk0/adam-devine-s-house-party-chasing-white-swans'
     IE = ComedyCentralIE
@@ -253,22 +296,31 @@ class TestNRKSubtitles(BaseTestSubtitles):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['no']))
-        self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2')
+        self.assertEqual(set(subtitles.keys()), set(['nb-ttv']))
+        self.assertEqual(md5(subtitles['nb-ttv']), '67e06ff02d0deaf975e68f6cb8f6a149')
 
 
 class TestRaiPlaySubtitles(BaseTestSubtitles):
-    url = 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
     IE = RaiPlayIE
 
-    def test_allsubtitles(self):
+    def test_subtitles_key(self):
+        self.url = 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(set(subtitles.keys()), set(['it']))
         self.assertEqual(md5(subtitles['it']), 'b1d90a98755126b61e667567a1f6680a')
 
+    def test_subtitles_array_key(self):
+        self.url = 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['it']))
+        self.assertEqual(md5(subtitles['it']), '4b3264186fbb103508abe5311cfcb9cd')
 
+
+@unittest.skip('IE broken - DRM only')
 class TestVikiSubtitles(BaseTestSubtitles):
     url = 'http://www.viki.com/videos/1060846v-punch-episode-18'
     IE = VikiIE
@@ -295,6 +347,7 @@ class TestThePlatformSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b')
 
 
+@unittest.skip('IE broken')
 class TestThePlatformFeedSubtitles(BaseTestSubtitles):
     url = 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207'
     IE = ThePlatformFeedIE
@@ -330,7 +383,7 @@ class TestDemocracynowSubtitles(BaseTestSubtitles):
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+        self.assertEqual(md5(subtitles['en']), 'a3cc4c0b5eadd74d9974f1c1f5101045')
 
     def test_subtitles_in_page(self):
         self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree'
@@ -338,7 +391,7 @@ class TestDemocracynowSubtitles(BaseTestSubtitles):
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+        self.assertEqual(md5(subtitles['en']), 'a3cc4c0b5eadd74d9974f1c1f5101045')
 
 
 if __name__ == '__main__':

test/test_utils.py

@@ -12,7 +12,9 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 # Various small unit tests
 import io
+import itertools
 import json
+import re
 import xml.etree.ElementTree
 
 from youtube_dl.utils import (
@@ -21,6 +23,7 @@ from youtube_dl.utils import (
     encode_base_n,
     caesar,
     clean_html,
+    clean_podcast_url,
     date_from_str,
     DateRange,
     detect_exe_version,
@@ -39,11 +42,14 @@ from youtube_dl.utils import (
     get_element_by_attribute,
     get_elements_by_class,
     get_elements_by_attribute,
+    get_first,
     InAdvancePagedList,
     int_or_none,
     intlist_to_bytes,
     is_html,
+    join_nonempty,
     js_to_json,
+    LazyList,
     limit_length,
     merge_dicts,
     mimetype2ext,
@@ -78,6 +84,8 @@ from youtube_dl.utils import (
     strip_or_none,
     subtitles_filename,
     timeconvert,
+    traverse_obj,
+    try_call,
     unescapeHTML,
     unified_strdate,
     unified_timestamp,
@@ -91,6 +99,7 @@ from youtube_dl.utils import (
     urlencode_postdata,
     urshift,
     update_url_query,
+    variadic,
     version_tuple,
     xpath_with_ns,
     xpath_element,
@@ -111,12 +120,18 @@ from youtube_dl.compat import (
     compat_getenv,
     compat_os_name,
     compat_setenv,
+    compat_str,
     compat_urlparse,
     compat_parse_qs,
 )
 
 
 class TestUtil(unittest.TestCase):
+
+    # yt-dlp shim
+    def assertCountEqual(self, expected, got, msg='count should be the same'):
+        return self.assertEqual(len(tuple(expected)), len(tuple(got)), msg=msg)
+
     def test_timeconvert(self):
         self.assertTrue(timeconvert('') is None)
         self.assertTrue(timeconvert('bougrg') is None)
@@ -369,6 +384,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
         self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
         self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
+        self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1)
+        self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86)
+        self.assertEqual(unified_timestamp('12/31/1969 20:01:18 EDT', False), 78)
 
     def test_determine_ext(self):
         self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@@ -1470,6 +1488,319 @@ Line 1
         self.assertEqual(get_elements_by_attribute('class', 'foo', html), [])
         self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), [])
 
+    def test_clean_podcast_url(self):
+        self.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3')
+        self.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3')
+
+    def test_LazyList(self):
+        it = list(range(10))
+
+        self.assertEqual(list(LazyList(it)), it)
+        self.assertEqual(LazyList(it).exhaust(), it)
+        self.assertEqual(LazyList(it)[5], it[5])
+
+        self.assertEqual(LazyList(it)[5:], it[5:])
+        self.assertEqual(LazyList(it)[:5], it[:5])
+        self.assertEqual(LazyList(it)[::2], it[::2])
+        self.assertEqual(LazyList(it)[1::2], it[1::2])
+        self.assertEqual(LazyList(it)[5::-1], it[5::-1])
+        self.assertEqual(LazyList(it)[6:2:-2], it[6:2:-2])
+        self.assertEqual(LazyList(it)[::-1], it[::-1])
+
+        self.assertTrue(LazyList(it))
+        self.assertFalse(LazyList(range(0)))
+        self.assertEqual(len(LazyList(it)), len(it))
+        self.assertEqual(repr(LazyList(it)), repr(it))
+        self.assertEqual(compat_str(LazyList(it)), compat_str(it))
+
+        self.assertEqual(list(LazyList(it, reverse=True)), it[::-1])
+        self.assertEqual(list(reversed(LazyList(it))[::-1]), it)
+        self.assertEqual(list(reversed(LazyList(it))[1:3:7]), it[::-1][1:3:7])
+
+    def test_LazyList_laziness(self):
+
+        def test(ll, idx, val, cache):
+            self.assertEqual(ll[idx], val)
+            self.assertEqual(ll._cache, list(cache))
+
+        ll = LazyList(range(10))
+        test(ll, 0, 0, range(1))
+        test(ll, 5, 5, range(6))
+        test(ll, -3, 7, range(10))
+
+        ll = LazyList(range(10), reverse=True)
+        test(ll, -1, 0, range(1))
+        test(ll, 3, 6, range(10))
+
+        ll = LazyList(itertools.count())
+        test(ll, 10, 10, range(11))
+        ll = reversed(ll)
+        test(ll, -15, 14, range(15))
+
+    def test_try_call(self):
+        def total(*x, **kwargs):
+            return sum(x) + sum(kwargs.values())
+
+        self.assertEqual(try_call(None), None,
+                         msg='not a fn should give None')
+        self.assertEqual(try_call(lambda: 1), 1,
+                         msg='int fn with no expected_type should give int')
+        self.assertEqual(try_call(lambda: 1, expected_type=int), 1,
+                         msg='int fn with expected_type int should give int')
+        self.assertEqual(try_call(lambda: 1, expected_type=dict), None,
+                         msg='int fn with wrong expected_type should give None')
+        self.assertEqual(try_call(total, args=(0, 1, 0, ), expected_type=int), 1,
+                         msg='fn should accept arglist')
+        self.assertEqual(try_call(total, kwargs={'a': 0, 'b': 1, 'c': 0}, expected_type=int), 1,
+                         msg='fn should accept kwargs')
+        self.assertEqual(try_call(lambda: 1, expected_type=dict), None,
+                         msg='int fn with no expected_type should give None')
+        self.assertEqual(try_call(lambda x: {}, total, args=(42, ), expected_type=int), 42,
+                         msg='expect first int result with expected_type int')
+
+    def test_variadic(self):
+        self.assertEqual(variadic(None), (None, ))
+        self.assertEqual(variadic('spam'), ('spam', ))
+        self.assertEqual(variadic('spam', allowed_types=dict), 'spam')
+
+    def test_traverse_obj(self):
+        _TEST_DATA = {
+            100: 100,
+            1.2: 1.2,
+            'str': 'str',
+            'None': None,
+            '...': Ellipsis,
+            'urls': [
+                {'index': 0, 'url': 'https://www.example.com/0'},
+                {'index': 1, 'url': 'https://www.example.com/1'},
+            ],
+            'data': (
+                {'index': 2},
+                {'index': 3},
+            ),
+            'dict': {},
+        }
+
+        # Test base functionality
+        self.assertEqual(traverse_obj(_TEST_DATA, ('str',)), 'str',
+                         msg='allow tuple path')
+        self.assertEqual(traverse_obj(_TEST_DATA, ['str']), 'str',
+                         msg='allow list path')
+        self.assertEqual(traverse_obj(_TEST_DATA, (value for value in ("str",))), 'str',
+                         msg='allow iterable path')
+        self.assertEqual(traverse_obj(_TEST_DATA, 'str'), 'str',
+                         msg='single items should be treated as a path')
+        self.assertEqual(traverse_obj(_TEST_DATA, None), _TEST_DATA)
+        self.assertEqual(traverse_obj(_TEST_DATA, 100), 100)
+        self.assertEqual(traverse_obj(_TEST_DATA, 1.2), 1.2)
+
+        # Test Ellipsis behavior
+        self.assertCountEqual(traverse_obj(_TEST_DATA, Ellipsis),
+                              (item for item in _TEST_DATA.values() if item is not None),
+                              msg='`...` should give all values except `None`')
+        self.assertCountEqual(traverse_obj(_TEST_DATA, ('urls', 0, Ellipsis)), _TEST_DATA['urls'][0].values(),
+                              msg='`...` selection for dicts should select all values')
+        self.assertEqual(traverse_obj(_TEST_DATA, (Ellipsis, Ellipsis, 'url')),
+                         ['https://www.example.com/0', 'https://www.example.com/1'],
+                         msg='nested `...` queries should work')
+        self.assertCountEqual(traverse_obj(_TEST_DATA, (Ellipsis, Ellipsis, 'index')), range(4),
+                              msg='`...` query result should be flattened')
+
+        # Test function as key
+        self.assertEqual(traverse_obj(_TEST_DATA, lambda x, y: x == 'urls' and isinstance(y, list)),
+                         [_TEST_DATA['urls']],
+                         msg='function as query key should perform a filter based on (key, value)')
+        self.assertCountEqual(traverse_obj(_TEST_DATA, lambda _, x: isinstance(x[0], compat_str)), {'str'},
+                              msg='exceptions in the query function should be caught')
+
+        # Test alternative paths
+        self.assertEqual(traverse_obj(_TEST_DATA, 'fail', 'str'), 'str',
+                         msg='multiple `paths` should be treated as alternative paths')
+        self.assertEqual(traverse_obj(_TEST_DATA, 'str', 100), 'str',
+                         msg='alternatives should exit early')
+        self.assertEqual(traverse_obj(_TEST_DATA, 'fail', 'fail'), None,
+                         msg='alternatives should return `default` if exhausted')
+        self.assertEqual(traverse_obj(_TEST_DATA, (Ellipsis, 'fail'), 100), 100,
+                         msg='alternatives should track their own branching return')
+        self.assertEqual(traverse_obj(_TEST_DATA, ('dict', Ellipsis), ('data', Ellipsis)), list(_TEST_DATA['data']),
+                         msg='alternatives on empty objects should search further')
+
+        # Test branch and path nesting
+        self.assertEqual(traverse_obj(_TEST_DATA, ('urls', (3, 0), 'url')), ['https://www.example.com/0'],
+                         msg='tuple as key should be treated as branches')
+        self.assertEqual(traverse_obj(_TEST_DATA, ('urls', [3, 0], 'url')), ['https://www.example.com/0'],
+                         msg='list as key should be treated as branches')
+        self.assertEqual(traverse_obj(_TEST_DATA, ('urls', ((1, 'fail'), (0, 'url')))), ['https://www.example.com/0'],
+                         msg='double nesting in path should be treated as paths')
+        self.assertEqual(traverse_obj(['0', [1, 2]], [(0, 1), 0]), [1],
+                         msg='do not fail early on branching')
+        self.assertCountEqual(traverse_obj(_TEST_DATA, ('urls', ((1, ('fail', 'url')), (0, 'url')))),
+                              ['https://www.example.com/0', 'https://www.example.com/1'],
+                              msg='triple nesting in path should be treated as branches')
+        self.assertEqual(traverse_obj(_TEST_DATA, ('urls', ('fail', (Ellipsis, 'url')))),
+                         ['https://www.example.com/0', 'https://www.example.com/1'],
+                         msg='ellipsis as branch path start gets flattened')
+
+        # Test dictionary as key
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: 100, 1: 1.2}), {0: 100, 1: 1.2},
+                         msg='dict key should result in a dict with the same keys')
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', 0, 'url')}),
+                         {0: 'https://www.example.com/0'},
+                         msg='dict key should allow paths')
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', (3, 0), 'url')}),
+                         {0: ['https://www.example.com/0']},
+                         msg='tuple in dict path should be treated as branches')
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', ((1, 'fail'), (0, 'url')))}),
+                         {0: ['https://www.example.com/0']},
+                         msg='double nesting in dict path should be treated as paths')
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', ((1, ('fail', 'url')), (0, 'url')))}),
+                         {0: ['https://www.example.com/1', 'https://www.example.com/0']},
+                         msg='triple nesting in dict path should be treated as branches')
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: 'fail'}), {},
+                         msg='remove `None` values when dict key')
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: 'fail'}, default=Ellipsis), {0: Ellipsis},
+                         msg='do not remove `None` values if `default`')
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: 'dict'}), {0: {}},
+                         msg='do not remove empty values when dict key')
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: 'dict'}, default=Ellipsis), {0: {}},
+                         msg='do not remove empty values when dict key and a default')
+        self.assertEqual(traverse_obj(_TEST_DATA, {0: ('dict', Ellipsis)}), {0: []},
+                         msg='if branch in dict key not successful, return `[]`')
+
+        # Testing default parameter behavior
+        _DEFAULT_DATA = {'None': None, 'int': 0, 'list': []}
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, 'fail'), None,
+                         msg='default value should be `None`')
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, 'fail', 'fail', default=Ellipsis), Ellipsis,
+                         msg='chained fails should result in default')
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, 'None', 'int'), 0,
+                         msg='should not short cirquit on `None`')
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, 'fail', default=1), 1,
+                         msg='invalid dict key should result in `default`')
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, 'None', default=1), 1,
+                         msg='`None` is a deliberate sentinel and should become `default`')
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, ('list', 10)), None,
+                         msg='`IndexError` should result in `default`')
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, (Ellipsis, 'fail'), default=1), 1,
+                         msg='if branched but not successful return `default` if defined, not `[]`')
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, (Ellipsis, 'fail'), default=None), None,
+                         msg='if branched but not successful return `default` even if `default` is `None`')
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, (Ellipsis, 'fail')), [],
+                         msg='if branched but not successful return `[]`, not `default`')
+        self.assertEqual(traverse_obj(_DEFAULT_DATA, ('list', Ellipsis)), [],
+                         msg='if branched but object is empty return `[]`, not `default`')
+
+        # Testing expected_type behavior
+        _EXPECTED_TYPE_DATA = {'str': 'str', 'int': 0}
+        self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'str', expected_type=compat_str), 'str',
+                         msg='accept matching `expected_type` type')
+        self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'str', expected_type=int), None,
+                         msg='reject non matching `expected_type` type')
+        self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'int', expected_type=lambda x: compat_str(x)), '0',
+                         msg='transform type using type function')
+        self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'str',
+                                      expected_type=lambda _: 1 / 0), None,
+                         msg='wrap expected_type function in try_call')
+        self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, Ellipsis, expected_type=compat_str), ['str'],
+                         msg='eliminate items that expected_type fails on')
+
+        # Test get_all behavior
+        _GET_ALL_DATA = {'key': [0, 1, 2]}
+        self.assertEqual(traverse_obj(_GET_ALL_DATA, ('key', Ellipsis), get_all=False), 0,
+                         msg='if not `get_all`, return only first matching value')
+        self.assertEqual(traverse_obj(_GET_ALL_DATA, Ellipsis, get_all=False), [0, 1, 2],
+                         msg='do not overflatten if not `get_all`')
+
+        # Test casesense behavior
+        _CASESENSE_DATA = {
+            'KeY': 'value0',
+            0: {
+                'KeY': 'value1',
+                0: {'KeY': 'value2'},
+            },
+            # FULLWIDTH LATIN CAPITAL LETTER K
+            '\uff2bey': 'value3',
+        }
+        self.assertEqual(traverse_obj(_CASESENSE_DATA, 'key'), None,
+                         msg='dict keys should be case sensitive unless `casesense`')
+        self.assertEqual(traverse_obj(_CASESENSE_DATA, 'keY',
+                                      casesense=False), 'value0',
+                         msg='allow non matching key case if `casesense`')
+        self.assertEqual(traverse_obj(_CASESENSE_DATA, '\uff4bey',  # FULLWIDTH LATIN SMALL LETTER K
+                                      casesense=False), 'value3',
+                         msg='allow non matching Unicode key case if `casesense`')
+        self.assertEqual(traverse_obj(_CASESENSE_DATA, (0, ('keY',)),
+                                      casesense=False), ['value1'],
+                         msg='allow non matching key case in branch if `casesense`')
+        self.assertEqual(traverse_obj(_CASESENSE_DATA, (0, ((0, 'keY'),)),
+                                      casesense=False), ['value2'],
+                         msg='allow non matching key case in branch path if `casesense`')
+
+        # Test traverse_string behavior
+        _TRAVERSE_STRING_DATA = {'str': 'str', 1.2: 1.2}
+        self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', 0)), None,
+                         msg='do not traverse into string if not `traverse_string`')
+        self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', 0),
+                                      _traverse_string=True), 's',
+                         msg='traverse into string if `traverse_string`')
+        self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, (1.2, 1),
+                                      _traverse_string=True), '.',
+                         msg='traverse into converted data if `traverse_string`')
+        self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', Ellipsis),
+                                      _traverse_string=True), list('str'),
+                         msg='`...` branching into string should result in list')
+        self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', (0, 2)),
+                                      _traverse_string=True), ['s', 'r'],
+                         msg='branching into string should result in list')
+        self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', lambda _, x: x),
+                                      _traverse_string=True), list('str'),
+                         msg='function branching into string should result in list')
+
+        # Test is_user_input behavior
+        _IS_USER_INPUT_DATA = {'range8': list(range(8))}
+        self.assertEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', '3'),
+                                      _is_user_input=True), 3,
+                         msg='allow for string indexing if `is_user_input`')
+        self.assertCountEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', '3:'),
+                                           _is_user_input=True), tuple(range(8))[3:],
+                              msg='allow for string slice if `is_user_input`')
+        self.assertCountEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':4:2'),
+                                           _is_user_input=True), tuple(range(8))[:4:2],
+                              msg='allow step in string slice if `is_user_input`')
+        self.assertCountEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':'),
+                                           _is_user_input=True), range(8),
+                              msg='`:` should be treated as `...` if `is_user_input`')
+        with self.assertRaises(TypeError, msg='too many params should result in error'):
+            traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':::'), _is_user_input=True)
+
+        # Test re.Match as input obj
+        mobj = re.match(r'^0(12)(?P<group>3)(4)?$', '0123')
+        self.assertEqual(traverse_obj(mobj, Ellipsis), [x for x in mobj.groups() if x is not None],
+                         msg='`...` on a `re.Match` should give its `groups()`')
+        self.assertEqual(traverse_obj(mobj, lambda k, _: k in (0, 2)), ['0123', '3'],
+                         msg='function on a `re.Match` should give groupno, value starting at 0')
+        self.assertEqual(traverse_obj(mobj, 'group'), '3',
+                         msg='str key on a `re.Match` should give group with that name')
+        self.assertEqual(traverse_obj(mobj, 2), '3',
+                         msg='int key on a `re.Match` should give group with that name')
+        self.assertEqual(traverse_obj(mobj, 'gRoUp', casesense=False), '3',
+                         msg='str key on a `re.Match` should respect casesense')
+        self.assertEqual(traverse_obj(mobj, 'fail'), None,
+                         msg='failing str key on a `re.Match` should return `default`')
+        self.assertEqual(traverse_obj(mobj, 'gRoUpS', casesense=False), None,
+                         msg='failing str key on a `re.Match` should return `default`')
+        self.assertEqual(traverse_obj(mobj, 8), None,
+                         msg='failing int key on a `re.Match` should return `default`')
+
+    def test_get_first(self):
+        self.assertEqual(get_first([{'a': None}, {'a': 'spam'}], 'a'), 'spam')
+
+    def test_join_nonempty(self):
+        self.assertEqual(join_nonempty('a', 'b'), 'a-b')
+        self.assertEqual(join_nonempty(
+            'a', 'b', 'c', 'd',
+            from_dict={'a': 'c', 'c': [], 'b': 'd', 'd': None}), 'c-d')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_chapters.py

@@ -1,275 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from test.helper import expect_value
-from youtube_dl.extractor import YoutubeIE
-
-
-class TestYoutubeChapters(unittest.TestCase):
-
-    _TEST_CASES = [
-        (
-            # https://www.youtube.com/watch?v=A22oy8dFjqc
-            # pattern: 00:00 - <title>
-            '''This is the absolute ULTIMATE experience of Queen's set at LIVE AID, this is the best video mixed to the absolutely superior stereo radio broadcast. This vastly superior audio mix takes a huge dump on all of the official mixes. Best viewed in 1080p. ENJOY! ***MAKE SURE TO READ THE DESCRIPTION***<br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+36);return false;">00:36</a> - Bohemian Rhapsody<br /><a href="#" onclick="yt.www.watch.player.seekTo(02*60+42);return false;">02:42</a> - Radio Ga Ga<br /><a href="#" onclick="yt.www.watch.player.seekTo(06*60+53);return false;">06:53</a> - Ay Oh!<br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+34);return false;">07:34</a> - Hammer To Fall<br /><a href="#" onclick="yt.www.watch.player.seekTo(12*60+08);return false;">12:08</a> - Crazy Little Thing Called Love<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+03);return false;">16:03</a> - We Will Rock You<br /><a href="#" onclick="yt.www.watch.player.seekTo(17*60+18);return false;">17:18</a> - We Are The Champions<br /><a href="#" onclick="yt.www.watch.player.seekTo(21*60+12);return false;">21:12</a> - Is This The World We Created...?<br /><br />Short song analysis:<br /><br />- "Bohemian Rhapsody": Although it's a short medley version, it's one of the best performances of the ballad section, with Freddie nailing the Bb4s with the correct studio phrasing (for the first time ever!).<br /><br />- "Radio Ga Ga": Although it's missing one chorus, this is one of - if not the best - the best versions ever, Freddie nails all the Bb4s and sounds very clean! Spike Edney's Roland Jupiter 8 also really shines through on this mix, compared to the DVD releases!<br /><br />- "Audience Improv": A great improv, Freddie sounds strong and confident. You gotta love when he sustains that A4 for 4 seconds!<br /><br />- "Hammer To Fall": Despite missing a verse and a chorus, it's a strong version (possibly the best ever). Freddie sings the song amazingly, and even ad-libs a C#5 and a C5! Also notice how heavy Brian's guitar sounds compared to the thin DVD mixes - it roars!<br /><br />- "Crazy Little Thing Called Love": A great version, the crowd loves the song, the jam is great as well! Only downside to this is the slight feedback issues.<br /><br />- "We Will Rock You": Although cut down to the 1st verse and chorus, Freddie sounds strong. He nails the A4, and the solo from Dr. May is brilliant!<br /><br />- "We Are the Champions": Perhaps the high-light of the performance - Freddie is very daring on this version, he sustains the pre-chorus Bb4s, nails the 1st C5, belts great A4s, but most importantly: He nails the chorus Bb4s, in all 3 choruses! This is the only time he has ever done so! It has to be said though, the last one sounds a bit rough, but that's a side effect of belting high notes for the past 18 minutes, with nodules AND laryngitis!<br /><br />- "Is This The World We Created... ?": Freddie and Brian perform a beautiful version of this, and it is one of the best versions ever. It's both sad and hilarious that a couple of BBC engineers are talking over the song, one of them being completely oblivious of the fact that he is interrupting the performance, on live television... Which was being televised to almost 2 billion homes.<br /><br /><br />All rights go to their respective owners!<br />-----Copyright Disclaimer Under Section 107 of the Copyright Act 1976, allowance is made for fair use for purposes such as criticism, comment, news reporting, teaching, scholarship, and research. Fair use is a use permitted by copyright statute that might otherwise be infringing. Non-profit, educational or personal use tips the balance in favor of fair use''',
-            1477,
-            [{
-                'start_time': 36,
-                'end_time': 162,
-                'title': 'Bohemian Rhapsody',
-            }, {
-                'start_time': 162,
-                'end_time': 413,
-                'title': 'Radio Ga Ga',
-            }, {
-                'start_time': 413,
-                'end_time': 454,
-                'title': 'Ay Oh!',
-            }, {
-                'start_time': 454,
-                'end_time': 728,
-                'title': 'Hammer To Fall',
-            }, {
-                'start_time': 728,
-                'end_time': 963,
-                'title': 'Crazy Little Thing Called Love',
-            }, {
-                'start_time': 963,
-                'end_time': 1038,
-                'title': 'We Will Rock You',
-            }, {
-                'start_time': 1038,
-                'end_time': 1272,
-                'title': 'We Are The Champions',
-            }, {
-                'start_time': 1272,
-                'end_time': 1477,
-                'title': 'Is This The World We Created...?',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=ekYlRhALiRQ
-            # pattern: <num>. <title> 0:00
-            '1.  Those Beaten Paths of Confusion <a href="#" onclick="yt.www.watch.player.seekTo(0*60+00);return false;">0:00</a><br />2.  Beyond the Shadows of Emptiness & Nothingness <a href="#" onclick="yt.www.watch.player.seekTo(11*60+47);return false;">11:47</a><br />3.  Poison Yourself...With Thought <a href="#" onclick="yt.www.watch.player.seekTo(26*60+30);return false;">26:30</a><br />4.  The Agents of Transformation <a href="#" onclick="yt.www.watch.player.seekTo(35*60+57);return false;">35:57</a><br />5.  Drowning in the Pain of Consciousness <a href="#" onclick="yt.www.watch.player.seekTo(44*60+32);return false;">44:32</a><br />6.  Deny the Disease of Life <a href="#" onclick="yt.www.watch.player.seekTo(53*60+07);return false;">53:07</a><br /><br />More info/Buy: http://crepusculonegro.storenvy.com/products/257645-cn-03-arizmenda-within-the-vacuum-of-infinity<br /><br />No copyright is intended. The rights to this video are assumed by the owner and its affiliates.',
-            4009,
-            [{
-                'start_time': 0,
-                'end_time': 707,
-                'title': '1. Those Beaten Paths of Confusion',
-            }, {
-                'start_time': 707,
-                'end_time': 1590,
-                'title': '2. Beyond the Shadows of Emptiness & Nothingness',
-            }, {
-                'start_time': 1590,
-                'end_time': 2157,
-                'title': '3. Poison Yourself...With Thought',
-            }, {
-                'start_time': 2157,
-                'end_time': 2672,
-                'title': '4. The Agents of Transformation',
-            }, {
-                'start_time': 2672,
-                'end_time': 3187,
-                'title': '5. Drowning in the Pain of Consciousness',
-            }, {
-                'start_time': 3187,
-                'end_time': 4009,
-                'title': '6. Deny the Disease of Life',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=WjL4pSzog9w
-            # pattern: 00:00 <title>
-            '<a href="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" class="yt-uix-servicelink  " data-target-new-window="True" data-servicelink="CDAQ6TgYACITCNf1raqT2dMCFdRjGAod_o0CBSj4HQ" data-url="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" rel="nofollow noopener" target="_blank">https://arizmenda.bandcamp.com/merch/...</a><br /><br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+00);return false;">00:00</a> Christening Unborn Deformities <br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+08);return false;">07:08</a> Taste of Purity<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+16);return false;">16:16</a> Sculpting Sins of a Universal Tongue<br /><a href="#" onclick="yt.www.watch.player.seekTo(24*60+45);return false;">24:45</a> Birth<br /><a href="#" onclick="yt.www.watch.player.seekTo(31*60+24);return false;">31:24</a> Neves<br /><a href="#" onclick="yt.www.watch.player.seekTo(37*60+55);return false;">37:55</a> Libations in Limbo',
-            2705,
-            [{
-                'start_time': 0,
-                'end_time': 428,
-                'title': 'Christening Unborn Deformities',
-            }, {
-                'start_time': 428,
-                'end_time': 976,
-                'title': 'Taste of Purity',
-            }, {
-                'start_time': 976,
-                'end_time': 1485,
-                'title': 'Sculpting Sins of a Universal Tongue',
-            }, {
-                'start_time': 1485,
-                'end_time': 1884,
-                'title': 'Birth',
-            }, {
-                'start_time': 1884,
-                'end_time': 2275,
-                'title': 'Neves',
-            }, {
-                'start_time': 2275,
-                'end_time': 2705,
-                'title': 'Libations in Limbo',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=o3r1sn-t3is
-            # pattern: <title> 00:00 <note>
-            'Download this show in MP3: <a href="http://sh.st/njZKK" class="yt-uix-servicelink  " data-url="http://sh.st/njZKK" data-target-new-window="True" data-servicelink="CDAQ6TgYACITCK3j8_6o2dMCFVDCGAoduVAKKij4HQ" rel="nofollow noopener" target="_blank">http://sh.st/njZKK</a><br /><br />Setlist:<br />I-E-A-I-A-I-O <a href="#" onclick="yt.www.watch.player.seekTo(00*60+45);return false;">00:45</a><br />Suite-Pee <a href="#" onclick="yt.www.watch.player.seekTo(4*60+26);return false;">4:26</a>  (Incomplete)<br />Attack <a href="#" onclick="yt.www.watch.player.seekTo(5*60+31);return false;">5:31</a> (First live performance since 2011)<br />Prison Song <a href="#" onclick="yt.www.watch.player.seekTo(8*60+42);return false;">8:42</a><br />Know <a href="#" onclick="yt.www.watch.player.seekTo(12*60+32);return false;">12:32</a> (First live performance since 2011)<br />Aerials <a href="#" onclick="yt.www.watch.player.seekTo(15*60+32);return false;">15:32</a><br />Soldier Side - Intro <a href="#" onclick="yt.www.watch.player.seekTo(19*60+13);return false;">19:13</a><br />B.Y.O.B. <a href="#" onclick="yt.www.watch.player.seekTo(20*60+09);return false;">20:09</a><br />Soil <a href="#" onclick="yt.www.watch.player.seekTo(24*60+32);return false;">24:32</a><br />Darts <a href="#" onclick="yt.www.watch.player.seekTo(27*60+48);return false;">27:48</a><br />Radio/Video <a href="#" onclick="yt.www.watch.player.seekTo(30*60+38);return false;">30:38</a><br />Hypnotize <a href="#" onclick="yt.www.watch.player.seekTo(35*60+05);return false;">35:05</a><br />Temper <a href="#" onclick="yt.www.watch.player.seekTo(38*60+08);return false;">38:08</a> (First live performance since 1999)<br />CUBErt <a href="#" onclick="yt.www.watch.player.seekTo(41*60+00);return false;">41:00</a><br />Needles <a href="#" onclick="yt.www.watch.player.seekTo(42*60+57);return false;">42:57</a><br />Deer Dance <a href="#" onclick="yt.www.watch.player.seekTo(46*60+27);return false;">46:27</a><br />Bounce <a href="#" onclick="yt.www.watch.player.seekTo(49*60+38);return false;">49:38</a><br />Suggestions <a href="#" onclick="yt.www.watch.player.seekTo(51*60+25);return false;">51:25</a><br />Psycho <a href="#" onclick="yt.www.watch.player.seekTo(53*60+52);return false;">53:52</a><br />Chop Suey! <a href="#" onclick="yt.www.watch.player.seekTo(58*60+13);return false;">58:13</a><br />Lonely Day <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+01*60+15);return false;">1:01:15</a><br />Question! <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+04*60+14);return false;">1:04:14</a><br />Lost in Hollywood <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+08*60+10);return false;">1:08:10</a><br />Vicinity of Obscenity  <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+13*60+40);return false;">1:13:40</a>(First live performance since 2012)<br />Forest <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+16*60+17);return false;">1:16:17</a><br />Cigaro <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+20*60+02);return false;">1:20:02</a><br />Toxicity <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+23*60+57);return false;">1:23:57</a>(with Chino Moreno)<br />Sugar <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+27*60+53);return false;">1:27:53</a>',
-            5640,
-            [{
-                'start_time': 45,
-                'end_time': 266,
-                'title': 'I-E-A-I-A-I-O',
-            }, {
-                'start_time': 266,
-                'end_time': 331,
-                'title': 'Suite-Pee (Incomplete)',
-            }, {
-                'start_time': 331,
-                'end_time': 522,
-                'title': 'Attack (First live performance since 2011)',
-            }, {
-                'start_time': 522,
-                'end_time': 752,
-                'title': 'Prison Song',
-            }, {
-                'start_time': 752,
-                'end_time': 932,
-                'title': 'Know (First live performance since 2011)',
-            }, {
-                'start_time': 932,
-                'end_time': 1153,
-                'title': 'Aerials',
-            }, {
-                'start_time': 1153,
-                'end_time': 1209,
-                'title': 'Soldier Side - Intro',
-            }, {
-                'start_time': 1209,
-                'end_time': 1472,
-                'title': 'B.Y.O.B.',
-            }, {
-                'start_time': 1472,
-                'end_time': 1668,
-                'title': 'Soil',
-            }, {
-                'start_time': 1668,
-                'end_time': 1838,
-                'title': 'Darts',
-            }, {
-                'start_time': 1838,
-                'end_time': 2105,
-                'title': 'Radio/Video',
-            }, {
-                'start_time': 2105,
-                'end_time': 2288,
-                'title': 'Hypnotize',
-            }, {
-                'start_time': 2288,
-                'end_time': 2460,
-                'title': 'Temper (First live performance since 1999)',
-            }, {
-                'start_time': 2460,
-                'end_time': 2577,
-                'title': 'CUBErt',
-            }, {
-                'start_time': 2577,
-                'end_time': 2787,
-                'title': 'Needles',
-            }, {
-                'start_time': 2787,
-                'end_time': 2978,
-                'title': 'Deer Dance',
-            }, {
-                'start_time': 2978,
-                'end_time': 3085,
-                'title': 'Bounce',
-            }, {
-                'start_time': 3085,
-                'end_time': 3232,
-                'title': 'Suggestions',
-            }, {
-                'start_time': 3232,
-                'end_time': 3493,
-                'title': 'Psycho',
-            }, {
-                'start_time': 3493,
-                'end_time': 3675,
-                'title': 'Chop Suey!',
-            }, {
-                'start_time': 3675,
-                'end_time': 3854,
-                'title': 'Lonely Day',
-            }, {
-                'start_time': 3854,
-                'end_time': 4090,
-                'title': 'Question!',
-            }, {
-                'start_time': 4090,
-                'end_time': 4420,
-                'title': 'Lost in Hollywood',
-            }, {
-                'start_time': 4420,
-                'end_time': 4577,
-                'title': 'Vicinity of Obscenity (First live performance since 2012)',
-            }, {
-                'start_time': 4577,
-                'end_time': 4802,
-                'title': 'Forest',
-            }, {
-                'start_time': 4802,
-                'end_time': 5037,
-                'title': 'Cigaro',
-            }, {
-                'start_time': 5037,
-                'end_time': 5273,
-                'title': 'Toxicity (with Chino Moreno)',
-            }, {
-                'start_time': 5273,
-                'end_time': 5640,
-                'title': 'Sugar',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=PkYLQbsqCE8
-            # pattern: <num> - <title> [<latinized title>] 0:00:00
-            '''Затемно (Zatemno) is an Obscure Black Metal Band from Russia.<br /><br />"Во прах (Vo prakh)'' Into The Ashes", Debut mini-album released may 6, 2016, by Death Knell Productions<br />Released on 6 panel digipak CD, limited to 100 copies only<br />And digital format on Bandcamp<br /><br />Tracklist<br /><br />1 - Во прах [Vo prakh] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+00*60+00);return false;">0:00:00</a><br />2 - Искупление [Iskupleniye] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+08*60+10);return false;">0:08:10</a><br />3 - Из серпов луны...[Iz serpov luny] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+14*60+30);return false;">0:14:30</a><br /><br />Links:<br /><a href="https://deathknellprod.bandcamp.com/album/--2" class="yt-uix-servicelink  " data-target-new-window="True" data-url="https://deathknellprod.bandcamp.com/album/--2" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://deathknellprod.bandcamp.com/a...</a><br /><a href="https://www.facebook.com/DeathKnellProd/" class="yt-uix-servicelink  " data-target-new-window="True" data-url="https://www.facebook.com/DeathKnellProd/" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://www.facebook.com/DeathKnellProd/</a><br /><br /><br />I don't have any right about this artifact, my only intention is to spread the music of the band, all rights are reserved to the Затемно (Zatemno) and his producers, Death Knell Productions.<br /><br />------------------------------------------------------------------<br /><br />Subscribe for more videos like this.<br />My link: <a href="https://web.facebook.com/AttackOfTheDragons" class="yt-uix-servicelink  " data-target-new-window="True" data-url="https://web.facebook.com/AttackOfTheDragons" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://web.facebook.com/AttackOfTheD...</a>''',
-            1138,
-            [{
-                'start_time': 0,
-                'end_time': 490,
-                'title': '1 - Во прах [Vo prakh]',
-            }, {
-                'start_time': 490,
-                'end_time': 870,
-                'title': '2 - Искупление [Iskupleniye]',
-            }, {
-                'start_time': 870,
-                'end_time': 1138,
-                'title': '3 - Из серпов луны...[Iz serpov luny]',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=xZW70zEasOk
-            # time point more than duration
-            '''● LCS Spring finals: Saturday and Sunday from <a href="#" onclick="yt.www.watch.player.seekTo(13*60+30);return false;">13:30</a> outside the venue! <br />● PAX East: Fri, Sat & Sun - more info in tomorrows video on the main channel!''',
-            283,
-            []
-        ),
-    ]
-
-    def test_youtube_chapters(self):
-        for description, duration, expected_chapters in self._TEST_CASES:
-            ie = YoutubeIE()
-            expect_value(
-                self, ie._extract_chapters_from_description(description, duration),
-                expected_chapters, None)
-
-
-if __name__ == '__main__':
-    unittest.main()

test/test_youtube_lists.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+# -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
 # Allow direct execution
@@ -9,10 +10,10 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import FakeYDL
 
-
 from youtube_dl.extractor import (
-    YoutubePlaylistIE,
     YoutubeIE,
+    YoutubePlaylistIE,
+    YoutubeTabIE,
 )
 
 
@@ -24,47 +25,40 @@ class TestYoutubeLists(unittest.TestCase):
     def test_youtube_playlist_noplaylist(self):
         dl = FakeYDL()
         dl.params['noplaylist'] = True
+        dl.params['format'] = 'best'
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertEqual(result['_type'], 'url')
+        result = dl.extract_info(result['url'], download=False, ie_key=result.get('ie_key'), process=False)
         self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
 
-    def test_youtube_course(self):
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        # TODO find a > 100 (paginating?) videos course
-        result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        entries = list(result['entries'])
-        self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
-        self.assertEqual(len(entries), 25)
-        self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
-
     def test_youtube_mix(self):
         dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
-        entries = result['entries']
-        self.assertTrue(len(entries) >= 50)
+        dl.params['format'] = 'best'
+        ie = YoutubeTabIE(dl)
+        result = dl.extract_info('https://www.youtube.com/watch?v=tyITL_exICo&list=RDCLAK5uy_kLWIr9gv1XLlPbaDS965-Db4TrBoUTxQ8',
+                                 download=False, ie_key=ie.ie_key(), process=True)
+        entries = (result or {}).get('entries', [{'id': 'not_found', }])
+        self.assertTrue(len(entries) >= 25)
         original_video = entries[0]
-        self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
+        self.assertEqual(original_video['id'], 'tyITL_exICo')
 
-    def test_youtube_toptracks(self):
-        print('Skipping: The playlist page gives error 500')
-        return
-        dl = FakeYDL()
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
-        entries = result['entries']
-        self.assertEqual(len(entries), 100)
-
-    def test_youtube_flat_playlist_titles(self):
+    def test_youtube_flat_playlist_extraction(self):
         dl = FakeYDL()
         dl.params['extract_flat'] = True
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=PL-KKIb8rvtMSrAO9YFbeM6UQrAqoFTUWv')
+        ie = YoutubeTabIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc')
         self.assertIsPlaylist(result)
-        for entry in result['entries']:
-            self.assertTrue(entry.get('title'))
+        entries = list(result['entries'])
+        self.assertTrue(len(entries) == 1)
+        video = entries[0]
+        self.assertEqual(video['_type'], 'url')
+        self.assertEqual(video['ie_key'], 'Youtube')
+        self.assertEqual(video['id'], 'BaW_jenozKc')
+        self.assertEqual(video['url'], 'BaW_jenozKc')
+        self.assertEqual(video['title'], 'youtube-dl test video "\'/\\ä↭𝕐')
+        self.assertEqual(video['duration'], 10)
+        self.assertEqual(video['uploader'], 'Philipp Hagemeister')
 
 
 if __name__ == '__main__':

test/test_youtube_misc.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+from youtube_dl.extractor import YoutubeIE
+
+
+class TestYoutubeMisc(unittest.TestCase):
+    def test_youtube_extract(self):
+        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
+        assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
+        assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
+        assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
+        assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
+        assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
+        assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_youtube_signature.py

@@ -12,72 +12,141 @@ import io
 import re
 import string
 
-from test.helper import FakeYDL
-from youtube_dl.extractor import YoutubeIE
 from youtube_dl.compat import compat_str, compat_urlretrieve
 
-_TESTS = [
+from test.helper import FakeYDL
+from youtube_dl.extractor import YoutubeIE
+from youtube_dl.jsinterp import JSInterpreter
+
+_SIG_TESTS = [
     (
         'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
-        'js',
         86,
         '>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
-        'js',
         85,
         '3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
-        'js',
         90,
         ']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js',
-        'js',
         84,
         'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js',
-        'js',
         '2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
         'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
-        'js',
         84,
         '123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js',
-        'js',
         83,
         '123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F'
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js',
-        'js',
         '4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
         '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
-        'js',
         '312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
         '112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
     )
 ]
 
+_NSIG_TESTS = [
+    (
+        'https://www.youtube.com/s/player/9216d1f7/player_ias.vflset/en_US/base.js',
+        'SLp9F5bwjAdhE9F-', 'gWnb9IK2DJ8Q1w',
+    ),
+    (
+        'https://www.youtube.com/s/player/f8cb7a3b/player_ias.vflset/en_US/base.js',
+        'oBo2h5euWy6osrUt', 'ivXHpm7qJjJN',
+    ),
+    (
+        'https://www.youtube.com/s/player/2dfe380c/player_ias.vflset/en_US/base.js',
+        'oBo2h5euWy6osrUt', '3DIBbn3qdQ',
+    ),
+    (
+        'https://www.youtube.com/s/player/f1ca6900/player_ias.vflset/en_US/base.js',
+        'cu3wyu6LQn2hse', 'jvxetvmlI9AN9Q',
+    ),
+    (
+        'https://www.youtube.com/s/player/8040e515/player_ias.vflset/en_US/base.js',
+        'wvOFaY-yjgDuIEg5', 'HkfBFDHmgw4rsw',
+    ),
+    (
+        'https://www.youtube.com/s/player/e06dea74/player_ias.vflset/en_US/base.js',
+        'AiuodmaDDYw8d3y4bf', 'ankd8eza2T6Qmw',
+    ),
+    (
+        'https://www.youtube.com/s/player/5dd88d1d/player-plasma-ias-phone-en_US.vflset/base.js',
+        'kSxKFLeqzv_ZyHSAt', 'n8gS8oRlHOxPFA',
+    ),
+    (
+        'https://www.youtube.com/s/player/324f67b9/player_ias.vflset/en_US/base.js',
+        'xdftNy7dh9QGnhW', '22qLGxrmX8F1rA',
+    ),
+    (
+        'https://www.youtube.com/s/player/4c3f79c5/player_ias.vflset/en_US/base.js',
+        'TDCstCG66tEAO5pR9o', 'dbxNtZ14c-yWyw',
+    ),
+    (
+        'https://www.youtube.com/s/player/c81bbb4a/player_ias.vflset/en_US/base.js',
+        'gre3EcLurNY2vqp94', 'Z9DfGxWP115WTg',
+    ),
+    (
+        'https://www.youtube.com/s/player/1f7d5369/player_ias.vflset/en_US/base.js',
+        'batNX7sYqIJdkJ', 'IhOkL_zxbkOZBw',
+    ),
+    (
+        'https://www.youtube.com/s/player/009f1d77/player_ias.vflset/en_US/base.js',
+        '5dwFHw8aFWQUQtffRq', 'audescmLUzI3jw',
+    ),
+    (
+        'https://www.youtube.com/s/player/dc0c6770/player_ias.vflset/en_US/base.js',
+        '5EHDMgYLV6HPGk_Mu-kk', 'n9lUJLHbxUI0GQ',
+    ),
+    (
+        'https://www.youtube.com/s/player/c2199353/player_ias.vflset/en_US/base.js',
+        '5EHDMgYLV6HPGk_Mu-kk', 'AD5rgS85EkrE7',
+    ),
+    (
+        'https://www.youtube.com/s/player/113ca41c/player_ias.vflset/en_US/base.js',
+        'cgYl-tlYkhjT7A', 'hI7BBr2zUgcmMg',
+    ),
+    (
+        'https://www.youtube.com/s/player/c57c113c/player_ias.vflset/en_US/base.js',
+        '-Txvy6bT5R6LqgnQNx', 'dcklJCnRUHbgSg',
+    ),
+    (
+        'https://www.youtube.com/s/player/5a3b6271/player_ias.vflset/en_US/base.js',
+        'B2j7f_UPT4rfje85Lu_e', 'm5DmNymaGQ5RdQ',
+    ),
+]
+
 
 class TestPlayerInfo(unittest.TestCase):
     def test_youtube_extract_player_info(self):
         PLAYER_URLS = (
+            ('https://www.youtube.com/s/player/4c3f79c5/player_ias.vflset/en_US/base.js', '4c3f79c5'),
             ('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/en_US/base.js', '64dddad9'),
+            ('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/fr_FR/base.js', '64dddad9'),
+            ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
+            ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
+            ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
             # obsolete
             ('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
             ('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
@@ -86,59 +155,70 @@ class TestPlayerInfo(unittest.TestCase):
             ('https://www.youtube.com/yts/jsbin/player-en_US-vflaxXRn1/base.js', 'vflaxXRn1'),
             ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
             ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
-            ('http://s.ytimg.com/yt/swfbin/watch_as3-vflrEm9Nq.swf', 'vflrEm9Nq'),
-            ('https://s.ytimg.com/yts/swfbin/player-vflenCdZL/watch_as3.swf', 'vflenCdZL'),
         )
         for player_url, expected_player_id in PLAYER_URLS:
-            expected_player_type = player_url.split('.')[-1]
-            player_type, player_id = YoutubeIE._extract_player_info(player_url)
-            self.assertEqual(player_type, expected_player_type)
+            player_id = YoutubeIE._extract_player_info(player_url)
             self.assertEqual(player_id, expected_player_id)
 
 
 class TestSignature(unittest.TestCase):
     def setUp(self):
         TEST_DIR = os.path.dirname(os.path.abspath(__file__))
-        self.TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata')
+        self.TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata/sigs')
         if not os.path.exists(self.TESTDATA_DIR):
             os.mkdir(self.TESTDATA_DIR)
 
+    def tearDown(self):
+        try:
+            for f in os.listdir(self.TESTDATA_DIR):
+                os.remove(f)
+        except OSError:
+            pass
 
-def make_tfunc(url, stype, sig_input, expected_sig):
-    m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$', url)
+
+def t_factory(name, sig_func, url_pattern):
+    def make_tfunc(url, sig_input, expected_sig):
+        m = url_pattern.match(url)
         assert m, '%r should follow URL format' % url
-    test_id = m.group(1)
+        test_id = m.group('id')
 
         def test_func(self):
-        basename = 'player-%s.%s' % (test_id, stype)
+            basename = 'player-{0}-{1}.js'.format(name, test_id)
             fn = os.path.join(self.TESTDATA_DIR, basename)
 
             if not os.path.exists(fn):
                 compat_urlretrieve(url, fn)
-
-        ydl = FakeYDL()
-        ie = YoutubeIE(ydl)
-        if stype == 'js':
             with io.open(fn, encoding='utf-8') as testf:
                 jscode = testf.read()
-            func = ie._parse_sig_js(jscode)
-        else:
-            assert stype == 'swf'
-            with open(fn, 'rb') as testf:
-                swfcode = testf.read()
-            func = ie._parse_sig_swf(swfcode)
+            self.assertEqual(sig_func(jscode, sig_input), expected_sig)
+
+        test_func.__name__ = str('test_{0}_js_{1}'.format(name, test_id))
+        setattr(TestSignature, test_func.__name__, test_func)
+    return make_tfunc
+
+
+def signature(jscode, sig_input):
+    func = YoutubeIE(FakeYDL())._parse_sig_js(jscode)
     src_sig = (
         compat_str(string.printable[:sig_input])
         if isinstance(sig_input, int) else sig_input)
-        got_sig = func(src_sig)
-        self.assertEqual(got_sig, expected_sig)
-
-    test_func.__name__ = str('test_signature_' + stype + '_' + test_id)
-    setattr(TestSignature, test_func.__name__, test_func)
+    return func(src_sig)
 
 
-for test_spec in _TESTS:
-    make_tfunc(*test_spec)
+def n_sig(jscode, sig_input):
+    funcname = YoutubeIE(FakeYDL())._extract_n_function_name(jscode)
+    return JSInterpreter(jscode).call_function(funcname, sig_input)
+
+
+make_sig_test = t_factory(
+    'signature', signature, re.compile(r'.*-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$'))
+for test_spec in _SIG_TESTS:
+    make_sig_test(*test_spec)
+
+make_nsig_test = t_factory(
+    'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_-]+)/.+.js$'))
+for test_spec in _NSIG_TESTS:
+    make_nsig_test(*test_spec)
 
 
 if __name__ == '__main__':

youtube_dl/YoutubeDL.py

@@ -73,6 +73,7 @@ from .utils import (
     PostProcessingError,
     preferredencoding,
     prepend_extension,
+    process_communicate_or_kill,
     register_socks_protocols,
     render_table,
     replace_extension,
@@ -86,6 +87,7 @@ from .utils import (
     subtitles_filename,
     UnavailableVideoError,
     url_basename,
+    variadic,
     version_tuple,
     write_json_file,
     write_string,
@@ -163,6 +165,7 @@ class YoutubeDL(object):
     simulate:          Do not download the video files.
     format:            Video format code. See options.py for more information.
     outtmpl:           Template for output names.
+    outtmpl_na_placeholder: Placeholder for unavailable meta fields.
     restrictfilenames: Do not allow "&" and spaces in file names
     ignoreerrors:      Do not stop on download errors.
     force_generic_extractor: Force downloader to use the generic extractor
@@ -338,6 +341,8 @@ class YoutubeDL(object):
     _pps = []
     _download_retcode = None
     _num_downloads = None
+    _playlist_level = 0
+    _playlist_urls = set()
     _screen_file = None
 
     def __init__(self, params=None, auto_init=True):
@@ -656,7 +661,7 @@ class YoutubeDL(object):
             template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
                                  for k, v in template_dict.items()
                                  if v is not None and not isinstance(v, (list, tuple, dict)))
-            template_dict = collections.defaultdict(lambda: 'NA', template_dict)
+            template_dict = collections.defaultdict(lambda: self.params.get('outtmpl_na_placeholder', 'NA'), template_dict)
 
             outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
 
@@ -676,8 +681,8 @@ class YoutubeDL(object):
 
             # Missing numeric fields used together with integer presentation types
             # in format specification will break the argument substitution since
-            # string 'NA' is returned for missing fields. We will patch output
-            # template for missing fields to meet string presentation type.
+            # string NA placeholder is returned for missing fields. We will patch
+            # output template for missing fields to meet string presentation type.
             for numeric_field in self._NUMERIC_FIELDS:
                 if numeric_field not in template_dict:
                     # As of [1] format syntax is:
@@ -717,7 +722,7 @@ class YoutubeDL(object):
                 filename = encodeFilename(filename, True).decode(preferredencoding())
             return sanitize_path(filename)
         except ValueError as err:
-            self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
+            self.report_error('Error in output template: ' + error_to_compat_str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
             return None
 
     def _match_entry(self, info_dict, incomplete):
@@ -770,11 +775,20 @@ class YoutubeDL(object):
 
     def extract_info(self, url, download=True, ie_key=None, extra_info={},
                      process=True, force_generic_extractor=False):
-        '''
-        Returns a list with a dictionary for each video we find.
-        If 'download', also downloads the videos.
-        extra_info is a dict containing the extra values to add to each result
-        '''
+        """
+        Return a list with a dictionary for each video extracted.
+
+        Arguments:
+        url -- URL to extract
+
+        Keyword arguments:
+        download -- whether to download videos during extraction
+        ie_key -- extractor key hint
+        extra_info -- dictionary containing the extra values to add to each result
+        process -- whether to resolve all unresolved references (URLs, playlist items),
+            must be True for download to work.
+        force_generic_extractor -- force using the generic extractor
+        """
 
         if not ie_key and force_generic_extractor:
             ie_key = 'Generic'
@@ -906,8 +920,51 @@ class YoutubeDL(object):
             return self.process_ie_result(
                 new_result, download=download, extra_info=extra_info)
         elif result_type in ('playlist', 'multi_video'):
+            # Protect from infinite recursion due to recursively nested playlists
+            # (see https://github.com/ytdl-org/youtube-dl/issues/27833)
+            webpage_url = ie_result['webpage_url']
+            if webpage_url in self._playlist_urls:
+                self.to_screen(
+                    '[download] Skipping already downloaded playlist: %s'
+                    % ie_result.get('title') or ie_result.get('id'))
+                return
+
+            self._playlist_level += 1
+            self._playlist_urls.add(webpage_url)
+            try:
+                return self.__process_playlist(ie_result, download)
+            finally:
+                self._playlist_level -= 1
+                if not self._playlist_level:
+                    self._playlist_urls.clear()
+        elif result_type == 'compat_list':
+            self.report_warning(
+                'Extractor %s returned a compat_list result. '
+                'It needs to be updated.' % ie_result.get('extractor'))
+
+            def _fixup(r):
+                self.add_extra_info(
+                    r,
+                    {
+                        'extractor': ie_result['extractor'],
+                        'webpage_url': ie_result['webpage_url'],
+                        'webpage_url_basename': url_basename(ie_result['webpage_url']),
+                        'extractor_key': ie_result['extractor_key'],
+                    }
+                )
+                return r
+            ie_result['entries'] = [
+                self.process_ie_result(_fixup(r), download, extra_info)
+                for r in ie_result['entries']
+            ]
+            return ie_result
+        else:
+            raise Exception('Invalid result type: %s' % result_type)
+
+    def __process_playlist(self, ie_result, download):
         # We process each entry in the playlist
         playlist = ie_result.get('title') or ie_result.get('id')
+
         self.to_screen('[download] Downloading playlist: %s' % playlist)
 
         playlist_results = []
@@ -1015,29 +1072,6 @@ class YoutubeDL(object):
         ie_result['entries'] = playlist_results
         self.to_screen('[download] Finished downloading playlist: %s' % playlist)
         return ie_result
-        elif result_type == 'compat_list':
-            self.report_warning(
-                'Extractor %s returned a compat_list result. '
-                'It needs to be updated.' % ie_result.get('extractor'))
-
-            def _fixup(r):
-                self.add_extra_info(
-                    r,
-                    {
-                        'extractor': ie_result['extractor'],
-                        'webpage_url': ie_result['webpage_url'],
-                        'webpage_url_basename': url_basename(ie_result['webpage_url']),
-                        'extractor_key': ie_result['extractor_key'],
-                    }
-                )
-                return r
-            ie_result['entries'] = [
-                self.process_ie_result(_fixup(r), download, extra_info)
-                for r in ie_result['entries']
-            ]
-            return ie_result
-        else:
-            raise Exception('Invalid result type: %s' % result_type)
 
     @__handle_extraction_exceptions
     def __process_iterable_entry(self, entry, download, extra_info):
@@ -1226,6 +1260,8 @@ class YoutubeDL(object):
                         group = _parse_format_selection(tokens, inside_group=True)
                         current_selector = FormatSelector(GROUP, group, [])
                     elif string == '+':
+                        if inside_merge:
+                            raise syntax_error('Unexpected "+"', start)
                         video_selector = current_selector
                         audio_selector = _parse_format_selection(tokens, inside_merge=True)
                         if not video_selector or not audio_selector:
@@ -1263,57 +1299,46 @@ class YoutubeDL(object):
                 format_spec = selector.selector
 
                 def selector_function(ctx):
-                    formats = list(ctx['formats'])
-                    if not formats:
-                        return
-                    if format_spec == 'all':
-                        for f in formats:
-                            yield f
-                    elif format_spec in ['best', 'worst', None]:
-                        format_idx = 0 if format_spec == 'worst' else -1
+
+                    def best_worst(fmts, fmt_spec='best'):
+                        format_idx = 0 if fmt_spec == 'worst' else -1
                         audiovideo_formats = [
-                            f for f in formats
+                            f for f in fmts
                             if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
                         if audiovideo_formats:
-                            yield audiovideo_formats[format_idx]
+                            return audiovideo_formats[format_idx]
                         # for extractors with incomplete formats (audio only (soundcloud)
                         # or video only (imgur)) we will fallback to best/worst
                         # {video,audio}-only format
                         elif ctx['incomplete_formats']:
-                            yield formats[format_idx]
-                    elif format_spec == 'bestaudio':
+                            return fmts[format_idx]
+
+                    formats = list(ctx['formats'])
+                    if not formats:
+                        return
+                    if format_spec == 'all':
+                        pass
+                    elif format_spec in ('best', 'worst', None):
+                        formats = best_worst(formats, format_spec)
+                    elif format_spec in ('bestaudio', 'worstaudio'):
                         audio_formats = [
                             f for f in formats
                             if f.get('vcodec') == 'none']
-                        if audio_formats:
-                            yield audio_formats[-1]
-                    elif format_spec == 'worstaudio':
-                        audio_formats = [
-                            f for f in formats
-                            if f.get('vcodec') == 'none']
-                        if audio_formats:
-                            yield audio_formats[0]
-                    elif format_spec == 'bestvideo':
+                        formats = audio_formats[:1] if format_spec == 'worstaudio' else audio_formats[-1:]
+                    elif format_spec in ('bestvideo', 'worstvideo'):
                         video_formats = [
                             f for f in formats
                             if f.get('acodec') == 'none']
-                        if video_formats:
-                            yield video_formats[-1]
-                    elif format_spec == 'worstvideo':
-                        video_formats = [
-                            f for f in formats
-                            if f.get('acodec') == 'none']
-                        if video_formats:
-                            yield video_formats[0]
+                        formats = video_formats[:1] if format_spec == 'worstvideo' else video_formats[-1:]
                     else:
                         extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
                         if format_spec in extensions:
                             filter_f = lambda f: f['ext'] == format_spec
                         else:
                             filter_f = lambda f: f['format_id'] == format_spec
-                        matches = list(filter(filter_f, formats))
-                        if matches:
-                            yield matches[-1]
+                        formats = best_worst(list(filter(filter_f, formats)))
+                    for f in variadic(formats or []):
+                        yield f
             elif selector.type == MERGE:
                 def _merge(formats_info):
                     format_1, format_2 = [f['format_id'] for f in formats_info]
@@ -1486,12 +1511,16 @@ class YoutubeDL(object):
         if 'display_id' not in info_dict and 'id' in info_dict:
             info_dict['display_id'] = info_dict['id']
 
-        if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
+        for ts_key, date_key in (
+                ('timestamp', 'upload_date'),
+                ('release_timestamp', 'release_date'),
+        ):
+            if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
                 # Working around out-of-range timestamp values (e.g. negative ones on Windows,
                 # see http://bugs.python.org/issue1646728)
                 try:
-                upload_date = datetime.datetime.utcfromtimestamp(info_dict['timestamp'])
-                info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+                    upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
+                    info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
                 except (ValueError, OverflowError, OSError):
                     pass
 
@@ -1531,9 +1560,6 @@ class YoutubeDL(object):
         else:
             formats = info_dict['formats']
 
-        if not formats:
-            raise ExtractorError('No video formats found!')
-
         def is_wellformed(f):
             url = f.get('url')
             if not url:
@@ -1546,7 +1572,10 @@ class YoutubeDL(object):
             return True
 
         # Filter out malformed formats for better extraction robustness
-        formats = list(filter(is_wellformed, formats))
+        formats = list(filter(is_wellformed, formats or []))
+
+        if not formats:
+            raise ExtractorError('No video formats found!')
 
         formats_dict = {}
 
@@ -1740,9 +1769,8 @@ class YoutubeDL(object):
 
         assert info_dict.get('_type', 'video') == 'video'
 
-        max_downloads = self.params.get('max_downloads')
-        if max_downloads is not None:
-            if self._num_downloads >= int(max_downloads):
+        max_downloads = int_or_none(self.params.get('max_downloads')) or float('inf')
+        if self._num_downloads >= max_downloads:
             raise MaxDownloadsReached()
 
         # TODO: backward compatibility, to be removed
@@ -1777,6 +1805,8 @@ class YoutubeDL(object):
                     os.makedirs(dn)
                 return True
             except (OSError, IOError) as err:
+                if isinstance(err, OSError) and err.errno == errno.EEXIST:
+                    return True
                 self.report_error('unable to create directory ' + error_to_compat_str(err))
                 return False
 
@@ -1866,8 +1896,17 @@ class YoutubeDL(object):
 
         if not self.params.get('skip_download', False):
             try:
+                def checked_get_suitable_downloader(info_dict, params):
+                    ed_args = params.get('external_downloader_args')
+                    dler = get_suitable_downloader(info_dict, params)
+                    if ed_args and not params.get('external_downloader_args'):
+                        # external_downloader_args was cleared because external_downloader was rejected
+                        self.report_warning('Requested external downloader cannot be used: '
+                                            'ignoring --external-downloader-args.')
+                    return dler
+
                 def dl(name, info):
-                    fd = get_suitable_downloader(info, self.params)(self, self.params)
+                    fd = checked_get_suitable_downloader(info, self.params)(self, self.params)
                     for ph in self._progress_hooks:
                         fd.add_progress_hook(ph)
                     if self.params.get('verbose'):
@@ -2009,9 +2048,12 @@ class YoutubeDL(object):
                 try:
                     self.post_process(filename, info_dict)
                 except (PostProcessingError) as err:
-                    self.report_error('postprocessing: %s' % str(err))
+                    self.report_error('postprocessing: %s' % error_to_compat_str(err))
                     return
                 self.record_download_archive(info_dict)
+                # avoid possible nugatory search for further items (PR #26638)
+                if self._num_downloads >= max_downloads:
+                    raise MaxDownloadsReached()
 
     def download(self, url_list):
         """Download a given list of URLs."""
@@ -2274,7 +2316,7 @@ class YoutubeDL(object):
                 ['git', 'rev-parse', '--short', 'HEAD'],
                 stdout=subprocess.PIPE, stderr=subprocess.PIPE,
                 cwd=os.path.dirname(os.path.abspath(__file__)))
-            out, err = sp.communicate()
+            out, err = process_communicate_or_kill(sp)
             out = out.decode().strip()
             if re.match('[0-9a-f]+', out):
                 self._write_string('[debug] Git HEAD: ' + out + '\n')

youtube_dl/__init__.py

@@ -340,6 +340,7 @@ def _real_main(argv=None):
         'format': opts.format,
         'listformats': opts.listformats,
         'outtmpl': outtmpl,
+        'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
         'autonumber_size': opts.autonumber_size,
         'autonumber_start': opts.autonumber_start,
         'restrictfilenames': opts.restrictfilenames,

youtube_dl/aes.py

@@ -8,6 +8,18 @@ from .utils import bytes_to_intlist, intlist_to_bytes
 BLOCK_SIZE_BYTES = 16
 
 
+def pkcs7_padding(data):
+    """
+    PKCS#7 padding
+
+    @param {int[]} data        cleartext
+    @returns {int[]}           padding data
+    """
+
+    remaining_length = BLOCK_SIZE_BYTES - len(data) % BLOCK_SIZE_BYTES
+    return data + [remaining_length] * remaining_length
+
+
 def aes_ctr_decrypt(data, key, counter):
     """
     Decrypt with aes in counter mode
@@ -76,8 +88,7 @@ def aes_cbc_encrypt(data, key, iv):
     previous_cipher_block = iv
     for i in range(block_count):
         block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
-        remaining_length = BLOCK_SIZE_BYTES - len(block)
-        block += [remaining_length] * remaining_length
+        block = pkcs7_padding(block)
         mixed_block = xor(block, previous_cipher_block)
 
         encrypted_block = aes_encrypt(mixed_block, expanded_key)
@@ -88,6 +99,28 @@ def aes_cbc_encrypt(data, key, iv):
     return encrypted_data
 
 
+def aes_ecb_encrypt(data, key):
+    """
+    Encrypt with aes in ECB mode. Using PKCS#7 padding
+
+    @param {int[]} data        cleartext
+    @param {int[]} key         16/24/32-Byte cipher key
+    @returns {int[]}           encrypted data
+    """
+    expanded_key = key_expansion(key)
+    block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
+
+    encrypted_data = []
+    for i in range(block_count):
+        block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
+        block = pkcs7_padding(block)
+
+        encrypted_block = aes_encrypt(block, expanded_key)
+        encrypted_data += encrypted_block
+
+    return encrypted_data
+
+
 def key_expansion(data):
     """
     Generate key schedule

youtube_dl/cache.py

@@ -10,12 +10,21 @@ import traceback
 
 from .compat import compat_getenv
 from .utils import (
+    error_to_compat_str,
     expand_path,
+    is_outdated_version,
+    try_get,
     write_json_file,
 )
+from .version import __version__
 
 
 class Cache(object):
+
+    _YTDL_DIR = 'youtube-dl'
+    _VERSION_KEY = _YTDL_DIR + '_version'
+    _DEFAULT_VERSION = '2021.12.17'
+
     def __init__(self, ydl):
         self._ydl = ydl
 
@@ -23,7 +32,7 @@ class Cache(object):
         res = self._ydl.params.get('cachedir')
         if res is None:
             cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
-            res = os.path.join(cache_root, 'youtube-dl')
+            res = os.path.join(cache_root, self._YTDL_DIR)
         return expand_path(res)
 
     def _get_cache_fn(self, section, key, dtype):
@@ -50,13 +59,22 @@ class Cache(object):
             except OSError as ose:
                 if ose.errno != errno.EEXIST:
                     raise
-            write_json_file(data, fn)
+            write_json_file({self._VERSION_KEY: __version__, 'data': data}, fn)
         except Exception:
             tb = traceback.format_exc()
             self._ydl.report_warning(
                 'Writing cache to %r failed: %s' % (fn, tb))
 
-    def load(self, section, key, dtype='json', default=None):
+    def _validate(self, data, min_ver):
+        version = try_get(data, lambda x: x[self._VERSION_KEY])
+        if not version:  # Backward compatibility
+            data, version = {'data': data}, self._DEFAULT_VERSION
+        if not is_outdated_version(version, min_ver or '0', assume_new=False):
+            return data['data']
+        self._ydl.to_screen(
+            'Discarding old cache from version {version} (needs {min_ver})'.format(**locals()))
+
+    def load(self, section, key, dtype='json', default=None, min_ver=None):
         assert dtype in ('json',)
 
         if not self.enabled:
@@ -66,12 +84,12 @@ class Cache(object):
         try:
             try:
                 with io.open(cache_fn, 'r', encoding='utf-8') as cachef:
-                    return json.load(cachef)
+                    return self._validate(json.load(cachef), min_ver)
             except ValueError:
                 try:
                     file_size = os.path.getsize(cache_fn)
                 except (OSError, IOError) as oe:
-                    file_size = str(oe)
+                    file_size = error_to_compat_str(oe)
                 self._ydl.report_warning(
                     'Cache retrieval from %s failed (%s)' % (cache_fn, file_size))
         except IOError:

youtube_dl/compat.py

@@ -21,6 +21,23 @@ import subprocess
 import sys
 import xml.etree.ElementTree
 
+# deal with critical unicode/str things first
+try:
+    # Python 2
+    compat_str, compat_basestring, compat_chr = (
+        unicode, basestring, unichr
+    )
+    from .casefold import casefold as compat_casefold
+except NameError:
+    compat_str, compat_basestring, compat_chr = (
+        str, str, chr
+    )
+    compat_casefold = lambda s: s.casefold()
+
+try:
+    import collections.abc as compat_collections_abc
+except ImportError:
+    import collections as compat_collections_abc
 
 try:
     import urllib.request as compat_urllib_request
@@ -73,6 +90,15 @@ try:
 except ImportError:  # Python 2
     import Cookie as compat_cookies
 
+if sys.version_info[0] == 2:
+    class compat_cookies_SimpleCookie(compat_cookies.SimpleCookie):
+        def load(self, rawdata):
+            if isinstance(rawdata, compat_str):
+                rawdata = str(rawdata)
+            return super(compat_cookies_SimpleCookie, self).load(rawdata)
+else:
+    compat_cookies_SimpleCookie = compat_cookies.SimpleCookie
+
 try:
     import html.entities as compat_html_entities
 except ImportError:  # Python 2
@@ -2360,11 +2386,6 @@ try:
 except ImportError:
     import BaseHTTPServer as compat_http_server
 
-try:
-    compat_str = unicode  # Python 2
-except NameError:
-    compat_str = str
-
 try:
     from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
@@ -2495,22 +2516,11 @@ except ImportError:  # Python < 3.4
 
             return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
 
-try:
-    compat_basestring = basestring  # Python 2
-except NameError:
-    compat_basestring = str
-
-try:
-    compat_chr = unichr  # Python 2
-except NameError:
-    compat_chr = chr
-
 try:
     from xml.etree.ElementTree import ParseError as compat_xml_parse_error
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 
-
 etree = xml.etree.ElementTree
 
 
@@ -2877,6 +2887,7 @@ else:
     _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
 
     def compat_get_terminal_size(fallback=(80, 24)):
+        from .utils import process_communicate_or_kill
         columns = compat_getenv('COLUMNS')
         if columns:
             columns = int(columns)
@@ -2893,7 +2904,7 @@ else:
                 sp = subprocess.Popen(
                     ['stty', 'size'],
                     stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-                out, err = sp.communicate()
+                out, err = process_communicate_or_kill(sp)
                 _lines, _columns = map(int, out.split())
             except Exception:
                 _columns, _lines = _terminal_size(*fallback)
@@ -2953,6 +2964,24 @@ else:
         compat_Struct = struct.Struct
 
 
+# compat_map/filter() returning an iterator, supposedly the
+# same versioning as for zip below
+try:
+    from future_builtins import map as compat_map
+except ImportError:
+    try:
+        from itertools import imap as compat_map
+    except ImportError:
+        compat_map = map
+
+try:
+    from future_builtins import filter as compat_filter
+except ImportError:
+    try:
+        from itertools import ifilter as compat_filter
+    except ImportError:
+        compat_filter = filter
+
 try:
     from future_builtins import zip as compat_zip
 except ImportError:  # not 2.6+ or is 3.x
@@ -2962,6 +2991,82 @@ except ImportError:  # not 2.6+ or is 3.x
         compat_zip = zip
 
 
+# method renamed between Py2/3
+try:
+    from itertools import zip_longest as compat_itertools_zip_longest
+except ImportError:
+    from itertools import izip_longest as compat_itertools_zip_longest
+
+
+# new class in collections
+try:
+    from collections import ChainMap as compat_collections_chain_map
+    # Py3.3's ChainMap is deficient
+    if sys.version_info < (3, 4):
+        raise ImportError
+except ImportError:
+    # Py <= 3.3
+    class compat_collections_chain_map(compat_collections_abc.MutableMapping):
+
+        maps = [{}]
+
+        def __init__(self, *maps):
+            self.maps = list(maps) or [{}]
+
+        def __getitem__(self, k):
+            for m in self.maps:
+                if k in m:
+                    return m[k]
+            raise KeyError(k)
+
+        def __setitem__(self, k, v):
+            self.maps[0].__setitem__(k, v)
+            return
+
+        def __contains__(self, k):
+            return any((k in m) for m in self.maps)
+
+        def __delitem(self, k):
+            if k in self.maps[0]:
+                del self.maps[0][k]
+                return
+            raise KeyError(k)
+
+        def __delitem__(self, k):
+            self.__delitem(k)
+
+        def __iter__(self):
+            return itertools.chain(*reversed(self.maps))
+
+        def __len__(self):
+            return len(iter(self))
+
+        # to match Py3, don't del directly
+        def pop(self, k, *args):
+            if self.__contains__(k):
+                off = self.__getitem__(k)
+                self.__delitem(k)
+                return off
+            elif len(args) > 0:
+                return args[0]
+            raise KeyError(k)
+
+        def new_child(self, m=None, **kwargs):
+            m = m or {}
+            m.update(kwargs)
+            return compat_collections_chain_map(m, *self.maps)
+
+        @property
+        def parents(self):
+            return compat_collections_chain_map(*(self.maps[1:]))
+
+
+# Pythons disagree on the type of a pattern (RegexObject, _sre.SRE_Pattern, Pattern, ...?)
+compat_re_Pattern = type(re.compile(''))
+# and on the type of a match
+compat_re_Match = type(re.match('a', 'a'))
+
+
 if sys.version_info < (3, 3):
     def compat_b64decode(s, *args, **kwargs):
         if isinstance(s, compat_str):
@@ -2996,15 +3101,20 @@ __all__ = [
     'compat_Struct',
     'compat_b64decode',
     'compat_basestring',
+    'compat_casefold',
     'compat_chr',
+    'compat_collections_abc',
+    'compat_collections_chain_map',
     'compat_cookiejar',
     'compat_cookiejar_Cookie',
     'compat_cookies',
+    'compat_cookies_SimpleCookie',
     'compat_ctypes_WINFUNCTYPE',
     'compat_etree_Element',
     'compat_etree_fromstring',
     'compat_etree_register_namespace',
     'compat_expanduser',
+    'compat_filter',
     'compat_get_terminal_size',
     'compat_getenv',
     'compat_getpass',
@@ -3015,12 +3125,16 @@ __all__ = [
     'compat_input',
     'compat_integer_types',
     'compat_itertools_count',
+    'compat_itertools_zip_longest',
     'compat_kwargs',
+    'compat_map',
     'compat_numeric_types',
     'compat_ord',
     'compat_os_name',
     'compat_parse_qs',
     'compat_print',
+    'compat_re_Match',
+    'compat_re_Pattern',
     'compat_realpath',
     'compat_setenv',
     'compat_shlex_quote',

youtube_dl/downloader/__init__.py

@@ -1,22 +1,31 @@
 from __future__ import unicode_literals
 
+from ..utils import (
+    determine_protocol,
+)
+
+
+def get_suitable_downloader(info_dict, params={}):
+    info_dict['protocol'] = determine_protocol(info_dict)
+    info_copy = info_dict.copy()
+    return _get_suitable_downloader(info_copy, params)
+
+
+# Some of these require get_suitable_downloader
 from .common import FileDownloader
+from .dash import DashSegmentsFD
 from .f4m import F4mFD
 from .hls import HlsFD
 from .http import HttpFD
 from .rtmp import RtmpFD
-from .dash import DashSegmentsFD
 from .rtsp import RtspFD
 from .ism import IsmFD
+from .niconico import NiconicoDmcFD
 from .external import (
     get_external_downloader,
     FFmpegFD,
 )
 
-from ..utils import (
-    determine_protocol,
-)
-
 PROTOCOL_MAP = {
     'rtmp': RtmpFD,
     'm3u8_native': HlsFD,
@@ -26,13 +35,12 @@ PROTOCOL_MAP = {
     'f4m': F4mFD,
     'http_dash_segments': DashSegmentsFD,
     'ism': IsmFD,
+    'niconico_dmc': NiconicoDmcFD,
 }
 
 
-def get_suitable_downloader(info_dict, params={}):
+def _get_suitable_downloader(info_dict, params={}):
     """Get the downloader class that can handle the info dict."""
-    protocol = determine_protocol(info_dict)
-    info_dict['protocol'] = protocol
 
     # if (info_dict.get('start_time') or info_dict.get('end_time')) and not info_dict.get('requested_formats') and FFmpegFD.can_download(info_dict):
     #     return FFmpegFD
@@ -42,7 +50,11 @@ def get_suitable_downloader(info_dict, params={}):
         ed = get_external_downloader(external_downloader)
         if ed.can_download(info_dict):
             return ed
+        # Avoid using unwanted args since external_downloader was rejected
+        if params.get('external_downloader_args'):
+            params['external_downloader_args'] = None
 
+    protocol = info_dict['protocol']
     if protocol.startswith('m3u8') and info_dict.get('is_live'):
         return FFmpegFD
 

youtube_dl/downloader/external.py

@@ -22,6 +22,7 @@ from ..utils import (
     handle_youtubedl_headers,
     check_executable,
     is_outdated_version,
+    process_communicate_or_kill,
 )
 
 
@@ -104,7 +105,7 @@ class ExternalFD(FileDownloader):
 
         p = subprocess.Popen(
             cmd, stderr=subprocess.PIPE)
-        _, stderr = p.communicate()
+        _, stderr = process_communicate_or_kill(p)
         if p.returncode != 0:
             self.to_stderr(stderr.decode('utf-8', 'replace'))
         return p.returncode
@@ -141,7 +142,7 @@ class CurlFD(ExternalFD):
 
         # curl writes the progress to stderr so don't capture it.
         p = subprocess.Popen(cmd)
-        p.communicate()
+        process_communicate_or_kill(p)
         return p.returncode
 
 
@@ -336,14 +337,17 @@ class FFmpegFD(ExternalFD):
         proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env)
         try:
             retval = proc.wait()
-        except KeyboardInterrupt:
-            # subprocces.run would send the SIGKILL signal to ffmpeg and the
+        except BaseException as e:
+            # subprocess.run would send the SIGKILL signal to ffmpeg and the
             # mp4 file couldn't be played, but if we ask ffmpeg to quit it
             # produces a file that is playable (this is mostly useful for live
             # streams). Note that Windows is not affected and produces playable
             # files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
-            if sys.platform != 'win32':
-                proc.communicate(b'q')
+            if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32':
+                process_communicate_or_kill(proc, b'q')
+            else:
+                proc.kill()
+                proc.wait()
             raise
         return retval
 

youtube_dl/downloader/hls.py

@@ -172,6 +172,10 @@ class HlsFD(FragmentFD):
                         iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
                         decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
                             self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
+                        # Don't decrypt the content in tests since the data is explicitly truncated and it's not to a valid block
+                        # size (see https://github.com/ytdl-org/youtube-dl/pull/27660). Tests only care that the correct data downloaded,
+                        # not what it decrypts to.
+                        if not test:
                             frag_content = AES.new(
                                 decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
                     self._append_fragment(ctx, frag_content)

youtube_dl/downloader/niconico.py

@@ -0,0 +1,66 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+try:
+    import threading
+except ImportError:
+    threading = None
+
+from .common import FileDownloader
+from ..downloader import get_suitable_downloader
+from ..extractor.niconico import NiconicoIE
+from ..utils import sanitized_Request
+
+
+class NiconicoDmcFD(FileDownloader):
+    """ Downloading niconico douga from DMC with heartbeat """
+
+    FD_NAME = 'niconico_dmc'
+
+    def real_download(self, filename, info_dict):
+        self.to_screen('[%s] Downloading from DMC' % self.FD_NAME)
+
+        ie = NiconicoIE(self.ydl)
+        info_dict, heartbeat_info_dict = ie._get_heartbeat_info(info_dict)
+
+        fd = get_suitable_downloader(info_dict, params=self.params)(self.ydl, self.params)
+        for ph in self._progress_hooks:
+            fd.add_progress_hook(ph)
+
+        if not threading:
+            self.to_screen('[%s] Threading for Heartbeat not available' % self.FD_NAME)
+            return fd.real_download(filename, info_dict)
+
+        success = download_complete = False
+        timer = [None]
+        heartbeat_lock = threading.Lock()
+        heartbeat_url = heartbeat_info_dict['url']
+        heartbeat_data = heartbeat_info_dict['data'].encode()
+        heartbeat_interval = heartbeat_info_dict.get('interval', 30)
+
+        request = sanitized_Request(heartbeat_url, heartbeat_data)
+
+        def heartbeat():
+            try:
+                self.ydl.urlopen(request).read()
+            except Exception:
+                self.to_screen('[%s] Heartbeat failed' % self.FD_NAME)
+
+            with heartbeat_lock:
+                if not download_complete:
+                    timer[0] = threading.Timer(heartbeat_interval, heartbeat)
+                    timer[0].start()
+
+        heartbeat_info_dict['ping']()
+        self.to_screen('[%s] Heartbeat with %d second interval ...' % (self.FD_NAME, heartbeat_interval))
+        try:
+            heartbeat()
+            if type(fd).__name__ == 'HlsFD':
+                info_dict.update(ie._extract_m3u8_formats(info_dict['url'], info_dict['id'])[0])
+            success = fd.real_download(filename, info_dict)
+        finally:
+            if heartbeat_lock:
+                with heartbeat_lock:
+                    timer[0].cancel()
+                    download_complete = True
+            return success

youtube_dl/downloader/rtmp.py

@@ -89,11 +89,13 @@ class RtmpFD(FileDownloader):
                                 self.to_screen('')
                             cursor_in_new_line = True
                             self.to_screen('[rtmpdump] ' + line)
-            finally:
-                proc.wait()
                 if not cursor_in_new_line:
                     self.to_screen('')
-            return proc.returncode
+                return proc.wait()
+            except BaseException:  # Including KeyboardInterrupt
+                proc.kill()
+                proc.wait()
+                raise
 
         url = info_dict['url']
         player_url = info_dict.get('player_url')

youtube_dl/extractor/abcnews.py

@@ -1,14 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import calendar
 import re
-import time
 
 from .amp import AMPIE
 from .common import InfoExtractor
-from .youtube import YoutubeIE
-from ..compat import compat_urlparse
+from ..utils import (
+    parse_duration,
+    parse_iso8601,
+    try_get,
+)
 
 
 class AbcNewsVideoIE(AMPIE):
@@ -18,8 +19,8 @@ class AbcNewsVideoIE(AMPIE):
                         (?:
                             abcnews\.go\.com/
                             (?:
-                                [^/]+/video/(?P<display_id>[0-9a-z-]+)-|
-                                video/embed\?.*?\bid=
+                                (?:[^/]+/)*video/(?P<display_id>[0-9a-z-]+)-|
+                                video/(?:embed|itemfeed)\?.*?\bid=
                             )|
                             fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/
                         )
@@ -36,6 +37,8 @@ class AbcNewsVideoIE(AMPIE):
             'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
             'duration': 180,
             'thumbnail': r're:^https?://.*\.jpg$',
+            'timestamp': 1380454200,
+            'upload_date': '20130929',
         },
         'params': {
             # m3u8 download
@@ -47,6 +50,12 @@ class AbcNewsVideoIE(AMPIE):
     }, {
         'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
         'only_matching': True,
+    }, {
+        'url': 'http://abcnews.go.com/video/itemfeed?id=46979033',
+        'only_matching': True,
+    }, {
+        'url': 'https://abcnews.go.com/GMA/News/video/history-christmas-story-67894761',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -67,28 +76,23 @@ class AbcNewsIE(InfoExtractor):
     _VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
 
     _TESTS = [{
-        'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
+        # Youtube Embeds
+        'url': 'https://abcnews.go.com/Entertainment/peter-billingsley-child-actor-christmas-story-hollywood-power/story?id=51286501',
         'info_dict': {
-            'id': '10505354',
-            'ext': 'flv',
-            'display_id': 'dramatic-video-rare-death-job-america',
-            'title': 'Occupational Hazards',
-            'description': 'Nightline investigates the dangers that lurk at various jobs.',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'upload_date': '20100428',
-            'timestamp': 1272412800,
+            'id': '51286501',
+            'title': "Peter Billingsley: From child actor in 'A Christmas Story' to Hollywood power player",
+            'description': 'Billingsley went from a child actor to Hollywood power player.',
         },
-        'add_ie': ['AbcNewsVideo'],
+        'playlist_count': 5,
     }, {
         'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
         'info_dict': {
             'id': '38897857',
             'ext': 'mp4',
-            'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016',
             'title': 'Justin Timberlake Drops Hints For Secret Single',
             'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.',
-            'upload_date': '20160515',
-            'timestamp': 1463329500,
+            'upload_date': '20160505',
+            'timestamp': 1462442280,
         },
         'params': {
             # m3u8 download
@@ -100,49 +104,55 @@ class AbcNewsIE(InfoExtractor):
     }, {
         'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
         'only_matching': True,
+    }, {
+        # inline.type == 'video'
+        'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('display_id')
-        video_id = mobj.group('id')
+        story_id = self._match_id(url)
+        webpage = self._download_webpage(url, story_id)
+        story = self._parse_json(self._search_regex(
+            r"window\['__abcnews__'\]\s*=\s*({.+?});",
+            webpage, 'data'), story_id)['page']['content']['story']['everscroll'][0]
+        article_contents = story.get('articleContents') or {}
 
-        webpage = self._download_webpage(url, video_id)
-        video_url = self._search_regex(
-            r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL')
-        full_video_url = compat_urlparse.urljoin(url, video_url)
-
-        youtube_url = YoutubeIE._extract_url(webpage)
-
-        timestamp = None
-        date_str = self._html_search_regex(
-            r'<span[^>]+class="timestamp">([^<]+)</span>',
-            webpage, 'timestamp', fatal=False)
-        if date_str:
-            tz_offset = 0
-            if date_str.endswith(' ET'):  # Eastern Time
-                tz_offset = -5
-                date_str = date_str[:-3]
-            date_formats = ['%b. %d, %Y', '%b %d, %Y, %I:%M %p']
-            for date_format in date_formats:
-                try:
-                    timestamp = calendar.timegm(time.strptime(date_str.strip(), date_format))
-                except ValueError:
-                    continue
-            if timestamp is not None:
-                timestamp -= tz_offset * 3600
-
-        entry = {
-            '_type': 'url_transparent',
+        def entries():
+            featured_video = story.get('featuredVideo') or {}
+            feed = try_get(featured_video, lambda x: x['video']['feed'])
+            if feed:
+                yield {
+                    '_type': 'url',
+                    'id': featured_video.get('id'),
+                    'title': featured_video.get('name'),
+                    'url': feed,
+                    'thumbnail': featured_video.get('images'),
+                    'description': featured_video.get('description'),
+                    'timestamp': parse_iso8601(featured_video.get('uploadDate')),
+                    'duration': parse_duration(featured_video.get('duration')),
                     'ie_key': AbcNewsVideoIE.ie_key(),
-            'url': full_video_url,
-            'id': video_id,
-            'display_id': display_id,
-            'timestamp': timestamp,
                 }
 
-        if youtube_url:
-            entries = [entry, self.url_result(youtube_url, ie=YoutubeIE.ie_key())]
-            return self.playlist_result(entries)
+            for inline in (article_contents.get('inlines') or []):
+                inline_type = inline.get('type')
+                if inline_type == 'iframe':
+                    iframe_url = try_get(inline, lambda x: x['attrs']['src'])
+                    if iframe_url:
+                        yield self.url_result(iframe_url)
+                elif inline_type == 'video':
+                    video_id = inline.get('id')
+                    if video_id:
+                        yield {
+                            '_type': 'url',
+                            'id': video_id,
+                            'url': 'http://abcnews.go.com/video/embed?id=' + video_id,
+                            'thumbnail': inline.get('imgSrc') or inline.get('imgDefault'),
+                            'description': inline.get('description'),
+                            'duration': parse_duration(inline.get('duration')),
+                            'ie_key': AbcNewsVideoIE.ie_key(),
+                        }
 
-        return entry
+        return self.playlist_result(
+            entries(), story_id, article_contents.get('headline'),
+            article_contents.get('subHead'))

youtube_dl/extractor/acast.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
+    clean_podcast_url,
     int_or_none,
     parse_iso8601,
 )
@@ -17,7 +18,7 @@ class ACastBaseIE(InfoExtractor):
         info = {
             'id': episode['id'],
             'display_id': episode.get('episodeUrl'),
-            'url': episode['url'],
+            'url': clean_podcast_url(episode['url']),
             'title': title,
             'description': clean_html(episode.get('description') or episode.get('summary')),
             'thumbnail': episode.get('image'),

youtube_dl/extractor/adn.py

@@ -10,6 +10,7 @@ import random
 from .common import InfoExtractor
 from ..aes import aes_cbc_decrypt
 from ..compat import (
+    compat_HTTPError,
     compat_b64decode,
     compat_ord,
 )
@@ -18,29 +19,50 @@ from ..utils import (
     bytes_to_long,
     ExtractorError,
     float_or_none,
+    int_or_none,
     intlist_to_bytes,
     long_to_bytes,
     pkcs1pad,
     strip_or_none,
-    urljoin,
+    try_get,
+    unified_strdate,
+    urlencode_postdata,
 )
 
 
 class ADNIE(InfoExtractor):
-    IE_DESC = 'Anime Digital Network'
-    _VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
-        'md5': 'e497370d847fd79d9d4c74be55575c7a',
+    IE_DESC = 'Animation Digital Network'
+    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
+        'md5': '1c9ef066ceb302c86f80c2b371615261',
         'info_dict': {
-            'id': '7778',
+            'id': '9841',
             'ext': 'mp4',
-            'title': 'Blue Exorcist - Kyôto Saga - Épisode 1',
-            'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
-        }
-    }
-    _BASE_URL = 'http://animedigitalnetwork.fr'
-    _RSA_KEY = (0xc35ae1e4356b65a73b551493da94b8cb443491c0aa092a357a5aee57ffc14dda85326f42d716e539a34542a0d3f363adf16c5ec222d713d5997194030ee2e4f0d1fb328c01a81cf6868c090d50de8e169c6b13d1675b9eeed1cbc51e1fffca9b38af07f37abd790924cd3bee59d0257cfda4fe5f3f0534877e21ce5821447d1b, 65537)
+            'title': 'Fruits Basket - Episode 1',
+            'description': 'md5:14be2f72c3c96809b0ca424b0097d336',
+            'series': 'Fruits Basket',
+            'duration': 1437,
+            'release_date': '20190405',
+            'comment_count': int,
+            'average_rating': float,
+            'season_number': 1,
+            'episode': 'À ce soir !',
+            'episode_number': 1,
+        },
+        'skip': 'Only available in region (FR, ...)',
+    }, {
+        'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
+        'only_matching': True,
+    }]
+
+    _NETRC_MACHINE = 'animationdigitalnetwork'
+    _BASE = 'animationdigitalnetwork.fr'
+    _API_BASE_URL = 'https://gw.api.' + _BASE + '/'
+    _PLAYER_BASE_URL = _API_BASE_URL + 'player/'
+    _HEADERS = {}
+    _LOGIN_ERR_MESSAGE = 'Unable to log in'
+    _RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
     _POS_ALIGN_MAP = {
         'start': 1,
         'end': 3,
@@ -54,26 +76,24 @@ class ADNIE(InfoExtractor):
     def _ass_subtitles_timecode(seconds):
         return '%01d:%02d:%02d.%02d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 100)
 
-    def _get_subtitles(self, sub_path, video_id):
-        if not sub_path:
+    def _get_subtitles(self, sub_url, video_id):
+        if not sub_url:
             return None
 
         enc_subtitles = self._download_webpage(
-            urljoin(self._BASE_URL, sub_path),
-            video_id, 'Downloading subtitles location', fatal=False) or '{}'
+            sub_url, video_id, 'Downloading subtitles location', fatal=False) or '{}'
         subtitle_location = (self._parse_json(enc_subtitles, video_id, fatal=False) or {}).get('location')
         if subtitle_location:
             enc_subtitles = self._download_webpage(
-                urljoin(self._BASE_URL, subtitle_location),
-                video_id, 'Downloading subtitles data', fatal=False,
-                headers={'Origin': 'https://animedigitalnetwork.fr'})
+                subtitle_location, video_id, 'Downloading subtitles data',
+                fatal=False, headers={'Origin': 'https://' + self._BASE})
         if not enc_subtitles:
             return None
 
-        # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
+        # http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
         dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
             bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
-            bytes_to_intlist(binascii.unhexlify(self._K + '4b8ef13ec1872730')),
+            bytes_to_intlist(binascii.unhexlify(self._K + '7fac1178830cfe0c')),
             bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
         ))
         subtitles_json = self._parse_json(
@@ -117,61 +137,103 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
             }])
         return subtitles
 
+    def _real_initialize(self):
+        username, password = self._get_login_info()
+        if not username:
+            return
+        try:
+            url = self._API_BASE_URL + 'authentication/login'
+            access_token = (self._download_json(
+                url, None, 'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
+                data=urlencode_postdata({
+                    'password': password,
+                    'rememberMe': False,
+                    'source': 'Web',
+                    'username': username,
+                })) or {}).get('accessToken')
+            if access_token:
+                self._HEADERS = {'authorization': 'Bearer ' + access_token}
+        except ExtractorError as e:
+            message = None
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                resp = self._parse_json(
+                    self._webpage_read_content(e.cause, url, username),
+                    username, fatal=False) or {}
+                message = resp.get('message') or resp.get('code')
+            self.report_warning(message or self._LOGIN_ERR_MESSAGE)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        player_config = self._parse_json(self._search_regex(
-            r'playerConfig\s*=\s*({.+});', webpage,
-            'player config', default='{}'), video_id, fatal=False)
-        if not player_config:
-            config_url = urljoin(self._BASE_URL, self._search_regex(
-                r'(?:id="player"|class="[^"]*adn-player-container[^"]*")[^>]+data-url="([^"]+)"',
-                webpage, 'config url'))
-            player_config = self._download_json(
-                config_url, video_id,
-                'Downloading player config JSON metadata')['player']
+        video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
+        player = self._download_json(
+            video_base_url + 'configuration', video_id,
+            'Downloading player config JSON metadata',
+            headers=self._HEADERS)['player']
+        options = player['options']
 
-        video_info = {}
-        video_info_str = self._search_regex(
-            r'videoInfo\s*=\s*({.+});', webpage,
-            'video info', fatal=False)
-        if video_info_str:
-            video_info = self._parse_json(
-                video_info_str, video_id, fatal=False) or {}
+        user = options['user']
+        if not user.get('hasAccess'):
+            self.raise_login_required()
 
-        options = player_config.get('options') or {}
-        metas = options.get('metas') or {}
-        links = player_config.get('links') or {}
-        sub_path = player_config.get('subtitles')
-        error = None
-        if not links:
-            links_url = player_config.get('linksurl') or options['videoUrl']
-            token = options['token']
+        token = self._download_json(
+            user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
+            video_id, 'Downloading access token', headers={
+                'x-player-refresh-token': user['refreshToken']
+            }, data=b'')['token']
+
+        links_url = try_get(options, lambda x: x['video']['url']) or (video_base_url + 'link')
         self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
         message = bytes_to_intlist(json.dumps({
             'k': self._K,
-                'e': 60,
             't': token,
         }))
+
+        # Sometimes authentication fails for no good reason, retry with
+        # a different random padding
+        links_data = None
+        for _ in range(3):
             padded_message = intlist_to_bytes(pkcs1pad(message, 128))
             n, e = self._RSA_KEY
             encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
             authorization = base64.b64encode(encrypted_message).decode()
+
+            try:
                 links_data = self._download_json(
-                urljoin(self._BASE_URL, links_url), video_id,
-                'Downloading links JSON metadata', headers={
-                    'Authorization': 'Bearer ' + authorization,
+                    links_url, video_id, 'Downloading links JSON metadata', headers={
+                        'X-Player-Token': authorization
+                    }, query={
+                        'freeWithAds': 'true',
+                        'adaptive': 'false',
+                        'withMetadata': 'true',
+                        'source': 'Web'
                     })
+                break
+            except ExtractorError as e:
+                if not isinstance(e.cause, compat_HTTPError):
+                    raise e
+
+                if e.cause.code == 401:
+                    # This usually goes away with a different random pkcs1pad, so retry
+                    continue
+
+                error = self._parse_json(
+                    self._webpage_read_content(e.cause, links_url, video_id),
+                    video_id, fatal=False) or {}
+                message = error.get('message')
+                if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
+                    self.raise_geo_restricted(msg=message)
+                raise ExtractorError(message)
+        else:
+            raise ExtractorError('Giving up retrying')
+
         links = links_data.get('links') or {}
-            metas = metas or links_data.get('meta') or {}
-            sub_path = sub_path or links_data.get('subtitles') or \
-                'index.php?option=com_vodapi&task=subtitles.getJSON&format=json&id=' + video_id
-            sub_path += '&token=' + token
-            error = links_data.get('error')
-        title = metas.get('title') or video_info['title']
+        metas = links_data.get('metadata') or {}
+        sub_url = (links.get('subtitles') or {}).get('all')
+        video_info = links_data.get('video') or {}
+        title = metas['title']
 
         formats = []
-        for format_id, qualities in links.items():
+        for format_id, qualities in (links.get('streaming') or {}).items():
             if not isinstance(qualities, dict):
                 continue
             for quality, load_balancer_url in qualities.items():
@@ -189,19 +251,26 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
                     for f in m3u8_formats:
                         f['language'] = 'fr'
                 formats.extend(m3u8_formats)
-        if not error:
-            error = options.get('error')
-        if not formats and error:
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
         self._sort_formats(formats)
 
+        video = (self._download_json(
+            self._API_BASE_URL + 'video/%s' % video_id, video_id,
+            'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
+        show = video.get('show') or {}
+
         return {
             'id': video_id,
             'title': title,
-            'description': strip_or_none(metas.get('summary') or video_info.get('resume')),
-            'thumbnail': video_info.get('image'),
+            'description': strip_or_none(metas.get('summary') or video.get('summary')),
+            'thumbnail': video_info.get('image') or player.get('image'),
             'formats': formats,
-            'subtitles': self.extract_subtitles(sub_path, video_id),
-            'episode': metas.get('subtitle') or video_info.get('videoTitle'),
-            'series': video_info.get('playlistTitle'),
+            'subtitles': self.extract_subtitles(sub_url, video_id),
+            'episode': metas.get('subtitle') or video.get('name'),
+            'episode_number': int_or_none(video.get('shortNumber')),
+            'series': show.get('title'),
+            'season_number': int_or_none(video.get('season')),
+            'duration': int_or_none(video_info.get('duration') or video.get('duration')),
+            'release_date': unified_strdate(video.get('releaseDate')),
+            'average_rating': float_or_none(video.get('rating') or metas.get('rating')),
+            'comment_count': int_or_none(video.get('commentsCount')),
         }

youtube_dl/extractor/aenetworks.py

@@ -20,8 +20,8 @@ class AENetworksBaseIE(ThePlatformIE):
             (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
             fyi\.tv
         )/'''
-    _THEPLATFORM_KEY = 'crazyjava'
-    _THEPLATFORM_SECRET = 's3cr3t'
+    _THEPLATFORM_KEY = '43jXaGRQud'
+    _THEPLATFORM_SECRET = 'S10BPXHMlb'
     _DOMAIN_MAP = {
         'history.com': ('HISTORY', 'history'),
         'aetv.com': ('AETV', 'aetv'),
@@ -252,11 +252,11 @@ class AENetworksShowIE(AENetworksListBaseIE):
     _TESTS = [{
         'url': 'http://www.history.com/shows/ancient-aliens',
         'info_dict': {
-            'id': 'SH012427480000',
+            'id': 'SERIES1574',
             'title': 'Ancient Aliens',
             'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f',
         },
-        'playlist_mincount': 168,
+        'playlist_mincount': 150,
     }]
     _RESOURCE = 'series'
     _ITEMS_KEY = 'episodes'

youtube_dl/extractor/aliexpress.py

@@ -18,7 +18,7 @@ class AliExpressLiveIE(InfoExtractor):
             'id': '2800002704436634',
             'ext': 'mp4',
             'title': 'CASIMA7.22',
-            'thumbnail': r're:http://.*\.jpg',
+            'thumbnail': r're:https?://.*\.jpg',
             'uploader': 'CASIMA Official Store',
             'timestamp': 1500717600,
             'upload_date': '20170722',

youtube_dl/extractor/aljazeera.py

@@ -1,13 +1,16 @@
 from __future__ import unicode_literals
 
+import json
+import re
+
 from .common import InfoExtractor
 
 
 class AlJazeeraIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?:programmes|video)/.*?/(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?P<type>program/[^/]+|(?:feature|video)s)/\d{4}/\d{1,2}/\d{1,2}/(?P<id>[^/?&#]+)'
 
     _TESTS = [{
-        'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
+        'url': 'https://www.aljazeera.com/program/episode/2014/9/19/deliverance',
         'info_dict': {
             'id': '3792260579001',
             'ext': 'mp4',
@@ -20,14 +23,34 @@ class AlJazeeraIE(InfoExtractor):
         'add_ie': ['BrightcoveNew'],
         'skip': 'Not accessible from Travis CI server',
     }, {
-        'url': 'http://www.aljazeera.com/video/news/2017/05/sierra-leone-709-carat-diamond-auctioned-170511100111930.html',
+        'url': 'https://www.aljazeera.com/videos/2017/5/11/sierra-leone-709-carat-diamond-to-be-auctioned-off',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.aljazeera.com/features/2017/8/21/transforming-pakistans-buses-into-art',
         'only_matching': True,
     }]
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s'
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
-        program_name = self._match_id(url)
-        webpage = self._download_webpage(url, program_name)
-        brightcove_id = self._search_regex(
-            r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
-        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
+        post_type, name = re.match(self._VALID_URL, url).groups()
+        post_type = {
+            'features': 'post',
+            'program': 'episode',
+            'videos': 'video',
+        }[post_type.split('/')[0]]
+        video = self._download_json(
+            'https://www.aljazeera.com/graphql', name, query={
+                'operationName': 'SingleArticleQuery',
+                'variables': json.dumps({
+                    'name': name,
+                    'postType': post_type,
+                }),
+            }, headers={
+                'wp-site': 'aje',
+            })['data']['article']['video']
+        video_id = video['id']
+        account_id = video.get('accountId') or '665003303001'
+        player_id = video.get('playerId') or 'BkeSH5BDb'
+        return self.url_result(
+            self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
+            'BrightcoveNew', video_id)

youtube_dl/extractor/alsace20tv.py

@@ -0,0 +1,89 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    dict_get,
+    get_element_by_class,
+    int_or_none,
+    unified_strdate,
+    url_or_none,
+)
+
+
+class Alsace20TVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?alsace20\.tv/(?:[\w-]+/)+[\w-]+-(?P<id>[\w]+)'
+    _TESTS = [{
+        'url': 'https://www.alsace20.tv/VOD/Actu/JT/Votre-JT-jeudi-3-fevrier-lyNHCXpYJh.html',
+        # 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
+        'info_dict': {
+            'id': 'lyNHCXpYJh',
+            'ext': 'mp4',
+            'description': 'md5:fc0bc4a0692d3d2dba4524053de4c7b7',
+            'title': 'Votre JT du jeudi 3 février',
+            'upload_date': '20220203',
+            'thumbnail': r're:https?://.+\.jpg',
+            'duration': 1073,
+            'view_count': int,
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }]
+
+    def _extract_video(self, video_id, url=None):
+        info = self._download_json(
+            'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
+            video_id) or {}
+        title = info['titre']
+
+        formats = []
+        for res, fmt_url in (info.get('files') or {}).items():
+            formats.extend(
+                self._extract_smil_formats(fmt_url, video_id, fatal=False)
+                if '/smil:_' in fmt_url
+                else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
+        self._sort_formats(formats)
+
+        webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
+        thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
+        upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
+        upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': clean_html(get_element_by_class('wysiwyg', webpage)),
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
+            'duration': int_or_none(self._og_search_property('video:duration', webpage) if webpage else None),
+            'view_count': int_or_none(info.get('nb_vues')),
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self._extract_video(video_id, url)
+
+
+class Alsace20TVEmbedIE(Alsace20TVIE):
+    _VALID_URL = r'https?://(?:www\.)?alsace20\.tv/emb/(?P<id>[\w]+)'
+    _TESTS = [{
+        'url': 'https://www.alsace20.tv/emb/lyNHCXpYJh',
+        # 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
+        'info_dict': {
+            'id': 'lyNHCXpYJh',
+            'ext': 'mp4',
+            'title': 'Votre JT du jeudi 3 février',
+            'upload_date': '20220203',
+            'thumbnail': r're:https?://.+\.jpg',
+            'view_count': int,
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self._extract_video(video_id)

youtube_dl/extractor/americastestkitchen.py

@@ -1,13 +1,16 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
+    int_or_none,
     try_get,
     unified_strdate,
+    unified_timestamp,
 )
 
 
@@ -22,8 +25,8 @@ class AmericasTestKitchenIE(InfoExtractor):
             'ext': 'mp4',
             'description': 'md5:64e606bfee910627efc4b5f050de92b3',
             'thumbnail': r're:^https?://',
-            'timestamp': 1523664000,
-            'upload_date': '20180414',
+            'timestamp': 1523318400,
+            'upload_date': '20180410',
             'release_date': '20180410',
             'series': "America's Test Kitchen",
             'season_number': 18,
@@ -33,6 +36,27 @@ class AmericasTestKitchenIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # Metadata parsing behaves differently for newer episodes (705) as opposed to older episodes (582 above)
+        'url': 'https://www.americastestkitchen.com/episode/705-simple-chicken-dinner',
+        'md5': '06451608c57651e985a498e69cec17e5',
+        'info_dict': {
+            'id': '5fbe8c61bda2010001c6763b',
+            'title': 'Simple Chicken Dinner',
+            'ext': 'mp4',
+            'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
+            'thumbnail': r're:^https?://',
+            'timestamp': 1610755200,
+            'upload_date': '20210116',
+            'release_date': '20210116',
+            'series': "America's Test Kitchen",
+            'season_number': 21,
+            'episode': 'Simple Chicken Dinner',
+            'episode_number': 3,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
         'only_matching': True,
@@ -60,7 +84,76 @@ class AmericasTestKitchenIE(InfoExtractor):
             'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
             'ie_key': 'Zype',
             'description': clean_html(video.get('description')),
+            'timestamp': unified_timestamp(video.get('publishDate')),
             'release_date': unified_strdate(video.get('publishDate')),
+            'episode_number': int_or_none(episode.get('number')),
+            'season_number': int_or_none(episode.get('season')),
             'series': try_get(episode, lambda x: x['show']['title']),
             'episode': episode.get('title'),
         }
+
+
+class AmericasTestKitchenSeasonIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
+    _TESTS = [{
+        # ATK Season
+        'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
+        'info_dict': {
+            'id': 'season_1',
+            'title': 'Season 1',
+        },
+        'playlist_count': 13,
+    }, {
+        # Cooks Country Season
+        'url': 'https://www.cookscountry.com/episodes/browse/season_12',
+        'info_dict': {
+            'id': 'season_12',
+            'title': 'Season 12',
+        },
+        'playlist_count': 13,
+    }]
+
+    def _real_extract(self, url):
+        show_name, season_number = re.match(self._VALID_URL, url).groups()
+        season_number = int(season_number)
+
+        slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
+
+        season = 'Season %d' % season_number
+
+        season_search = self._download_json(
+            'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
+            season, headers={
+                'Origin': 'https://www.%s.com' % show_name,
+                'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
+                'X-Algolia-Application-Id': 'Y1FNZXUI30',
+            }, query={
+                'facetFilters': json.dumps([
+                    'search_season_list:' + season,
+                    'search_document_klass:episode',
+                    'search_show_slug:' + slug,
+                ]),
+                'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
+                'attributesToHighlight': '',
+                'hitsPerPage': 1000,
+            })
+
+        def entries():
+            for episode in (season_search.get('hits') or []):
+                search_url = episode.get('search_url')
+                if not search_url:
+                    continue
+                yield {
+                    '_type': 'url',
+                    'url': 'https://www.%s.com%s' % (show_name, search_url),
+                    'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
+                    'title': episode.get('title'),
+                    'description': episode.get('description'),
+                    'timestamp': unified_timestamp(episode.get('search_document_date')),
+                    'season_number': season_number,
+                    'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)),
+                    'ie_key': AmericasTestKitchenIE.ie_key(),
+                }
+
+        return self.playlist_result(
+            entries(), 'season_%d' % season_number, season)

youtube_dl/extractor/amp.py

@@ -8,6 +8,7 @@ from ..utils import (
     int_or_none,
     mimetype2ext,
     parse_iso8601,
+    unified_timestamp,
     url_or_none,
 )
 
@@ -88,7 +89,7 @@ class AMPIE(InfoExtractor):
 
         self._sort_formats(formats)
 
-        timestamp = parse_iso8601(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
+        timestamp = unified_timestamp(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
 
         return {
             'id': video_id,

youtube_dl/extractor/animeondemand.py

@@ -116,8 +116,6 @@ class AnimeOnDemandIE(InfoExtractor):
             r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
             webpage, 'anime description', default=None)
 
-        entries = []
-
         def extract_info(html, video_id, num=None):
             title, description = [None] * 2
             formats = []
@@ -233,7 +231,7 @@ class AnimeOnDemandIE(InfoExtractor):
                 self._sort_formats(info['formats'])
                 f = common_info.copy()
                 f.update(info)
-                entries.append(f)
+                yield f
 
             # Extract teaser/trailer only when full episode is not available
             if not info['formats']:
@@ -247,7 +245,7 @@ class AnimeOnDemandIE(InfoExtractor):
                         'title': m.group('title'),
                         'url': urljoin(url, m.group('href')),
                     })
-                    entries.append(f)
+                    yield f
 
         def extract_episodes(html):
             for num, episode_html in enumerate(re.findall(
@@ -275,7 +273,8 @@ class AnimeOnDemandIE(InfoExtractor):
                     'episode_number': episode_number,
                 }
 
-                extract_entries(episode_html, video_id, common_info)
+                for e in extract_entries(episode_html, video_id, common_info):
+                    yield e
 
         def extract_film(html, video_id):
             common_info = {
@@ -283,11 +282,18 @@ class AnimeOnDemandIE(InfoExtractor):
                 'title': anime_title,
                 'description': anime_description,
             }
-            extract_entries(html, video_id, common_info)
+            for e in extract_entries(html, video_id, common_info):
+                yield e
 
-        extract_episodes(webpage)
+        def entries():
+            has_episodes = False
+            for e in extract_episodes(webpage):
+                has_episodes = True
+                yield e
 
-        if not entries:
-            extract_film(webpage, anime_id)
+            if not has_episodes:
+                for e in extract_film(webpage, anime_id):
+                    yield e
 
-        return self.playlist_result(entries, anime_id, anime_title, anime_description)
+        return self.playlist_result(
+            entries(), anime_id, anime_title, anime_description)

youtube_dl/extractor/aol.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .yahoo import YahooIE
 from ..compat import (
     compat_parse_qs,
     compat_urllib_parse_urlparse,
@@ -15,9 +15,9 @@ from ..utils import (
 )
 
 
-class AolIE(InfoExtractor):
+class AolIE(YahooIE):
     IE_NAME = 'aol.com'
-    _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>[0-9a-f]+)'
+    _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
 
     _TESTS = [{
         # video with 5min ID
@@ -76,10 +76,16 @@ class AolIE(InfoExtractor):
     }, {
         'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
         'only_matching': True,
+    }, {
+        # Yahoo video
+        'url': 'https://www.aol.com/video/play/991e6700-ac02-11ea-99ff-357400036f61/24bbc846-3e30-3c46-915e-fe8ccd7fcc46/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        if '-' in video_id:
+            return self._extract_yahoo_video(video_id, 'us')
 
         response = self._download_json(
             'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,

youtube_dl/extractor/apa.py

@@ -6,25 +6,21 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
-    js_to_json,
+    int_or_none,
     url_or_none,
 )
 
 
 class APAIE(InfoExtractor):
-    _VALID_URL = r'https?://[^/]+\.apa\.at/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+    _VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
     _TESTS = [{
         'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
         'md5': '2b12292faeb0a7d930c778c7a5b4759b',
         'info_dict': {
-            'id': 'jjv85FdZ',
+            'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
             'ext': 'mp4',
-            'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
-            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
             'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 254,
-            'timestamp': 1519211149,
-            'upload_date': '20180221',
         },
     }, {
         'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
@@ -46,9 +42,11 @@ class APAIE(InfoExtractor):
                 webpage)]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id, base_url = mobj.group('id', 'base_url')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            '%s/player/%s' % (base_url, video_id), video_id)
 
         jwplatform_id = self._search_regex(
             r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
@@ -59,16 +57,18 @@ class APAIE(InfoExtractor):
                 'jwplatform:' + jwplatform_id, ie='JWPlatform',
                 video_id=video_id)
 
-        sources = self._parse_json(
-            self._search_regex(
-                r'sources\s*=\s*(\[.+?\])\s*;', webpage, 'sources'),
-            video_id, transform_source=js_to_json)
+        def extract(field, name=None):
+            return self._search_regex(
+                r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
+                webpage, name or field, default=None, group='value')
+
+        title = extract('title') or video_id
+        description = extract('description')
+        thumbnail = extract('poster', 'thumbnail')
 
         formats = []
-        for source in sources:
-            if not isinstance(source, dict):
-                continue
-            source_url = url_or_none(source.get('file'))
+        for format_id in ('hls', 'progressive'):
+            source_url = url_or_none(extract(format_id))
             if not source_url:
                 continue
             ext = determine_ext(source_url)
@@ -77,18 +77,19 @@ class APAIE(InfoExtractor):
                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',
                     m3u8_id='hls', fatal=False))
             else:
+                height = int_or_none(self._search_regex(
+                    r'(\d+)\.mp4', source_url, 'height', default=None))
                 formats.append({
                     'url': source_url,
+                    'format_id': format_id,
+                    'height': height,
                 })
         self._sort_formats(formats)
 
-        thumbnail = self._search_regex(
-            r'image\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
-            'thumbnail', fatal=False, group='url')
-
         return {
             'id': video_id,
-            'title': video_id,
+            'title': title,
+            'description': description,
             'thumbnail': thumbnail,
             'formats': formats,
         }

youtube_dl/extractor/appleconnect.py

@@ -9,10 +9,10 @@ from ..utils import (
 
 
 class AppleConnectIE(InfoExtractor):
-    _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)'
-    _TEST = {
+    _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/(?:id)?sa\.(?P<id>[\w-]+)'
+    _TESTS = [{
         'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
-        'md5': 'e7c38568a01ea45402570e6029206723',
+        'md5': 'c1d41f72c8bcaf222e089434619316e4',
         'info_dict': {
             'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
             'ext': 'm4v',
@@ -22,7 +22,10 @@ class AppleConnectIE(InfoExtractor):
             'upload_date': '20150710',
             'timestamp': 1436545535,
         },
-    }
+    }, {
+        'url': 'https://itunes.apple.com/us/post/sa.0fe0229f-2457-11e5-9f40-1bb645f2d5d9',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -36,7 +39,7 @@ class AppleConnectIE(InfoExtractor):
 
         video_data = self._parse_json(video_json, video_id)
         timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
-        like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count'))
+        like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count', default=None))
 
         return {
             'id': video_id,

youtube_dl/extractor/applepodcasts.py

@@ -0,0 +1,93 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    clean_podcast_url,
+    get_element_by_class,
+    int_or_none,
+    parse_codecs,
+    parse_iso8601,
+    try_get,
+)
+
+
+class ApplePodcastsIE(InfoExtractor):
+    _VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
+        'md5': '41dc31cd650143e530d9423b6b5a344f',
+        'info_dict': {
+            'id': '1000482637777',
+            'ext': 'mp3',
+            'title': '207 - Whitney Webb Returns',
+            'description': 'md5:75ef4316031df7b41ced4e7b987f79c6',
+            'upload_date': '20200705',
+            'timestamp': 1593932400,
+            'duration': 6454,
+            'series': 'The Tim Dillon Show',
+            'thumbnail': 're:.+[.](png|jpe?g|webp)',
+        }
+    }, {
+        'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
+        'only_matching': True,
+    }, {
+        'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns?i=1000482637777',
+        'only_matching': True,
+    }, {
+        'url': 'https://podcasts.apple.com/podcast/id1135137367?i=1000482637777',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        episode_id = self._match_id(url)
+        webpage = self._download_webpage(url, episode_id)
+        episode_data = {}
+        ember_data = {}
+        # new page type 2021-11
+        amp_data = self._parse_json(self._search_regex(
+            r'(?s)id="shoebox-media-api-cache-amp-podcasts"[^>]*>\s*({.+?})\s*<',
+            webpage, 'AMP data', default='{}'), episode_id, fatal=False) or {}
+        amp_data = try_get(amp_data,
+                           lambda a: self._parse_json(
+                               next(a[x] for x in iter(a) if episode_id in x),
+                               episode_id),
+                           dict) or {}
+        amp_data = amp_data.get('d') or []
+        episode_data = try_get(
+            amp_data,
+            lambda a: next(x for x in a
+                           if x['type'] == 'podcast-episodes' and x['id'] == episode_id),
+            dict)
+        if not episode_data:
+            # try pre 2021-11 page type: TODO: consider deleting if no longer used
+            ember_data = self._parse_json(self._search_regex(
+                r'(?s)id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
+                webpage, 'ember data'), episode_id) or {}
+            ember_data = ember_data.get(episode_id) or ember_data
+            episode_data = try_get(ember_data, lambda x: x['data'], dict)
+        episode = episode_data['attributes']
+        description = episode.get('description') or {}
+
+        series = None
+        for inc in (amp_data or ember_data.get('included') or []):
+            if inc.get('type') == 'media/podcast':
+                series = try_get(inc, lambda x: x['attributes']['name'])
+        series = series or clean_html(get_element_by_class('podcast-header__identity', webpage))
+
+        info = [{
+            'id': episode_id,
+            'title': episode['name'],
+            'url': clean_podcast_url(episode['assetUrl']),
+            'description': description.get('standard') or description.get('short'),
+            'timestamp': parse_iso8601(episode.get('releaseDateTime')),
+            'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
+            'series': series,
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }]
+        self._sort_formats(info)
+        info = info[0]
+        codecs = parse_codecs(info.get('ext', 'mp3'))
+        info.update(codecs)
+        return info

youtube_dl/extractor/archiveorg.py

@@ -2,15 +2,17 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    unified_strdate,
     clean_html,
+    extract_attributes,
+    unified_strdate,
+    unified_timestamp,
 )
 
 
 class ArchiveOrgIE(InfoExtractor):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
-    _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
         'md5': '8af1d4cf447933ed3c7f4871162602db',
@@ -19,8 +21,11 @@ class ArchiveOrgIE(InfoExtractor):
             'ext': 'ogg',
             'title': '1968 Demo - FJCC Conference Presentation Reel #1',
             'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
-            'upload_date': '19681210',
-            'uploader': 'SRI International'
+            'creator': 'SRI International',
+            'release_date': '19681210',
+            'uploader': 'SRI International',
+            'timestamp': 1268695290,
+            'upload_date': '20100315',
         }
     }, {
         'url': 'https://archive.org/details/Cops1922',
@@ -29,22 +34,43 @@ class ArchiveOrgIE(InfoExtractor):
             'id': 'Cops1922',
             'ext': 'mp4',
             'title': 'Buster Keaton\'s "Cops" (1922)',
-            'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
+            'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
+            'timestamp': 1387699629,
+            'upload_date': '20131222',
         }
     }, {
         'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
         'only_matching': True,
+    }, {
+        'url': 'https://archive.org/details/MSNBCW_20131125_040000_To_Catch_a_Predator/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
             'http://archive.org/embed/' + video_id, video_id)
-        jwplayer_playlist = self._parse_json(self._search_regex(
+
+        playlist = None
+        play8 = self._search_regex(
+            r'(<[^>]+\bclass=["\']js-play8-playlist[^>]+>)', webpage,
+            'playlist', default=None)
+        if play8:
+            attrs = extract_attributes(play8)
+            playlist = attrs.get('value')
+        if not playlist:
+            # Old jwplayer fallback
+            playlist = self._search_regex(
                 r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
-            webpage, 'jwplayer playlist'), video_id)
+                webpage, 'jwplayer playlist', default='[]')
+        jwplayer_playlist = self._parse_json(playlist, video_id, fatal=False)
+        if jwplayer_playlist:
             info = self._parse_jwplayer_data(
                 {'playlist': jwplayer_playlist}, video_id, base_url=url)
+        else:
+            # HTML5 media fallback
+            info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+            info['id'] = video_id
 
         def get_optional(metadata, field):
             return metadata.get(field, [None])[0]
@@ -58,8 +84,12 @@ class ArchiveOrgIE(InfoExtractor):
             'description': clean_html(get_optional(metadata, 'description')),
         })
         if info.get('_type') != 'playlist':
+            creator = get_optional(metadata, 'creator')
             info.update({
-                'uploader': get_optional(metadata, 'creator'),
-                'upload_date': unified_strdate(get_optional(metadata, 'date')),
+                'creator': creator,
+                'release_date': unified_strdate(get_optional(metadata, 'date')),
+                'uploader': get_optional(metadata, 'publisher') or creator,
+                'timestamp': unified_timestamp(get_optional(metadata, 'publicdate')),
+                'language': get_optional(metadata, 'language'),
             })
         return info

youtube_dl/extractor/ard.py

@@ -187,13 +187,13 @@ class ARDMediathekIE(ARDMediathekBaseIE):
             if doc.tag == 'rss':
                 return GenericIE()._extract_rss(url, video_id, doc)
 
-        title = self._html_search_regex(
+        title = self._og_search_title(webpage, default=None) or self._html_search_regex(
             [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
              r'<meta name="dcterms\.title" content="(.*?)"/>',
              r'<h4 class="headline">(.*?)</h4>',
              r'<title[^>]*>(.*?)</title>'],
             webpage, 'title')
-        description = self._html_search_meta(
+        description = self._og_search_description(webpage, default=None) or self._html_search_meta(
             'dcterms.abstract', webpage, 'description', default=None)
         if description is None:
             description = self._html_search_meta(
@@ -249,31 +249,40 @@ class ARDMediathekIE(ARDMediathekBaseIE):
 
 
 class ARDIE(InfoExtractor):
-    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _VALID_URL = r'(?P<mainurl>https?://(?:www\.)?daserste\.de/(?:[^/?#&]+/)+(?P<id>[^/?#&]+))\.html'
     _TESTS = [{
-        # available till 14.02.2019
-        'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html',
-        'md5': '8e4ec85f31be7c7fc08a26cdbc5a1f49',
+        # available till 7.01.2022
+        'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-die-woche-video100.html',
+        'md5': '867d8aa39eeaf6d76407c5ad1bb0d4c1',
         'info_dict': {
-            'display_id': 'das-groko-drama-zerlegen-sich-die-volksparteien-video',
-            'id': '102',
+            'id': 'maischberger-die-woche-video100',
+            'display_id': 'maischberger-die-woche-video100',
             'ext': 'mp4',
-            'duration': 4435.0,
-            'title': 'Das GroKo-Drama: Zerlegen sich die Volksparteien?',
-            'upload_date': '20180214',
+            'duration': 3687.0,
+            'title': 'maischberger. die woche vom 7. Januar 2021',
+            'upload_date': '20210107',
             'thumbnail': r're:^https?://.*\.jpg$',
         },
     }, {
-        'url': 'https://www.daserste.de/information/reportage-dokumentation/erlebnis-erde/videosextern/woelfe-und-herdenschutzhunde-ungleiche-brueder-102.html',
+        'url': 'https://www.daserste.de/information/politik-weltgeschehen/morgenmagazin/videosextern/dominik-kahun-aus-der-nhl-direkt-zur-weltmeisterschaft-100.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.daserste.de/information/nachrichten-wetter/tagesthemen/videosextern/tagesthemen-17736.html',
         'only_matching': True,
     }, {
         'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
         'only_matching': True,
+    }, {
+        'url': 'https://www.daserste.de/unterhaltung/serie/in-aller-freundschaft-die-jungen-aerzte/Drehpause-100.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.daserste.de/unterhaltung/film/filmmittwoch-im-ersten/videos/making-ofwendezeit-video-100.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('id')
 
         player_url = mobj.group('mainurl') + '~playerXml.xml'
         doc = self._download_xml(player_url, display_id)
@@ -284,26 +293,63 @@ class ARDIE(InfoExtractor):
 
         formats = []
         for a in video_node.findall('.//asset'):
+            file_name = xpath_text(a, './fileName', default=None)
+            if not file_name:
+                continue
+            format_type = a.attrib.get('type')
+            format_url = url_or_none(file_name)
+            if format_url:
+                ext = determine_ext(file_name)
+                if ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, display_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id=format_type or 'hls', fatal=False))
+                    continue
+                elif ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        update_url_query(format_url, {'hdcore': '3.7.0'}),
+                        display_id, f4m_id=format_type or 'hds', fatal=False))
+                    continue
             f = {
-                'format_id': a.attrib['type'],
-                'width': int_or_none(a.find('./frameWidth').text),
-                'height': int_or_none(a.find('./frameHeight').text),
-                'vbr': int_or_none(a.find('./bitrateVideo').text),
-                'abr': int_or_none(a.find('./bitrateAudio').text),
-                'vcodec': a.find('./codecVideo').text,
-                'tbr': int_or_none(a.find('./totalBitrate').text),
+                'format_id': format_type,
+                'width': int_or_none(xpath_text(a, './frameWidth')),
+                'height': int_or_none(xpath_text(a, './frameHeight')),
+                'vbr': int_or_none(xpath_text(a, './bitrateVideo')),
+                'abr': int_or_none(xpath_text(a, './bitrateAudio')),
+                'vcodec': xpath_text(a, './codecVideo'),
+                'tbr': int_or_none(xpath_text(a, './totalBitrate')),
             }
-            if a.find('./serverPrefix').text:
-                f['url'] = a.find('./serverPrefix').text
-                f['playpath'] = a.find('./fileName').text
+            server_prefix = xpath_text(a, './serverPrefix', default=None)
+            if server_prefix:
+                f.update({
+                    'url': server_prefix,
+                    'playpath': file_name,
+                })
             else:
-                f['url'] = a.find('./fileName').text
+                if not format_url:
+                    continue
+                f['url'] = format_url
             formats.append(f)
         self._sort_formats(formats)
 
+        _SUB_FORMATS = (
+            ('./dataTimedText', 'ttml'),
+            ('./dataTimedTextNoOffset', 'ttml'),
+            ('./dataTimedTextVtt', 'vtt'),
+        )
+
+        subtitles = {}
+        for subsel, subext in _SUB_FORMATS:
+            for node in video_node.findall(subsel):
+                subtitles.setdefault('de', []).append({
+                    'url': node.attrib['url'],
+                    'ext': subext,
+                })
+
         return {
-            'id': mobj.group('id'),
+            'id': xpath_text(video_node, './videoId', default=display_id),
             'formats': formats,
+            'subtitles': subtitles,
             'display_id': display_id,
             'title': video_node.find('./title').text,
             'duration': parse_duration(video_node.find('./duration').text),
@@ -313,19 +359,19 @@ class ARDIE(InfoExtractor):
 
 
 class ARDBetaMediathekIE(ARDMediathekBaseIE):
-    _VALID_URL = r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?P<client>[^/]+)/(?:player|live|video)/(?P<display_id>(?:[^/]+/)*)(?P<video_id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?:[^/]+/)?(?:player|live|video)/(?:[^/]+/)*(?P<id>Y3JpZDovL[a-zA-Z0-9]+)'
     _TESTS = [{
-        'url': 'https://ardmediathek.de/ard/video/die-robuste-roswita/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
-        'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f',
+        'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
+        'md5': 'a1dc75a39c61601b980648f7c9f9f71d',
         'info_dict': {
             'display_id': 'die-robuste-roswita',
-            'id': '70153354',
+            'id': '78566716',
             'title': 'Die robuste Roswita',
-            'description': r're:^Der Mord.*trüber ist als die Ilm.',
+            'description': r're:^Der Mord.*totgeglaubte Ehefrau Roswita',
             'duration': 5316,
-            'thumbnail': 'https://img.ardmediathek.de/standard/00/70/15/33/90/-1852531467/16x9/960?mandant=ard',
-            'timestamp': 1577047500,
-            'upload_date': '20191222',
+            'thumbnail': 'https://img.ardmediathek.de/standard/00/78/56/67/84/575672121/16x9/960?mandant=ard',
+            'timestamp': 1596658200,
+            'upload_date': '20200805',
             'ext': 'mp4',
         },
     }, {
@@ -343,22 +389,22 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
     }, {
         'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg',
         'only_matching': True,
+    }, {
+        'url': 'https://www.ardmediathek.de/video/coronavirus-update-ndr-info/astrazeneca-kurz-lockdown-und-pims-syndrom-81/ndr/Y3JpZDovL25kci5kZS84NzE0M2FjNi0wMWEwLTQ5ODEtOTE5NS1mOGZhNzdhOTFmOTI/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3dkci5kZS9CZWl0cmFnLWQ2NDJjYWEzLTMwZWYtNGI4NS1iMTI2LTU1N2UxYTcxOGIzOQ/tatort-duo-koeln-leipzig-ihr-kinderlein-kommet',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('video_id')
-        display_id = mobj.group('display_id')
-        if display_id:
-            display_id = display_id.rstrip('/')
-        if not display_id:
-            display_id = video_id
+        video_id = self._match_id(url)
 
         player_page = self._download_json(
             'https://api.ardmediathek.de/public-gateway',
-            display_id, data=json.dumps({
+            video_id, data=json.dumps({
                 'query': '''{
-  playerPage(client:"%s", clipId: "%s") {
+  playerPage(client: "ard", clipId: "%s") {
     blockedByFsk
     broadcastedOn
     maturityContentRating
@@ -388,7 +434,7 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
       }
     }
   }
-}''' % (mobj.group('client'), video_id),
+}''' % video_id,
             }).encode(), headers={
                 'Content-Type': 'application/json'
             })['data']['playerPage']
@@ -413,7 +459,6 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
                 r'\(FSK\s*(\d+)\)\s*$', description, 'age limit', default=None))
         info.update({
             'age_limit': age_limit,
-            'display_id': display_id,
             'title': title,
             'description': description,
             'timestamp': unified_timestamp(player_page.get('broadcastedOn')),

youtube_dl/extractor/arnes.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+    remove_start,
+)
+
+
+class ArnesIE(InfoExtractor):
+    IE_NAME = 'video.arnes.si'
+    IE_DESC = 'Arnes Video'
+    _VALID_URL = r'https?://video\.arnes\.si/(?:[a-z]{2}/)?(?:watch|embed|api/(?:asset|public/video))/(?P<id>[0-9a-zA-Z]{12})'
+    _TESTS = [{
+        'url': 'https://video.arnes.si/watch/a1qrWTOQfVoU?t=10',
+        'md5': '4d0f4d0a03571b33e1efac25fd4a065d',
+        'info_dict': {
+            'id': 'a1qrWTOQfVoU',
+            'ext': 'mp4',
+            'title': 'Linearna neodvisnost, definicija',
+            'description': 'Linearna neodvisnost, definicija',
+            'license': 'PRIVATE',
+            'creator': 'Polona Oblak',
+            'timestamp': 1585063725,
+            'upload_date': '20200324',
+            'channel': 'Polona Oblak',
+            'channel_id': 'q6pc04hw24cj',
+            'channel_url': 'https://video.arnes.si/?channel=q6pc04hw24cj',
+            'duration': 596.75,
+            'view_count': int,
+            'tags': ['linearna_algebra'],
+            'start_time': 10,
+        }
+    }, {
+        'url': 'https://video.arnes.si/api/asset/s1YjnV7hadlC/play.mp4',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/embed/s1YjnV7hadlC',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/en/watch/s1YjnV7hadlC',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/embed/s1YjnV7hadlC?t=123&hideRelated=1',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/api/public/video/s1YjnV7hadlC',
+        'only_matching': True,
+    }]
+    _BASE_URL = 'https://video.arnes.si'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            self._BASE_URL + '/api/public/video/' + video_id, video_id)['data']
+        title = video['title']
+
+        formats = []
+        for media in (video.get('media') or []):
+            media_url = media.get('url')
+            if not media_url:
+                continue
+            formats.append({
+                'url': self._BASE_URL + media_url,
+                'format_id': remove_start(media.get('format'), 'FORMAT_'),
+                'format_note': media.get('formatTranslation'),
+                'width': int_or_none(media.get('width')),
+                'height': int_or_none(media.get('height')),
+            })
+        self._sort_formats(formats)
+
+        channel = video.get('channel') or {}
+        channel_id = channel.get('url')
+        thumbnail = video.get('thumbnailUrl')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': self._BASE_URL + thumbnail,
+            'description': video.get('description'),
+            'license': video.get('license'),
+            'creator': video.get('author'),
+            'timestamp': parse_iso8601(video.get('creationTime')),
+            'channel': channel.get('name'),
+            'channel_id': channel_id,
+            'channel_url': self._BASE_URL + '/?channel=' + channel_id if channel_id else None,
+            'duration': float_or_none(video.get('duration'), 1000),
+            'view_count': int_or_none(video.get('views')),
+            'tags': video.get('hashtags'),
+            'start_time': int_or_none(compat_parse_qs(
+                compat_urllib_parse_urlparse(url).query).get('t', [None])[0]),
+        }

youtube_dl/extractor/arte.py

@@ -12,6 +12,7 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     qualities,
+    strip_or_none,
     try_get,
     unified_strdate,
     url_or_none,
@@ -252,3 +253,49 @@ class ArteTVPlaylistIE(ArteTVBaseIE):
         title = collection.get('title')
         description = collection.get('shortDescription') or collection.get('teaserText')
         return self.playlist_result(entries, playlist_id, title, description)
+
+
+class ArteTVCategoryIE(ArteTVBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>%s)/videos/(?P<id>[\w-]+(?:/[\w-]+)*)/?\s*$' % ArteTVBaseIE._ARTE_LANGUAGES
+    _TESTS = [{
+        'url': 'https://www.arte.tv/en/videos/politics-and-society/',
+        'info_dict': {
+            'id': 'politics-and-society',
+            'title': 'Politics and society',
+            'description': 'Investigative documentary series, geopolitical analysis, and international commentary',
+        },
+        'playlist_mincount': 13,
+    },
+    ]
+
+    @classmethod
+    def suitable(cls, url):
+        return (
+            not any(ie.suitable(url) for ie in (ArteTVIE, ArteTVPlaylistIE, ))
+            and super(ArteTVCategoryIE, cls).suitable(url))
+
+    def _real_extract(self, url):
+        lang, playlist_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(url, playlist_id)
+
+        items = []
+        for video in re.finditer(
+                r'<a\b[^>]*?href\s*=\s*(?P<q>"|\'|\b)(?P<url>https?://www\.arte\.tv/%s/videos/[\w/-]+)(?P=q)' % lang,
+                webpage):
+            video = video.group('url')
+            if video == url:
+                continue
+            if any(ie.suitable(video) for ie in (ArteTVIE, ArteTVPlaylistIE, )):
+                items.append(video)
+
+        if items:
+            title = (self._og_search_title(webpage, default=None)
+                     or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title>', default=None))
+            title = strip_or_none(title.rsplit('|', 1)[0]) or self._generic_title(url)
+
+            result = self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=title)
+            if result:
+                description = self._og_search_description(webpage, default=None)
+                if description:
+                    result['description'] = description
+                return result

youtube_dl/extractor/audiomack.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class AudiomackIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P<id>[\w/-]+)'
+    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:song/|(?=.+/song/))(?P<id>[\w/-]+)'
     IE_NAME = 'audiomack'
     _TESTS = [
         # hosted on audiomack
@@ -29,25 +29,27 @@ class AudiomackIE(InfoExtractor):
             }
         },
         # audiomack wrapper around soundcloud song
+        # Needs new test URL.
         {
             'add_ie': ['Soundcloud'],
             'url': 'http://www.audiomack.com/song/hip-hop-daily/black-mamba-freestyle',
-            'info_dict': {
-                'id': '258901379',
-                'ext': 'mp3',
-                'description': 'mamba day freestyle for the legend Kobe Bryant ',
-                'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
-                'uploader': 'ILOVEMAKONNEN',
-                'upload_date': '20160414',
-            }
+            'only_matching': True,
+            # 'info_dict': {
+                # 'id': '258901379',
+                # 'ext': 'mp3',
+                # 'description': 'mamba day freestyle for the legend Kobe Bryant ',
+                # 'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
+                # 'uploader': 'ILOVEMAKONNEN',
+                # 'upload_date': '20160414',
+            # }
         },
     ]
 
     def _real_extract(self, url):
-        # URLs end with [uploader name]/[uploader title]
+        # URLs end with [uploader name]/song/[uploader title]
         # this title is whatever the user types in, and is rarely
         # the proper song title.  Real metadata is in the api response
-        album_url_tag = self._match_id(url)
+        album_url_tag = self._match_id(url).replace('/song/', '/')
 
         # Request the extended version of the api for extra fields like artist and title
         api_response = self._download_json(
@@ -73,13 +75,13 @@ class AudiomackIE(InfoExtractor):
 
 
 class AudiomackAlbumIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)'
+    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:album/|(?=.+/album/))(?P<id>[\w/-]+)'
     IE_NAME = 'audiomack:album'
     _TESTS = [
         # Standard album playlist
         {
             'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
-            'playlist_count': 15,
+            'playlist_count': 11,
             'info_dict':
             {
                 'id': '812251',
@@ -95,24 +97,24 @@ class AudiomackAlbumIE(InfoExtractor):
             },
             'playlist': [{
                 'info_dict': {
-                    'title': 'PPP (Pistol P Project) - 9. Heaven or Hell (CHIMACA) ft Zuse (prod by DJ FU)',
-                    'id': '837577',
+                    'title': 'PPP (Pistol P Project) - 10. 4 Minutes Of Hell Part 4 (prod by DY OF 808 MAFIA)',
+                    'id': '837580',
                     'ext': 'mp3',
                     'uploader': 'Lil Herb a.k.a. G Herbo',
                 }
             }],
             'params': {
-                'playliststart': 9,
-                'playlistend': 9,
+                'playliststart': 2,
+                'playlistend': 2,
             }
         }
     ]
 
     def _real_extract(self, url):
-        # URLs end with [uploader name]/[uploader title]
+        # URLs end with [uploader name]/album/[uploader title]
         # this title is whatever the user types in, and is rarely
         # the proper song title.  Real metadata is in the api response
-        album_url_tag = self._match_id(url)
+        album_url_tag = self._match_id(url).replace('/album/', '/')
         result = {'_type': 'playlist', 'entries': []}
         # There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
         # Therefore we don't know how many songs the album has and must infi-loop until failure
@@ -134,7 +136,7 @@ class AudiomackAlbumIE(InfoExtractor):
                 # Pull out the album metadata and add to result (if it exists)
                 for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
                     if apikey in api_response and resultkey not in result:
-                        result[resultkey] = api_response[apikey]
+                        result[resultkey] = compat_str(api_response[apikey])
                 song_id = url_basename(api_response['url']).rpartition('.')[0]
                 result['entries'].append({
                     'id': compat_str(api_response.get('id', song_id)),

youtube_dl/extractor/awaan.py

@@ -48,6 +48,7 @@ class AWAANBaseIE(InfoExtractor):
             'duration': int_or_none(video_data.get('duration')),
             'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
             'is_live': is_live,
+            'uploader_id': video_data.get('user_id'),
         }
 
 
@@ -107,6 +108,7 @@ class AWAANLiveIE(AWAANBaseIE):
             'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
             'upload_date': '20150107',
             'timestamp': 1420588800,
+            'uploader_id': '71',
         },
         'params': {
             # m3u8 download

youtube_dl/extractor/azmedien.py

@@ -47,7 +47,7 @@ class AZMedienIE(InfoExtractor):
         'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
         'only_matching': True
     }]
-    _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/cb9f2f81ed22e9b47f4ca64ea3cc5a5d13e88d1d'
+    _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/a4016f65fe62b81dc6664dd9f4910e4ab40383be'
     _PARTNER_ID = '1719221'
 
     def _real_extract(self, url):

youtube_dl/extractor/bandaichannel.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .brightcove import BrightcoveNewIE
+from ..utils import extract_attributes
+
+
+class BandaiChannelIE(BrightcoveNewIE):
+    IE_NAME = 'bandaichannel'
+    _VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
+    _TESTS = [{
+        'url': 'https://www.b-ch.com/titles/514/001',
+        'md5': 'a0f2d787baa5729bed71108257f613a4',
+        'info_dict': {
+            'id': '6128044564001',
+            'ext': 'mp4',
+            'title': 'メタルファイターMIKU 第1話',
+            'timestamp': 1580354056,
+            'uploader_id': '5797077852001',
+            'upload_date': '20200130',
+            'duration': 1387.733,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        attrs = extract_attributes(self._search_regex(
+            r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
+        bc = self._download_json(
+            'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
+            video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
+        return self._parse_brightcove_metadata(bc, bc['id'])

youtube_dl/extractor/bandcamp.py

@@ -49,6 +49,7 @@ class BandcampIE(InfoExtractor):
             'uploader': 'Ben Prunty',
             'timestamp': 1396508491,
             'upload_date': '20140403',
+            'release_timestamp': 1396483200,
             'release_date': '20140403',
             'duration': 260.877,
             'track': 'Lanius (Battle)',
@@ -69,6 +70,7 @@ class BandcampIE(InfoExtractor):
             'uploader': 'Mastodon',
             'timestamp': 1322005399,
             'upload_date': '20111122',
+            'release_timestamp': 1076112000,
             'release_date': '20040207',
             'duration': 120.79,
             'track': 'Hail to Fire',
@@ -197,7 +199,7 @@ class BandcampIE(InfoExtractor):
             'thumbnail': thumbnail,
             'uploader': artist,
             'timestamp': timestamp,
-            'release_date': unified_strdate(tralbum.get('album_release_date')),
+            'release_timestamp': unified_timestamp(tralbum.get('album_release_date')),
             'duration': duration,
             'track': track,
             'track_number': track_number,

youtube_dl/extractor/bbc.py

@@ -1,37 +1,46 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import functools
 import itertools
+import json
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_etree_Element,
+    compat_HTTPError,
+    compat_parse_qs,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_parse_urlparse,
+    compat_urlparse,
+)
 from ..utils import (
+    ExtractorError,
+    OnDemandPagedList,
     clean_html,
     dict_get,
-    ExtractorError,
     float_or_none,
     get_element_by_class,
     int_or_none,
     js_to_json,
     parse_duration,
     parse_iso8601,
+    strip_or_none,
     try_get,
     unescapeHTML,
+    unified_timestamp,
     url_or_none,
     urlencode_postdata,
     urljoin,
 )
-from ..compat import (
-    compat_etree_Element,
-    compat_HTTPError,
-    compat_urlparse,
-)
 
 
 class BBCCoUkIE(InfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _ID_REGEX = r'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})'
+    _ID_REGEX = r'(?:[pbml][\da-z]{7}|w[\da-z]{7,14})'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:www\.)?bbc\.co\.uk/
@@ -387,9 +396,17 @@ class BBCCoUkIE(InfoExtractor):
                         formats.extend(self._extract_mpd_formats(
                             href, programme_id, mpd_id=format_id, fatal=False))
                     elif transfer_format == 'hls':
-                        formats.extend(self._extract_m3u8_formats(
+                        # TODO: let expected_status be passed into _extract_xxx_formats() instead
+                        try:
+                            fmts = self._extract_m3u8_formats(
                                 href, programme_id, ext='mp4', entry_protocol='m3u8_native',
-                            m3u8_id=format_id, fatal=False))
+                                m3u8_id=format_id, fatal=False)
+                        except ExtractorError as e:
+                            if not (isinstance(e.exc_info[1], compat_urllib_error.HTTPError)
+                                    and e.exc_info[1].code in (403, 404)):
+                                raise
+                            fmts = []
+                        formats.extend(fmts)
                     elif transfer_format == 'hds':
                         formats.extend(self._extract_f4m_formats(
                             href, programme_id, f4m_id=format_id, fatal=False))
@@ -756,23 +773,44 @@ class BBCIE(BBCCoUkIE):
         'only_matching': True,
     }, {
         # custom redirection to www.bbc.com
+        # also, video with window.__INITIAL_DATA__
         'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
-        'only_matching': True,
+        'info_dict': {
+            'id': 'p02xzws1',
+            'ext': 'mp4',
+            'title': "Pluto may have 'nitrogen glaciers'",
+            'description': 'md5:6a95b593f528d7a5f2605221bc56912f',
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'timestamp': 1437785037,
+            'upload_date': '20150725',
+        },
+    }, {
+        # video with window.__INITIAL_DATA__ and value as JSON string
+        'url': 'https://www.bbc.com/news/av/world-europe-59468682',
+        'info_dict': {
+            'id': 'p0b71qth',
+            'ext': 'mp4',
+            'title': 'Why France is making this woman a national hero',
+            'description': 'md5:7affdfab80e9c3a1f976230a1ff4d5e4',
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'timestamp': 1638230731,
+            'upload_date': '20211130',
+        },
     }, {
         # single video article embedded with data-media-vpid
         'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
         'only_matching': True,
     }, {
+        # bbcthreeConfig
         'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1',
         'info_dict': {
             'id': 'p06556y7',
             'ext': 'mp4',
-            'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
-            'description': 'md5:4b7dfd063d5a789a1512e99662be3ddd',
+            'title': 'Things Not To Say to people that live on council estates',
+            'description': "From being labelled a 'chav', to the presumption that they're 'scroungers', people who live on council estates encounter all kinds of prejudices and false assumptions about themselves, their families, and their lifestyles. Here, eight people discuss the common statements, misconceptions, and clichés that they're tired of hearing.",
+            'duration': 360,
+            'thumbnail': r're:https?://.+/.+\.jpg',
         },
-        'params': {
-            'skip_download': True,
-        }
     }, {
         # window.__PRELOADED_STATE__
         'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl',
@@ -793,11 +831,25 @@ class BBCIE(BBCCoUkIE):
             'description': 'Learn English words and phrases from this story',
         },
         'add_ie': [BBCCoUkIE.ie_key()],
+    }, {
+        # BBC Reel
+        'url': 'https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness',
+        'info_dict': {
+            'id': 'p07c6sb9',
+            'ext': 'mp4',
+            'title': 'How positive thinking is harming your happiness',
+            'alt_title': 'The downsides of positive thinking',
+            'description': 'md5:fad74b31da60d83b8265954ee42d85b4',
+            'duration': 235,
+            'thumbnail': r're:https?://.+/p07c9dsr.jpg',
+            'upload_date': '20190604',
+            'categories': ['Psychology'],
+        },
     }]
 
     @classmethod
     def suitable(cls, url):
-        EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE)
+        EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerEpisodesIE, BBCCoUkIPlayerGroupIE, BBCCoUkPlaylistIE)
         return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
                 else super(BBCIE, cls).suitable(url))
 
@@ -929,7 +981,7 @@ class BBCIE(BBCCoUkIE):
                                     else:
                                         entry['title'] = info['title']
                                         entry['formats'].extend(info['formats'])
-                                except Exception as e:
+                                except ExtractorError as e:
                                     # Some playlist URL may fail with 500, at the same time
                                     # the other one may work fine (e.g.
                                     # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
@@ -980,6 +1032,37 @@ class BBCIE(BBCCoUkIE):
                 'subtitles': subtitles,
             }
 
+        # bbc reel (e.g. https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness)
+        initial_data = self._parse_json(self._html_search_regex(
+            r'<script[^>]+id=(["\'])initial-data\1[^>]+data-json=(["\'])(?P<json>(?:(?!\2).)+)',
+            webpage, 'initial data', default='{}', group='json'), playlist_id, fatal=False)
+        if initial_data:
+            init_data = try_get(
+                initial_data, lambda x: x['initData']['items'][0], dict) or {}
+            smp_data = init_data.get('smpData') or {}
+            clip_data = try_get(smp_data, lambda x: x['items'][0], dict) or {}
+            version_id = clip_data.get('versionID')
+            if version_id:
+                title = smp_data['title']
+                formats, subtitles = self._download_media_selector(version_id)
+                self._sort_formats(formats)
+                image_url = smp_data.get('holdingImageURL')
+                display_date = init_data.get('displayDate')
+                topic_title = init_data.get('topicTitle')
+
+                return {
+                    'id': version_id,
+                    'title': title,
+                    'formats': formats,
+                    'alt_title': init_data.get('shortTitle'),
+                    'thumbnail': image_url.replace('$recipe', 'raw') if image_url else None,
+                    'description': smp_data.get('summary') or init_data.get('shortSummary'),
+                    'upload_date': display_date.replace('-', '') if display_date else None,
+                    'subtitles': subtitles,
+                    'duration': int_or_none(clip_data.get('duration')),
+                    'categories': [topic_title] if topic_title else None,
+                }
+
         # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
         # There are several setPayload calls may be present but the video
         # seems to be always related to the first one
@@ -1041,7 +1124,7 @@ class BBCIE(BBCCoUkIE):
                 thumbnail = None
                 image_url = current_programme.get('image_url')
                 if image_url:
-                    thumbnail = image_url.replace('{recipe}', '1920x1920')
+                    thumbnail = image_url.replace('{recipe}', 'raw')
                 return {
                     'id': programme_id,
                     'title': title,
@@ -1100,9 +1183,16 @@ class BBCIE(BBCCoUkIE):
                 return self.playlist_result(
                     entries, playlist_id, playlist_title, playlist_description)
 
-        initial_data = self._parse_json(self._search_regex(
-            r'window\.__INITIAL_DATA__\s*=\s*({.+?});', webpage,
-            'preload state', default='{}'), playlist_id, fatal=False)
+        initial_data = self._search_regex(
+            r'window\.__INITIAL_DATA__\s*=\s*("{.+?}")\s*;', webpage,
+            'quoted preload state', default=None)
+        if initial_data is None:
+            initial_data = self._search_regex(
+                r'window\.__INITIAL_DATA__\s*=\s*({.+?})\s*;', webpage,
+                'preload state', default={})
+        else:
+            initial_data = self._parse_json(initial_data or '"{}"', playlist_id, fatal=False)
+        initial_data = self._parse_json(initial_data, playlist_id, fatal=False)
         if initial_data:
             def parse_media(media):
                 if not media:
@@ -1114,19 +1204,39 @@ class BBCIE(BBCCoUkIE):
                         continue
                     formats, subtitles = self._download_media_selector(item_id)
                     self._sort_formats(formats)
+                    item_desc = None
+                    blocks = try_get(media, lambda x: x['summary']['blocks'], list)
+                    if blocks:
+                        summary = []
+                        for block in blocks:
+                            text = try_get(block, lambda x: x['model']['text'], compat_str)
+                            if text:
+                                summary.append(text)
+                        if summary:
+                            item_desc = '\n\n'.join(summary)
+                    item_time = None
+                    for meta in try_get(media, lambda x: x['metadata']['items'], list) or []:
+                        if try_get(meta, lambda x: x['label']) == 'Published':
+                            item_time = unified_timestamp(meta.get('timestamp'))
+                            break
                     entries.append({
                         'id': item_id,
                         'title': item_title,
                         'thumbnail': item.get('holdingImageUrl'),
                         'formats': formats,
                         'subtitles': subtitles,
+                        'timestamp': item_time,
+                        'description': strip_or_none(item_desc),
                     })
             for resp in (initial_data.get('data') or {}).values():
                 name = resp.get('name')
                 if name == 'media-experience':
                     parse_media(try_get(resp, lambda x: x['data']['initialItem']['mediaItem'], dict))
                 elif name == 'article':
-                    for block in (try_get(resp, lambda x: x['data']['blocks'], list) or []):
+                    for block in (try_get(resp,
+                                          (lambda x: x['data']['blocks'],
+                                           lambda x: x['data']['content']['model']['blocks'],),
+                                          list) or []):
                         if block.get('type') != 'media':
                             continue
                         parse_media(block.get('model'))
@@ -1293,21 +1403,149 @@ class BBCCoUkPlaylistBaseIE(InfoExtractor):
             playlist_id, title, description)
 
 
-class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
-    IE_NAME = 'bbc.co.uk:iplayer:playlist'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
-    _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
-    _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
+class BBCCoUkIPlayerPlaylistBaseIE(InfoExtractor):
+    _VALID_URL_TMPL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/%%s/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
+
+    @staticmethod
+    def _get_default(episode, key, default_key='default'):
+        return try_get(episode, lambda x: x[key][default_key])
+
+    def _get_description(self, data):
+        synopsis = data.get(self._DESCRIPTION_KEY) or {}
+        return dict_get(synopsis, ('large', 'medium', 'small'))
+
+    def _fetch_page(self, programme_id, per_page, series_id, page):
+        elements = self._get_elements(self._call_api(
+            programme_id, per_page, page + 1, series_id))
+        for element in elements:
+            episode = self._get_episode(element)
+            episode_id = episode.get('id')
+            if not episode_id:
+                continue
+            thumbnail = None
+            image = self._get_episode_image(episode)
+            if image:
+                thumbnail = image.replace('{recipe}', 'raw')
+            category = self._get_default(episode, 'labels', 'category')
+            yield {
+                '_type': 'url',
+                'id': episode_id,
+                'title': self._get_episode_field(episode, 'subtitle'),
+                'url': 'https://www.bbc.co.uk/iplayer/episode/' + episode_id,
+                'thumbnail': thumbnail,
+                'description': self._get_description(episode),
+                'categories': [category] if category else None,
+                'series': self._get_episode_field(episode, 'title'),
+                'ie_key': BBCCoUkIE.ie_key(),
+            }
+
+    def _real_extract(self, url):
+        pid = self._match_id(url)
+        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        series_id = qs.get('seriesId', [None])[0]
+        page = qs.get('page', [None])[0]
+        per_page = 36 if page else self._PAGE_SIZE
+        fetch_page = functools.partial(self._fetch_page, pid, per_page, series_id)
+        entries = fetch_page(int(page) - 1) if page else OnDemandPagedList(fetch_page, self._PAGE_SIZE)
+        playlist_data = self._get_playlist_data(self._call_api(pid, 1))
+        return self.playlist_result(
+            entries, pid, self._get_playlist_title(playlist_data),
+            self._get_description(playlist_data))
+
+
+class BBCCoUkIPlayerEpisodesIE(BBCCoUkIPlayerPlaylistBaseIE):
+    IE_NAME = 'bbc.co.uk:iplayer:episodes'
+    _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'episodes'
     _TESTS = [{
         'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
         'info_dict': {
             'id': 'b05rcz9v',
             'title': 'The Disappearance',
-            'description': 'French thriller serial about a missing teenager.',
+            'description': 'md5:58eb101aee3116bad4da05f91179c0cb',
         },
-        'playlist_mincount': 6,
-        'skip': 'This programme is not currently available on BBC iPlayer',
+        'playlist_mincount': 8,
     }, {
+        # all seasons
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/b094m5t9/doctor-foster',
+        'info_dict': {
+            'id': 'b094m5t9',
+            'title': 'Doctor Foster',
+            'description': 'md5:5aa9195fad900e8e14b52acd765a9fd6',
+        },
+        'playlist_mincount': 10,
+    }, {
+        # explicit season
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/b094m5t9/doctor-foster?seriesId=b094m6nv',
+        'info_dict': {
+            'id': 'b094m5t9',
+            'title': 'Doctor Foster',
+            'description': 'md5:5aa9195fad900e8e14b52acd765a9fd6',
+        },
+        'playlist_mincount': 5,
+    }, {
+        # all pages
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/m0004c4v/beechgrove',
+        'info_dict': {
+            'id': 'm0004c4v',
+            'title': 'Beechgrove',
+            'description': 'Gardening show that celebrates Scottish horticulture and growing conditions.',
+        },
+        'playlist_mincount': 37,
+    }, {
+        # explicit page
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/m0004c4v/beechgrove?page=2',
+        'info_dict': {
+            'id': 'm0004c4v',
+            'title': 'Beechgrove',
+            'description': 'Gardening show that celebrates Scottish horticulture and growing conditions.',
+        },
+        'playlist_mincount': 1,
+    }]
+    _PAGE_SIZE = 100
+    _DESCRIPTION_KEY = 'synopsis'
+
+    def _get_episode_image(self, episode):
+        return self._get_default(episode, 'image')
+
+    def _get_episode_field(self, episode, field):
+        return self._get_default(episode, field)
+
+    @staticmethod
+    def _get_elements(data):
+        return data['entities']['results']
+
+    @staticmethod
+    def _get_episode(element):
+        return element.get('episode') or {}
+
+    def _call_api(self, pid, per_page, page=1, series_id=None):
+        variables = {
+            'id': pid,
+            'page': page,
+            'perPage': per_page,
+        }
+        if series_id:
+            variables['sliceId'] = series_id
+        return self._download_json(
+            'https://graph.ibl.api.bbc.co.uk/', pid, headers={
+                'Content-Type': 'application/json'
+            }, data=json.dumps({
+                'id': '5692d93d5aac8d796a0305e895e61551',
+                'variables': variables,
+            }).encode('utf-8'))['data']['programme']
+
+    @staticmethod
+    def _get_playlist_data(data):
+        return data
+
+    def _get_playlist_title(self, data):
+        return self._get_default(data, 'title')
+
+
+class BBCCoUkIPlayerGroupIE(BBCCoUkIPlayerPlaylistBaseIE):
+    IE_NAME = 'bbc.co.uk:iplayer:group'
+    _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'group'
+    _TESTS = [{
         # Available for over a year unlike 30 days for most other programmes
         'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32',
         'info_dict': {
@@ -1316,14 +1554,56 @@ class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
             'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
         },
         'playlist_mincount': 10,
+    }, {
+        # all pages
+        'url': 'https://www.bbc.co.uk/iplayer/group/p081d7j7',
+        'info_dict': {
+            'id': 'p081d7j7',
+            'title': 'Music in Scotland',
+            'description': 'Perfomances in Scotland and programmes featuring Scottish acts.',
+        },
+        'playlist_mincount': 47,
+    }, {
+        # explicit page
+        'url': 'https://www.bbc.co.uk/iplayer/group/p081d7j7?page=2',
+        'info_dict': {
+            'id': 'p081d7j7',
+            'title': 'Music in Scotland',
+            'description': 'Perfomances in Scotland and programmes featuring Scottish acts.',
+        },
+        'playlist_mincount': 11,
     }]
+    _PAGE_SIZE = 200
+    _DESCRIPTION_KEY = 'synopses'
 
-    def _extract_title_and_description(self, webpage):
-        title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
-        description = self._search_regex(
-            r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
-            webpage, 'description', fatal=False, group='value')
-        return title, description
+    def _get_episode_image(self, episode):
+        return self._get_default(episode, 'images', 'standard')
+
+    def _get_episode_field(self, episode, field):
+        return episode.get(field)
+
+    @staticmethod
+    def _get_elements(data):
+        return data['elements']
+
+    @staticmethod
+    def _get_episode(element):
+        return element
+
+    def _call_api(self, pid, per_page, page=1, series_id=None):
+        return self._download_json(
+            'http://ibl.api.bbc.co.uk/ibl/v1/groups/%s/episodes' % pid,
+            pid, query={
+                'page': page,
+                'per_page': per_page,
+            })['group_episodes']
+
+    @staticmethod
+    def _get_playlist_data(data):
+        return data['group']
+
+    def _get_playlist_title(self, data):
+        return data.get('title')
 
 
 class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):

youtube_dl/extractor/bfmtv.py

@@ -0,0 +1,103 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import extract_attributes
+
+
+class BFMTVBaseIE(InfoExtractor):
+    _VALID_URL_BASE = r'https?://(?:www\.)?bfmtv\.com/'
+    _VALID_URL_TMPL = _VALID_URL_BASE + r'(?:[^/]+/)*[^/?&#]+_%s[A-Z]-(?P<id>\d{12})\.html'
+    _VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block"[^>]*>)'
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
+
+    def _brightcove_url_result(self, video_id, video_block):
+        account_id = video_block.get('accountid') or '876450612001'
+        player_id = video_block.get('playerid') or 'I2qBTln4u'
+        return self.url_result(
+            self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
+            'BrightcoveNew', video_id)
+
+
+class BFMTVIE(BFMTVBaseIE):
+    IE_NAME = 'bfmtv'
+    _VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'V'
+    _TESTS = [{
+        'url': 'https://www.bfmtv.com/politique/emmanuel-macron-l-islam-est-une-religion-qui-vit-une-crise-aujourd-hui-partout-dans-le-monde_VN-202010020146.html',
+        'info_dict': {
+            'id': '6196747868001',
+            'ext': 'mp4',
+            'title': 'Emmanuel Macron: "L\'Islam est une religion qui vit une crise aujourd’hui, partout dans le monde"',
+            'description': 'Le Président s\'exprime sur la question du séparatisme depuis les Mureaux, dans les Yvelines.',
+            'uploader_id': '876450610001',
+            'upload_date': '20201002',
+            'timestamp': 1601629620,
+        },
+    }]
+
+    def _real_extract(self, url):
+        bfmtv_id = self._match_id(url)
+        webpage = self._download_webpage(url, bfmtv_id)
+        video_block = extract_attributes(self._search_regex(
+            self._VIDEO_BLOCK_REGEX, webpage, 'video block'))
+        return self._brightcove_url_result(video_block['videoid'], video_block)
+
+
+class BFMTVLiveIE(BFMTVIE):
+    IE_NAME = 'bfmtv:live'
+    _VALID_URL = BFMTVBaseIE._VALID_URL_BASE + '(?P<id>(?:[^/]+/)?en-direct)'
+    _TESTS = [{
+        'url': 'https://www.bfmtv.com/en-direct/',
+        'info_dict': {
+            'id': '5615950982001',
+            'ext': 'mp4',
+            'title': r're:^le direct BFMTV WEB \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'uploader_id': '876450610001',
+            'upload_date': '20171018',
+            'timestamp': 1508329950,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.bfmtv.com/economie/en-direct/',
+        'only_matching': True,
+    }]
+
+
+class BFMTVArticleIE(BFMTVBaseIE):
+    IE_NAME = 'bfmtv:article'
+    _VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'A'
+    _TESTS = [{
+        'url': 'https://www.bfmtv.com/sante/covid-19-un-responsable-de-l-institut-pasteur-se-demande-quand-la-france-va-se-reconfiner_AV-202101060198.html',
+        'info_dict': {
+            'id': '202101060198',
+            'title': 'Covid-19: un responsable de l\'Institut Pasteur se demande "quand la France va se reconfiner"',
+            'description': 'md5:947974089c303d3ac6196670ae262843',
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'https://www.bfmtv.com/international/pour-bolsonaro-le-bresil-est-en-faillite-mais-il-ne-peut-rien-faire_AD-202101060232.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.bfmtv.com/sante/covid-19-oui-le-vaccin-de-pfizer-distribue-en-france-a-bien-ete-teste-sur-des-personnes-agees_AN-202101060275.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        bfmtv_id = self._match_id(url)
+        webpage = self._download_webpage(url, bfmtv_id)
+
+        entries = []
+        for video_block_el in re.findall(self._VIDEO_BLOCK_REGEX, webpage):
+            video_block = extract_attributes(video_block_el)
+            video_id = video_block.get('videoid')
+            if not video_id:
+                continue
+            entries.append(self._brightcove_url_result(video_id, video_block))
+
+        return self.playlist_result(
+            entries, bfmtv_id, self._og_search_title(webpage, fatal=False),
+            self._html_search_meta(['og:description', 'description'], webpage))

youtube_dl/extractor/bibeltv.py

@@ -0,0 +1,30 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class BibelTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bibeltv\.de/mediathek/videos/(?:crn/)?(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.bibeltv.de/mediathek/videos/329703-sprachkurs-in-malaiisch',
+        'md5': '252f908192d611de038b8504b08bf97f',
+        'info_dict': {
+            'id': 'ref:329703',
+            'ext': 'mp4',
+            'title': 'Sprachkurs in Malaiisch',
+            'description': 'md5:3e9f197d29ee164714e67351cf737dfe',
+            'timestamp': 1608316701,
+            'uploader_id': '5840105145001',
+            'upload_date': '20201218',
+        }
+    }, {
+        'url': 'https://www.bibeltv.de/mediathek/videos/crn/326374',
+        'only_matching': True,
+    }]
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5840105145001/default_default/index.html?videoId=ref:%s'
+
+    def _real_extract(self, url):
+        crn_id = self._match_id(url)
+        return self.url_result(
+            self.BRIGHTCOVE_URL_TEMPLATE % crn_id, 'BrightcoveNew')

youtube_dl/extractor/bigo.py

@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError, urlencode_postdata
+
+
+class BigoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bigo\.tv/(?:[a-z]{2,}/)?(?P<id>[^/]+)'
+
+    _TESTS = [{
+        'url': 'https://www.bigo.tv/ja/221338632',
+        'info_dict': {
+            'id': '6576287577575737440',
+            'title': '土よ〜💁‍♂️ 休憩室/REST room',
+            'thumbnail': r're:https?://.+',
+            'uploader': '✨Shin💫',
+            'uploader_id': '221338632',
+            'is_live': True,
+        },
+        'skip': 'livestream',
+    }, {
+        'url': 'https://www.bigo.tv/th/Tarlerm1304',
+        'only_matching': True,
+    }, {
+        'url': 'https://bigo.tv/115976881',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+
+        info_raw = self._download_json(
+            'https://bigo.tv/studio/getInternalStudioInfo',
+            user_id, data=urlencode_postdata({'siteId': user_id}))
+
+        if not isinstance(info_raw, dict):
+            raise ExtractorError('Received invalid JSON data')
+        if info_raw.get('code'):
+            raise ExtractorError(
+                'Bigo says: %s (code %s)' % (info_raw.get('msg'), info_raw.get('code')), expected=True)
+        info = info_raw.get('data') or {}
+
+        if not info.get('alive'):
+            raise ExtractorError('This user is offline.', expected=True)
+
+        return {
+            'id': info.get('roomId') or user_id,
+            'title': info.get('roomTopic') or info.get('nick_name') or user_id,
+            'formats': [{
+                'url': info.get('hls_src'),
+                'ext': 'mp4',
+                'protocol': 'm3u8',
+            }],
+            'thumbnail': info.get('snapshot'),
+            'uploader': info.get('nick_name'),
+            'uploader_id': user_id,
+            'is_live': True,
+        }

youtube_dl/extractor/bilibili.py

@@ -156,6 +156,7 @@ class BiliBiliIE(InfoExtractor):
             cid = js['result']['cid']
 
         headers = {
+            'Accept': 'application/json',
             'Referer': url
         }
         headers.update(self.geo_verification_headers())
@@ -232,7 +233,7 @@ class BiliBiliIE(InfoExtractor):
             webpage)
         if uploader_mobj:
             info.update({
-                'uploader': uploader_mobj.group('name'),
+                'uploader': uploader_mobj.group('name').strip(),
                 'uploader_id': uploader_mobj.group('id'),
             })
         if not info.get('uploader'):
@@ -368,6 +369,11 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
             'filesize': int_or_none(play_data.get('size')),
         }]
 
+        for a_format in formats:
+            a_format.setdefault('http_headers', {}).update({
+                'Referer': url,
+            })
+
         song = self._call_api('song/info', au_id)
         title = song['title']
         statistic = song.get('statistic') or {}

youtube_dl/extractor/bleacherreport.py

@@ -90,13 +90,19 @@ class BleacherReportCMSIE(AMPIE):
     _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36}|\d{5})'
     _TESTS = [{
         'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms',
-        'md5': '2e4b0a997f9228ffa31fada5c53d1ed1',
+        'md5': '670b2d73f48549da032861130488c681',
         'info_dict': {
             'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
             'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
+            'upload_date': '20150723',
+            'timestamp': 1437679032,
+
         },
+        'expected_warnings': [
+            'Unable to download f4m manifest'
+        ]
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/blinkx.py

@@ -1,86 +0,0 @@
-from __future__ import unicode_literals
-
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    remove_start,
-    int_or_none,
-)
-
-
-class BlinkxIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
-    IE_NAME = 'blinkx'
-
-    _TEST = {
-        'url': 'http://www.blinkx.com/ce/Da0Gw3xc5ucpNduzLuDDlv4WC9PuI4fDi1-t6Y3LyfdY2SZS5Urbvn-UPJvrvbo8LTKTc67Wu2rPKSQDJyZeeORCR8bYkhs8lI7eqddznH2ofh5WEEdjYXnoRtj7ByQwt7atMErmXIeYKPsSDuMAAqJDlQZ-3Ff4HJVeH_s3Gh8oQ',
-        'md5': '337cf7a344663ec79bf93a526a2e06c7',
-        'info_dict': {
-            'id': 'Da0Gw3xc',
-            'ext': 'mp4',
-            'title': 'No Daily Show for John Oliver; HBO Show Renewed - IGN News',
-            'uploader': 'IGN News',
-            'upload_date': '20150217',
-            'timestamp': 1424215740,
-            'description': 'HBO has renewed Last Week Tonight With John Oliver for two more seasons.',
-            'duration': 47.743333,
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        display_id = video_id[:8]
-
-        api_url = ('https://apib4.blinkx.com/api.php?action=play_video&'
-                   + 'video=%s' % video_id)
-        data_json = self._download_webpage(api_url, display_id)
-        data = json.loads(data_json)['api']['results'][0]
-        duration = None
-        thumbnails = []
-        formats = []
-        for m in data['media']:
-            if m['type'] == 'jpg':
-                thumbnails.append({
-                    'url': m['link'],
-                    'width': int(m['w']),
-                    'height': int(m['h']),
-                })
-            elif m['type'] == 'original':
-                duration = float(m['d'])
-            elif m['type'] == 'youtube':
-                yt_id = m['link']
-                self.to_screen('Youtube video detected: %s' % yt_id)
-                return self.url_result(yt_id, 'Youtube', video_id=yt_id)
-            elif m['type'] in ('flv', 'mp4'):
-                vcodec = remove_start(m['vcodec'], 'ff')
-                acodec = remove_start(m['acodec'], 'ff')
-                vbr = int_or_none(m.get('vbr') or m.get('vbitrate'), 1000)
-                abr = int_or_none(m.get('abr') or m.get('abitrate'), 1000)
-                tbr = vbr + abr if vbr and abr else None
-                format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
-                formats.append({
-                    'format_id': format_id,
-                    'url': m['link'],
-                    'vcodec': vcodec,
-                    'acodec': acodec,
-                    'abr': abr,
-                    'vbr': vbr,
-                    'tbr': tbr,
-                    'width': int_or_none(m.get('w')),
-                    'height': int_or_none(m.get('h')),
-                })
-
-        self._sort_formats(formats)
-
-        return {
-            'id': display_id,
-            'fullid': video_id,
-            'title': data['title'],
-            'formats': formats,
-            'uploader': data['channel_name'],
-            'timestamp': data['pubdate_epoch'],
-            'description': data.get('description'),
-            'thumbnails': thumbnails,
-            'duration': duration,
-        }

youtube_dl/extractor/bongacams.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -12,13 +13,28 @@ from ..utils import (
 
 
 class BongaCamsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.com)/(?P<id>[^/?&#]+)'
+    _VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.(?:com|net))/(?P<id>[^/?&#]+)'
     _TESTS = [{
         'url': 'https://de.bongacams.com/azumi-8',
         'only_matching': True,
     }, {
         'url': 'https://cn.bongacams.com/azumi-8',
         'only_matching': True,
+    }, {
+        'url': 'https://de.bongacams.net/claireashton',
+        'info_dict': {
+            'id': 'claireashton',
+            'ext': 'mp4',
+            'title': r're:ClaireAshton \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'age_limit': 18,
+            'uploader_id': 'ClaireAshton',
+            'uploader': 'ClaireAshton',
+            'like_count': int,
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/bravotv.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class BravoTVIE(AdobePassIE):
-    _VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<req_id>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
         'md5': 'e34684cfea2a96cd2ee1ef3a60909de9',
@@ -28,10 +28,13 @@ class BravoTVIE(AdobePassIE):
     }, {
         'url': 'http://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
         'only_matching': True,
+    }, {
+        'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        site, display_id = re.match(self._VALID_URL, url).groups()
         webpage = self._download_webpage(url, display_id)
         settings = self._parse_json(self._search_regex(
             r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>({.+?})</script>', webpage, 'drupal settings'),
@@ -53,11 +56,14 @@ class BravoTVIE(AdobePassIE):
                 tp_path = release_pid = tve['release_pid']
             if tve.get('entitlement') == 'auth':
                 adobe_pass = settings.get('tve_adobe_auth', {})
+                if site == 'bravotv':
+                    site = 'bravo'
                 resource = self._get_mvpd_resource(
-                    adobe_pass.get('adobePassResourceId', 'bravo'),
+                    adobe_pass.get('adobePassResourceId') or site,
                     tve['title'], release_pid, tve.get('rating'))
                 query['auth'] = self._extract_mvpd_auth(
-                    url, release_pid, adobe_pass.get('adobePassRequestorId', 'bravo'), resource)
+                    url, release_pid,
+                    adobe_pass.get('adobePassRequestorId') or site, resource)
         else:
             shared_playlist = settings['ls_playlist']
             account_pid = shared_playlist['account_pid']

youtube_dl/extractor/canvas.py

@@ -8,18 +8,20 @@ from .gigya import GigyaBaseIE
 from ..compat import compat_HTTPError
 from ..utils import (
     ExtractorError,
-    strip_or_none,
+    clean_html,
+    extract_attributes,
     float_or_none,
+    get_element_by_class,
     int_or_none,
     merge_dicts,
-    parse_iso8601,
     str_or_none,
+    strip_or_none,
     url_or_none,
 )
 
 
 class CanvasIE(InfoExtractor):
-    _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza|dako)/assets/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
         'md5': '68993eda72ef62386a15ea2cf3c93107',
@@ -37,6 +39,7 @@ class CanvasIE(InfoExtractor):
         'url': 'https://mediazone.vrt.be/api/v1/canvas/assets/mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
         'only_matching': True,
     }]
+    _GEO_BYPASS = False
     _HLS_ENTRY_PROTOCOLS_MAP = {
         'HLS': 'm3u8_native',
         'HLS_AES': 'm3u8',
@@ -47,6 +50,8 @@ class CanvasIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         site_id, video_id = mobj.group('site_id'), mobj.group('id')
 
+        data = None
+        if site_id != 'vrtvideo':
             # Old API endpoint, serves more formats but may fail for some videos
             data = self._download_json(
                 'https://mediazone.vrt.be/api/v1/%s/assets/%s'
@@ -55,21 +60,24 @@ class CanvasIE(InfoExtractor):
 
         # New API endpoint
         if not data:
+            headers = self.geo_verification_headers()
+            headers.update({'Content-Type': 'application/json'})
             token = self._download_json(
                 '%s/tokens' % self._REST_API_BASE, video_id,
-                'Downloading token', data=b'',
-                headers={'Content-Type': 'application/json'})['vrtPlayerToken']
+                'Downloading token', data=b'', headers=headers)['vrtPlayerToken']
             data = self._download_json(
                 '%s/videos/%s' % (self._REST_API_BASE, video_id),
-                video_id, 'Downloading video JSON', fatal=False, query={
+                video_id, 'Downloading video JSON', query={
                     'vrtPlayerToken': token,
                     'client': '%s@PROD' % site_id,
                 }, expected_status=400)
-            message = data.get('message')
-            if message and not data.get('title'):
-                if data.get('code') == 'AUTHENTICATION_REQUIRED':
-                    self.raise_login_required(message)
-                raise ExtractorError(message, expected=True)
+            if not data.get('title'):
+                code = data.get('code')
+                if code == 'AUTHENTICATION_REQUIRED':
+                    self.raise_login_required()
+                elif code == 'INVALID_LOCATION':
+                    self.raise_geo_restricted(countries=['BE'])
+                raise ExtractorError(data.get('message') or code, expected=True)
 
         title = data['title']
         description = data.get('description')
@@ -205,20 +213,24 @@ class CanvasEenIE(InfoExtractor):
 
 class VrtNUIE(GigyaBaseIE):
     IE_DESC = 'VrtNU.be'
-    _VALID_URL = r'https?://(?:www\.)?vrt\.be/(?P<site_id>vrtnu)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?vrt\.be/vrtnu/a-z/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
     _TESTS = [{
         # Available via old API endpoint
-        'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1/postbus-x-s1a1/',
+        'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1989/postbus-x-s1989a1/',
         'info_dict': {
-            'id': 'pbs-pub-2e2d8c27-df26-45c9-9dc6-90c78153044d$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
+            'id': 'pbs-pub-e8713dac-899e-41de-9313-81269f4c04ac$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
             'ext': 'mp4',
-            'title': 'De zwarte weduwe',
-            'description': 'md5:db1227b0f318c849ba5eab1fef895ee4',
+            'title': 'Postbus X - Aflevering 1 (Seizoen 1989)',
+            'description': 'md5:b704f669eb9262da4c55b33d7c6ed4b7',
             'duration': 1457.04,
             'thumbnail': r're:^https?://.*\.jpg$',
-            'season': 'Season 1',
-            'season_number': 1,
+            'series': 'Postbus X',
+            'season': 'Seizoen 1989',
+            'season_number': 1989,
+            'episode': 'De zwarte weduwe',
             'episode_number': 1,
+            'timestamp': 1595822400,
+            'upload_date': '20200727',
         },
         'skip': 'This video is only available for registered users',
         'params': {
@@ -300,69 +312,73 @@ class VrtNUIE(GigyaBaseIE):
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
-        webpage, urlh = self._download_webpage_handle(url, display_id)
+        webpage = self._download_webpage(url, display_id)
+
+        attrs = extract_attributes(self._search_regex(
+            r'(<nui-media[^>]+>)', webpage, 'media element'))
+        video_id = attrs['videoid']
+        publication_id = attrs.get('publicationid')
+        if publication_id:
+            video_id = publication_id + '$' + video_id
+
+        page = (self._parse_json(self._search_regex(
+            r'digitalData\s*=\s*({.+?});', webpage, 'digial data',
+            default='{}'), video_id, fatal=False) or {}).get('page') or {}
 
         info = self._search_json_ld(webpage, display_id, default={})
-
-        # title is optional here since it may be extracted by extractor
-        # that is delegated from here
-        title = strip_or_none(self._html_search_regex(
-            r'(?ms)<h1 class="content__heading">(.+?)</h1>',
-            webpage, 'title', default=None))
-
-        description = self._html_search_regex(
-            r'(?ms)<div class="content__description">(.+?)</div>',
-            webpage, 'description', default=None)
-
-        season = self._html_search_regex(
-            [r'''(?xms)<div\ class="tabs__tab\ tabs__tab--active">\s*
-                    <span>seizoen\ (.+?)</span>\s*
-                </div>''',
-             r'<option value="seizoen (\d{1,3})" data-href="[^"]+?" selected>'],
-            webpage, 'season', default=None)
-
-        season_number = int_or_none(season)
-
-        episode_number = int_or_none(self._html_search_regex(
-            r'''(?xms)<div\ class="content__episode">\s*
-                    <abbr\ title="aflevering">afl</abbr>\s*<span>(\d+)</span>
-                </div>''',
-            webpage, 'episode_number', default=None))
-
-        release_date = parse_iso8601(self._html_search_regex(
-            r'(?ms)<div class="content__broadcastdate">\s*<time\ datetime="(.+?)"',
-            webpage, 'release_date', default=None))
-
-        # If there's a ? or a # in the URL, remove them and everything after
-        clean_url = urlh.geturl().split('?')[0].split('#')[0].strip('/')
-        securevideo_url = clean_url + '.mssecurevideo.json'
-
-        try:
-            video = self._download_json(securevideo_url, display_id)
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
-                self.raise_login_required()
-            raise
-
-        # We are dealing with a '../<show>.relevant' URL
-        redirect_url = video.get('url')
-        if redirect_url:
-            return self.url_result(self._proto_relative_url(redirect_url, 'https:'))
-
-        # There is only one entry, but with an unknown key, so just get
-        # the first one
-        video_id = list(video.values())[0].get('videoid')
-
         return merge_dicts(info, {
             '_type': 'url_transparent',
             'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id,
             'ie_key': CanvasIE.ie_key(),
             'id': video_id,
             'display_id': display_id,
+            'season_number': int_or_none(page.get('episode_season')),
+        })
+
+
+class DagelijkseKostIE(InfoExtractor):
+    IE_DESC = 'dagelijksekost.een.be'
+    _VALID_URL = r'https?://dagelijksekost\.een\.be/gerechten/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://dagelijksekost.een.be/gerechten/hachis-parmentier-met-witloof',
+        'md5': '30bfffc323009a3e5f689bef6efa2365',
+        'info_dict': {
+            'id': 'md-ast-27a4d1ff-7d7b-425e-b84f-a4d227f592fa',
+            'display_id': 'hachis-parmentier-met-witloof',
+            'ext': 'mp4',
+            'title': 'Hachis parmentier met witloof',
+            'description': 'md5:9960478392d87f63567b5b117688cdc5',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 283.02,
+        },
+        'expected_warnings': ['is not a supported codec'],
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        title = strip_or_none(get_element_by_class(
+            'dish-metadata__title', webpage
+        ) or self._html_search_meta(
+            'twitter:title', webpage))
+
+        description = clean_html(get_element_by_class(
+            'dish-description', webpage)
+        ) or self._html_search_meta(
+            ('description', 'twitter:description', 'og:description'),
+            webpage)
+
+        video_id = self._html_search_regex(
+            r'data-url=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id',
+            group='id')
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'https://mediazone.vrt.be/api/v1/dako/assets/%s' % video_id,
+            'ie_key': CanvasIE.ie_key(),
+            'id': video_id,
+            'display_id': display_id,
             'title': title,
             'description': description,
-            'season': season,
-            'season_number': season_number,
-            'episode_number': episode_number,
-            'release_date': release_date,
-        })
+        }

youtube_dl/extractor/cbs.py

@@ -27,7 +27,7 @@ class CBSBaseIE(ThePlatformFeedIE):
 
 
 class CBSIE(CBSBaseIE):
-    _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
+    _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:(?:cbs|paramountplus)\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
 
     _TESTS = [{
         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
@@ -52,6 +52,9 @@ class CBSIE(CBSBaseIE):
     }, {
         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.paramountplus.com/shows/all-rise/video/QmR1WhNkh1a_IrdHZrbcRklm176X_rVc/all-rise-space/',
+        'only_matching': True,
     }]
 
     def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):

youtube_dl/extractor/cbsnews.py

@@ -26,7 +26,7 @@ class CBSNewsEmbedIE(CBSIE):
     def _real_extract(self, url):
         item = self._parse_json(zlib.decompress(compat_b64decode(
             compat_urllib_parse_unquote(self._match_id(url))),
-            -zlib.MAX_WBITS), None)['video']['items'][0]
+            -zlib.MAX_WBITS).decode('utf-8'), None)['video']['items'][0]
         return self._extract_video_info(item['mpxRefId'], 'cbsnews')
 
 

youtube_dl/extractor/cbssports.py

@@ -1,38 +1,113 @@
 from __future__ import unicode_literals
 
-from .cbs import CBSBaseIE
+import re
+
+# from .cbs import CBSBaseIE
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    try_get,
+)
 
 
-class CBSSportsIE(CBSBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/(?:video|news)/(?P<id>[^/?#&]+)'
-
+# class CBSSportsEmbedIE(CBSBaseIE):
+class CBSSportsEmbedIE(InfoExtractor):
+    IE_NAME = 'cbssports:embed'
+    _VALID_URL = r'''(?ix)https?://(?:(?:www\.)?cbs|embed\.247)sports\.com/player/embed.+?
+        (?:
+            ids%3D(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})|
+            pcid%3D(?P<pcid>\d+)
+        )'''
     _TESTS = [{
-        'url': 'https://www.cbssports.com/nba/video/donovan-mitchell-flashes-star-potential-in-game-2-victory-over-thunder/',
-        'info_dict': {
-            'id': '1214315075735',
-            'ext': 'mp4',
-            'title': 'Donovan Mitchell flashes star potential in Game 2 victory over Thunder',
-            'description': 'md5:df6f48622612c2d6bd2e295ddef58def',
-            'timestamp': 1524111457,
-            'upload_date': '20180419',
-            'uploader': 'CBSI-NEW',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        }
+        'url': 'https://www.cbssports.com/player/embed/?args=player_id%3Db56c03a6-231a-4bbe-9c55-af3c8a8e9636%26ids%3Db56c03a6-231a-4bbe-9c55-af3c8a8e9636%26resizable%3D1%26autoplay%3Dtrue%26domain%3Dcbssports.com%26comp_ads_enabled%3Dfalse%26watchAndRead%3D0%26startTime%3D0%26env%3Dprod',
+        'only_matching': True,
     }, {
-        'url': 'https://www.cbssports.com/nba/news/nba-playoffs-2018-watch-76ers-vs-heat-game-3-series-schedule-tv-channel-online-stream/',
+        'url': 'https://embed.247sports.com/player/embed/?args=%3fplayer_id%3d1827823171591%26channel%3dcollege-football-recruiting%26pcid%3d1827823171591%26width%3d640%26height%3d360%26autoplay%3dTrue%26comp_ads_enabled%3dFalse%26uvpc%3dhttps%253a%252f%252fwww.cbssports.com%252fapi%252fcontent%252fvideo%252fconfig%252f%253fcfg%253duvp_247sports_v4%2526partner%253d247%26uvpc_m%3dhttps%253a%252f%252fwww.cbssports.com%252fapi%252fcontent%252fvideo%252fconfig%252f%253fcfg%253duvp_247sports_m_v4%2526partner_m%253d247_mobile%26utag%3d247sportssite%26resizable%3dTrue',
         'only_matching': True,
     }]
 
-    def _extract_video_info(self, filter_query, video_id):
-        return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
+    # def _extract_video_info(self, filter_query, video_id):
+    #     return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
 
+    def _real_extract(self, url):
+        uuid, pcid = re.match(self._VALID_URL, url).groups()
+        query = {'id': uuid} if uuid else {'pcid': pcid}
+        video = self._download_json(
+            'https://www.cbssports.com/api/content/video/',
+            uuid or pcid, query=query)[0]
+        video_id = video['id']
+        title = video['title']
+        metadata = video.get('metaData') or {}
+        # return self._extract_video_info('byId=%d' % metadata['mpxOutletId'], video_id)
+        # return self._extract_video_info('byGuid=' + metadata['mpxRefId'], video_id)
+
+        formats = self._extract_m3u8_formats(
+            metadata['files'][0]['url'], video_id, 'mp4',
+            'm3u8_native', m3u8_id='hls', fatal=False)
+        self._sort_formats(formats)
+
+        image = video.get('image')
+        thumbnails = None
+        if image:
+            image_path = image.get('path')
+            if image_path:
+                thumbnails = [{
+                    'url': image_path,
+                    'width': int_or_none(image.get('width')),
+                    'height': int_or_none(image.get('height')),
+                    'filesize': int_or_none(image.get('size')),
+                }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': video.get('description'),
+            'timestamp': int_or_none(try_get(video, lambda x: x['dateCreated']['epoch'])),
+            'duration': int_or_none(metadata.get('duration')),
+        }
+
+
+class CBSSportsBaseIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        video_id = self._search_regex(
-            [r'(?:=|%26)pcid%3D(\d+)', r'embedVideo(?:Container)?_(\d+)'],
-            webpage, 'video id')
-        return self._extract_video_info('byId=%s' % video_id, video_id)
+        iframe_url = self._search_regex(
+            r'<iframe[^>]+(?:data-)?src="(https?://[^/]+/player/embed[^"]+)"',
+            webpage, 'embed url')
+        return self.url_result(iframe_url, CBSSportsEmbedIE.ie_key())
+
+
+class CBSSportsIE(CBSSportsBaseIE):
+    IE_NAME = 'cbssports'
+    _VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/video/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.cbssports.com/college-football/video/cover-3-stanford-spring-gleaning/',
+        'info_dict': {
+            'id': 'b56c03a6-231a-4bbe-9c55-af3c8a8e9636',
+            'ext': 'mp4',
+            'title': 'Cover 3: Stanford Spring Gleaning',
+            'description': 'The Cover 3 crew break down everything you need to know about the Stanford Cardinal this spring.',
+            'timestamp': 1617218398,
+            'upload_date': '20210331',
+            'duration': 502,
+        },
+    }]
+
+
+class TwentyFourSevenSportsIE(CBSSportsBaseIE):
+    IE_NAME = '247sports'
+    _VALID_URL = r'https?://(?:www\.)?247sports\.com/Video/(?:[^/?#&]+-)?(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://247sports.com/Video/2021-QB-Jake-Garcia-senior-highlights-through-five-games-10084854/',
+        'info_dict': {
+            'id': '4f1265cb-c3b5-44a8-bb1d-1914119a0ccc',
+            'ext': 'mp4',
+            'title': '2021 QB Jake Garcia senior highlights through five games',
+            'description': 'md5:8cb67ebed48e2e6adac1701e0ff6e45b',
+            'timestamp': 1607114223,
+            'upload_date': '20201204',
+            'duration': 208,
+        },
+    }]

youtube_dl/extractor/ccma.py

@@ -1,15 +1,18 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import calendar
+import datetime
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
+    extract_timezone,
     int_or_none,
     parse_duration,
-    parse_iso8601,
     parse_resolution,
+    try_get,
     url_or_none,
 )
 
@@ -24,8 +27,9 @@ class CCMAIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'L\'espot de La Marató de TV3',
             'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
-            'timestamp': 1470918540,
-            'upload_date': '20160811',
+            'timestamp': 1478608140,
+            'upload_date': '20161108',
+            'age_limit': 0,
         }
     }, {
         'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
@@ -35,8 +39,24 @@ class CCMAIE(InfoExtractor):
             'ext': 'mp3',
             'title': 'El Consell de Savis analitza el derbi',
             'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
-            'upload_date': '20171205',
-            'timestamp': 1512507300,
+            'upload_date': '20170512',
+            'timestamp': 1494622500,
+            'vcodec': 'none',
+            'categories': ['Esports'],
+        }
+    }, {
+        'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/',
+        'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
+        'info_dict': {
+            'id': '6031387',
+            'ext': 'mp4',
+            'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)',
+            'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60',
+            'timestamp': 1582577700,
+            'upload_date': '20200224',
+            'subtitles': 'mincount:4',
+            'age_limit': 16,
+            'series': 'Crims',
         }
     }]
 
@@ -72,17 +92,28 @@ class CCMAIE(InfoExtractor):
 
         informacio = media['informacio']
         title = informacio['titol']
-        durada = informacio.get('durada', {})
+        durada = informacio.get('durada') or {}
         duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
-        timestamp = parse_iso8601(informacio.get('data_emissio', {}).get('utc'))
+        tematica = try_get(informacio, lambda x: x['tematica']['text'])
+
+        timestamp = None
+        data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
+        try:
+            timezone, data_utc = extract_timezone(data_utc)
+            timestamp = calendar.timegm((datetime.datetime.strptime(
+                data_utc, '%Y-%d-%mT%H:%M:%S') - timezone).timetuple())
+        except TypeError:
+            pass
 
         subtitles = {}
-        subtitols = media.get('subtitols', {})
-        if subtitols:
-            sub_url = subtitols.get('url')
+        subtitols = media.get('subtitols') or []
+        if isinstance(subtitols, dict):
+            subtitols = [subtitols]
+        for st in subtitols:
+            sub_url = st.get('url')
             if sub_url:
                 subtitles.setdefault(
-                    subtitols.get('iso') or subtitols.get('text') or 'ca', []).append({
+                    st.get('iso') or st.get('text') or 'ca', []).append({
                         'url': sub_url,
                     })
 
@@ -97,6 +128,16 @@ class CCMAIE(InfoExtractor):
                     'height': int_or_none(imatges.get('alcada')),
                 }]
 
+        age_limit = None
+        codi_etic = try_get(informacio, lambda x: x['codi_etic']['id'])
+        if codi_etic:
+            codi_etic_s = codi_etic.split('_')
+            if len(codi_etic_s) == 2:
+                if codi_etic_s[1] == 'TP':
+                    age_limit = 0
+                else:
+                    age_limit = int_or_none(codi_etic_s[1])
+
         return {
             'id': media_id,
             'title': title,
@@ -106,4 +147,9 @@ class CCMAIE(InfoExtractor):
             'thumbnails': thumbnails,
             'subtitles': subtitles,
             'formats': formats,
+            'age_limit': age_limit,
+            'alt_title': informacio.get('titol_complet'),
+            'episode_number': int_or_none(informacio.get('capitol')),
+            'categories': [tematica] if tematica else None,
+            'series': informacio.get('programa'),
         }

youtube_dl/extractor/cda.py

@@ -95,8 +95,11 @@ class CDAIE(InfoExtractor):
         if 'Ten film jest dostępny dla użytkowników premium' in webpage:
             raise ExtractorError('This video is only available for premium users.', expected=True)
 
+        if re.search(r'niedostępn[ey] w(?:&nbsp;|\s+)Twoim kraju\s*<', webpage):
+            self.raise_geo_restricted()
+
         need_confirm_age = False
-        if self._html_search_regex(r'(<form[^>]+action="/a/validatebirth")',
+        if self._html_search_regex(r'(<form[^>]+action="[^"]*/a/validatebirth[^"]*")',
                                    webpage, 'birthday validate form', default=None):
             webpage = self._download_age_confirm_page(
                 url, video_id, note='Confirming age')
@@ -130,6 +133,8 @@ class CDAIE(InfoExtractor):
             'age_limit': 18 if need_confirm_age else 0,
         }
 
+        info = self._search_json_ld(webpage, video_id, default={})
+
         # Source: https://www.cda.pl/js/player.js?t=1606154898
         def decrypt_file(a):
             for p in ('_XDDD', '_CDA', '_ADC', '_CXD', '_QWE', '_Q5', '_IKSDE'):
@@ -194,7 +199,7 @@ class CDAIE(InfoExtractor):
                 handler = self._download_webpage
 
             webpage = handler(
-                self._BASE_URL + href, video_id,
+                urljoin(self._BASE_URL, href), video_id,
                 'Downloading %s version information' % resolution, fatal=False)
             if not webpage:
                 # Manually report warning because empty page is returned when
@@ -206,6 +211,4 @@ class CDAIE(InfoExtractor):
 
         self._sort_formats(formats)
 
-        info = self._search_json_ld(webpage, video_id, default={})
-
         return merge_dicts(info_dict, info)

youtube_dl/extractor/ceskatelevize.py

@@ -12,35 +12,21 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     sanitized_Request,
-    unescapeHTML,
-    update_url_query,
+    str_or_none,
+    traverse_obj,
     urlencode_postdata,
     USER_AGENTS,
 )
 
 
 class CeskaTelevizeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/ivysilani/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
     _TESTS = [{
-        'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
-        'info_dict': {
-            'id': '61924494877246241',
-            'ext': 'mp4',
-            'title': 'Hyde Park Civilizace: Život v Grónsku',
-            'description': 'md5:3fec8f6bb497be5cdb0c9e8781076626',
-            'thumbnail': r're:^https?://.*\.jpg',
-            'duration': 3350,
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }, {
         'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en',
         'info_dict': {
             'id': '61924494877028507',
             'ext': 'mp4',
-            'title': 'Hyde Park Civilizace: Bonus 01 - En',
+            'title': 'Bonus 01 - En - Hyde Park Civilizace',
             'description': 'English Subtittles',
             'thumbnail': r're:^https?://.*\.jpg',
             'duration': 81.3,
@@ -51,31 +37,111 @@ class CeskaTelevizeIE(InfoExtractor):
         },
     }, {
         # live stream
-        'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
+        'url': 'http://www.ceskatelevize.cz/zive/ct1/',
         'info_dict': {
-            'id': 402,
+            'id': '102',
             'ext': 'mp4',
-            'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'title': r'ČT1 - živé vysílání online',
+            'description': 'Sledujte živé vysílání kanálu ČT1 online. Vybírat si můžete i z dalších kanálů České televize na kterémkoli z vašich zařízení.',
             'is_live': True,
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
-        'skip': 'Georestricted to Czech Republic',
+    }, {
+        # another
+        'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
+        'only_matching': True,
+        'info_dict': {
+            'id': 402,
+            'ext': 'mp4',
+            'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'is_live': True,
+        },
+        # 'skip': 'Georestricted to Czech Republic',
     }, {
         'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
         'only_matching': True,
+    }, {
+        # video with 18+ caution trailer
+        'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
+        'info_dict': {
+            'id': '215562210900007-bogotart',
+            'title': 'Bogotart - Queer',
+            'description': 'Hlavní město Kolumbie v doprovodu queer umělců. Vroucí svět plný vášně, sebevědomí, ale i násilí a bolesti',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': '61924494877311053',
+                'ext': 'mp4',
+                'title': 'Bogotart - Queer (Varování 18+)',
+                'duration': 11.9,
+            },
+        }, {
+            'info_dict': {
+                'id': '61924494877068022',
+                'ext': 'mp4',
+                'title': 'Bogotart - Queer (Queer)',
+                'thumbnail': r're:^https?://.*\.jpg',
+                'duration': 1558.3,
+            },
+        }],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # iframe embed
+        'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
+        'only_matching': True,
     }]
 
+    def _search_nextjs_data(self, webpage, video_id, **kw):
+        return self._parse_json(
+            self._search_regex(
+                r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
+                webpage, 'next.js data', **kw),
+            video_id, **kw)
+
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
+        webpage, urlh = self._download_webpage_handle(url, playlist_id)
+        parsed_url = compat_urllib_parse_urlparse(urlh.geturl())
+        site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize')
+        playlist_title = self._og_search_title(webpage, default=None)
+        if site_name and playlist_title:
+            playlist_title = re.split(r'\s*[—|]\s*%s' % (site_name, ), playlist_title, 1)[0]
+        playlist_description = self._og_search_description(webpage, default=None)
+        if playlist_description:
+            playlist_description = playlist_description.replace('\xa0', ' ')
 
-        webpage = self._download_webpage(url, playlist_id)
+        type_ = 'IDEC'
+        if re.search(r'(^/porady|/zive)/', parsed_url.path):
+            next_data = self._search_nextjs_data(webpage, playlist_id)
+            if '/zive/' in parsed_url.path:
+                idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'liveBroadcast', 'current', 'idec'), get_all=False)
+            else:
+                idec = traverse_obj(next_data, ('props', 'pageProps', 'data', ('show', 'mediaMeta'), 'idec'), get_all=False)
+                if not idec:
+                    idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'videobonusDetail', 'bonusId'), get_all=False)
+                    if idec:
+                        type_ = 'bonus'
+            if not idec:
+                raise ExtractorError('Failed to find IDEC id')
+            iframe_hash = self._download_webpage(
+                'https://www.ceskatelevize.cz/v-api/iframe-hash/',
+                playlist_id, note='Getting IFRAME hash')
+            query = {'hash': iframe_hash, 'origin': 'iVysilani', 'autoStart': 'true', type_: idec, }
+            webpage = self._download_webpage(
+                'https://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php',
+                playlist_id, note='Downloading player', query=query)
 
         NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
-            raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
+            self.raise_geo_restricted(NOT_AVAILABLE_STRING)
+        if any(not_found in webpage for not_found in ('Neplatný parametr pro videopřehrávač', 'IDEC nebyl nalezen', )):
+            raise ExtractorError('no video with IDEC available', video_id=idec, expected=True)
 
         type_ = None
         episode_id = None
@@ -100,7 +166,7 @@ class CeskaTelevizeIE(InfoExtractor):
         data = {
             'playlist[0][type]': type_,
             'playlist[0][id]': episode_id,
-            'requestUrl': compat_urllib_parse_urlparse(url).path,
+            'requestUrl': parsed_url.path,
             'requestSource': 'iVysilani',
         }
 
@@ -108,7 +174,7 @@ class CeskaTelevizeIE(InfoExtractor):
 
         for user_agent in (None, USER_AGENTS['Safari']):
             req = sanitized_Request(
-                'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
+                'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/',
                 data=urlencode_postdata(data))
 
             req.add_header('Content-type', 'application/x-www-form-urlencoded')
@@ -130,9 +196,6 @@ class CeskaTelevizeIE(InfoExtractor):
             req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
             req.add_header('Referer', url)
 
-            playlist_title = self._og_search_title(webpage, default=None)
-            playlist_description = self._og_search_description(webpage, default=None)
-
             playlist = self._download_json(req, playlist_id, fatal=False)
             if not playlist:
                 continue
@@ -167,7 +230,7 @@ class CeskaTelevizeIE(InfoExtractor):
                     entries[num]['formats'].extend(formats)
                     continue
 
-                item_id = item.get('id') or item['assetId']
+                item_id = str_or_none(item.get('id') or item['assetId'])
                 title = item['title']
 
                 duration = float_or_none(item.get('duration'))
@@ -181,8 +244,6 @@ class CeskaTelevizeIE(InfoExtractor):
 
                 if playlist_len == 1:
                     final_title = playlist_title or title
-                    if is_live:
-                        final_title = self._live_title(final_title)
                 else:
                     final_title = '%s (%s)' % (playlist_title, title)
 
@@ -200,6 +261,8 @@ class CeskaTelevizeIE(InfoExtractor):
         for e in entries:
             self._sort_formats(e['formats'])
 
+        if len(entries) == 1:
+            return entries[0]
         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
 
     def _get_subtitles(self, episode_id, subs):
@@ -236,54 +299,3 @@ class CeskaTelevizeIE(InfoExtractor):
                     yield line
 
         return '\r\n'.join(_fix_subtitle(subtitles))
-
-
-class CeskaTelevizePoradyIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/porady/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
-    _TESTS = [{
-        # video with 18+ caution trailer
-        'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
-        'info_dict': {
-            'id': '215562210900007-bogotart',
-            'title': 'Queer: Bogotart',
-            'description': 'Alternativní průvodce současným queer světem',
-        },
-        'playlist': [{
-            'info_dict': {
-                'id': '61924494876844842',
-                'ext': 'mp4',
-                'title': 'Queer: Bogotart (Varování 18+)',
-                'duration': 10.2,
-            },
-        }, {
-            'info_dict': {
-                'id': '61924494877068022',
-                'ext': 'mp4',
-                'title': 'Queer: Bogotart (Queer)',
-                'thumbnail': r're:^https?://.*\.jpg',
-                'duration': 1558.3,
-            },
-        }],
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }, {
-        # iframe embed
-        'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        data_url = update_url_query(unescapeHTML(self._search_regex(
-            (r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
-             r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?ceskatelevize\.cz/ivysilani/embed/iFramePlayer\.php.*?)\1'),
-            webpage, 'iframe player url', group='url')), query={
-                'autoStart': 'true',
-        })
-
-        return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())

youtube_dl/extractor/comedycentral.py

@@ -1,142 +1,51 @@
 from __future__ import unicode_literals
 
 from .mtv import MTVServicesInfoExtractor
-from .common import InfoExtractor
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
-        (video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes)))
-        /(?P<title>.*)'''
+    _VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?)/(?P<id>[0-9a-z]{6})'
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
     _TESTS = [{
-        'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
-        'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
+        'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
+        'md5': 'b8acb347177c680ff18a292aa2166f80',
         'info_dict': {
-            'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
+            'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025',
             'ext': 'mp4',
-            'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother',
-            'description': 'After a certain point, breastfeeding becomes c**kblocking.',
-            'timestamp': 1376798400,
-            'upload_date': '20130818',
+            'title': 'The Daily Show with Trevor Noah|August 28, 2020|25|25149|Doc Rivers and Steve Ballmer - The NBA Player Strike',
+            'description': 'md5:5334307c433892b85f4f5e5ac9ef7498',
+            'timestamp': 1598670000,
+            'upload_date': '20200829',
         },
     }, {
-        'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
+        'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314',
         'only_matching': True,
-    }]
-
-
-class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
-        (?:full-episodes|shows(?=/[^/]+/full-episodes))
-        /(?P<id>[^?]+)'''
-    _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
-
-    _TESTS = [{
-        'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
-        'info_dict': {
-            'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
-            'title': 'November 28, 2016 - Ryan Speedo Green',
-        },
-        'playlist_count': 4,
     }, {
-        'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-        webpage = self._download_webpage(url, playlist_id)
-        mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1')
-        videos_info = self._get_videos_info(mgid)
-        return videos_info
-
-
-class ToshIE(MTVServicesInfoExtractor):
-    IE_DESC = 'Tosh.0'
-    _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
-    _FEED_URL = 'http://tosh.cc.com/feeds/mrss'
-
-    _TESTS = [{
-        'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
-        'info_dict': {
-            'description': 'Tosh asked fans to share their summer plans.',
-            'title': 'Twitter Users Share Summer Plans',
-        },
-        'playlist': [{
-            'md5': 'f269e88114c1805bb6d7653fecea9e06',
-            'info_dict': {
-                'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
-                'ext': 'mp4',
-                'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
-                'description': 'Tosh asked fans to share their summer plans.',
-                'thumbnail': r're:^https?://.*\.jpg',
-                # It's really reported to be published on year 2077
-                'upload_date': '20770610',
-                'timestamp': 3390510600,
-                'subtitles': {
-                    'en': 'mincount:3',
-                },
-            },
-        }]
-    }, {
-        'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
+        'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
         'only_matching': True,
     }]
 
 
 class ComedyCentralTVIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/folgen/(?P<id>[0-9a-z]{6})'
     _TESTS = [{
-        'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
+        'url': 'https://www.comedycentral.tv/folgen/pxdpec/josh-investigates-klimawandel-staffel-1-ep-1',
         'info_dict': {
-            'id': 'local_playlist-f99b626bdfe13568579a',
-            'ext': 'flv',
-            'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
+            'id': '15907dc3-ec3c-11e8-a442-0e40cf2fc285',
+            'ext': 'mp4',
+            'title': 'Josh Investigates',
+            'description': 'Steht uns das Ende der Welt bevor?',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
-        'only_matching': True,
     }]
+    _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
+    _GEO_COUNTRIES = ['DE']
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        mrss_url = self._search_regex(
-            r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
-            webpage, 'mrss url', group='url')
-
-        return self._get_videos_info_from_url(mrss_url, video_id)
-
-
-class ComedyCentralShortnameIE(InfoExtractor):
-    _VALID_URL = r'^:(?P<id>tds|thedailyshow|theopposition)$'
-    _TESTS = [{
-        'url': ':tds',
-        'only_matching': True,
-    }, {
-        'url': ':thedailyshow',
-        'only_matching': True,
-    }, {
-        'url': ':theopposition',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        shortcut_map = {
-            'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
-            'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
-            'theopposition': 'http://www.cc.com/shows/the-opposition-with-jordan-klepper/full-episodes',
+    def _get_feed_query(self, uri):
+        return {
+            'accountOverride': 'intl.mtvi.com',
+            'arcEp': 'web.cc.tv',
+            'ep': 'b9032c3a',
+            'imageEp': 'web.cc.tv',
+            'mgid': uri,
         }
-        return self.url_result(shortcut_map[video_id])

youtube_dl/extractor/common.py

@@ -17,7 +17,7 @@ import math
 
 from ..compat import (
     compat_cookiejar_Cookie,
-    compat_cookies,
+    compat_cookies_SimpleCookie,
     compat_etree_Element,
     compat_etree_fromstring,
     compat_getpass,
@@ -70,6 +70,7 @@ from ..utils import (
     str_or_none,
     str_to_int,
     strip_or_none,
+    try_get,
     unescapeHTML,
     unified_strdate,
     unified_timestamp,
@@ -230,8 +231,10 @@ class InfoExtractor(object):
     uploader:       Full name of the video uploader.
     license:        License name the video is licensed under.
     creator:        The creator of the video.
+    release_timestamp: UNIX timestamp of the moment the video was released.
     release_date:   The date (YYYYMMDD) when the video was released.
-    timestamp:      UNIX timestamp of the moment the video became available.
+    timestamp:      UNIX timestamp of the moment the video became available
+                    (uploaded).
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
@@ -1273,6 +1276,7 @@ class InfoExtractor(object):
 
         def extract_video_object(e):
             assert e['@type'] == 'VideoObject'
+            author = e.get('author')
             info.update({
                 'url': url_or_none(e.get('contentUrl')),
                 'title': unescapeHTML(e.get('name')),
@@ -1280,7 +1284,11 @@ class InfoExtractor(object):
                 'thumbnail': url_or_none(e.get('thumbnailUrl') or e.get('thumbnailURL')),
                 'duration': parse_duration(e.get('duration')),
                 'timestamp': unified_timestamp(e.get('uploadDate')),
-                'uploader': str_or_none(e.get('author')),
+                # author can be an instance of 'Organization' or 'Person' types.
+                # both types can have 'name' property(inherited from 'Thing' type). [1]
+                # however some websites are using 'Text' type instead.
+                # 1. https://schema.org/VideoObject
+                'uploader': author.get('name') if isinstance(author, dict) else author if isinstance(author, compat_str) else None,
                 'filesize': float_or_none(e.get('contentSize')),
                 'tbr': int_or_none(e.get('bitrate')),
                 'width': int_or_none(e.get('width')),
@@ -2064,7 +2072,7 @@ class InfoExtractor(object):
             })
         return entries
 
-    def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, data=None, headers={}, query={}):
+    def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}):
         res = self._download_xml_handle(
             mpd_url, video_id,
             note=note or 'Downloading MPD manifest',
@@ -2078,10 +2086,9 @@ class InfoExtractor(object):
         mpd_base_url = base_url(urlh.geturl())
 
         return self._parse_mpd_formats(
-            mpd_doc, mpd_id=mpd_id, mpd_base_url=mpd_base_url,
-            formats_dict=formats_dict, mpd_url=mpd_url)
+            mpd_doc, mpd_id, mpd_base_url, mpd_url)
 
-    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}, mpd_url=None):
+    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', mpd_url=None):
         """
         Parse formats from MPD manifest.
         References:
@@ -2359,15 +2366,7 @@ class InfoExtractor(object):
                         else:
                             # Assuming direct URL to unfragmented media.
                             f['url'] = base_url
-
-                        # According to [1, 5.3.5.2, Table 7, page 35] @id of Representation
-                        # is not necessarily unique within a Period thus formats with
-                        # the same `format_id` are quite possible. There are numerous examples
-                        # of such manifests (see https://github.com/ytdl-org/youtube-dl/issues/15111,
-                        # https://github.com/ytdl-org/youtube-dl/issues/13919)
-                        full_info = formats_dict.get(representation_id, {}).copy()
-                        full_info.update(f)
-                        formats.append(full_info)
+                        formats.append(f)
                     else:
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
         return formats
@@ -2715,7 +2714,7 @@ class InfoExtractor(object):
 
     def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
         mobj = re.search(
-            r'(?s)jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)(?!</script>).*?\.setup\s*\((?P<options>[^)]+)\)',
+            r'''(?s)jwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?!</script>).*?\.\s*setup\s*\(\s*(?P<options>(?:\([^)]*\)|[^)])+)\s*\)''',
             webpage)
         if mobj:
             try:
@@ -2736,9 +2735,14 @@ class InfoExtractor(object):
 
     def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True,
                              m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
+        flat_pl = try_get(jwplayer_data, lambda x: x.get('playlist') or True)
+        if flat_pl is None:
+            # not even a dict
+            return []
+
         # JWPlayer backward compatibility: flattened playlists
         # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
-        if 'playlist' not in jwplayer_data:
+        if flat_pl is True:
             jwplayer_data = {'playlist': [jwplayer_data]}
 
         entries = []
@@ -2786,6 +2790,13 @@ class InfoExtractor(object):
                 'timestamp': int_or_none(video_data.get('pubdate')),
                 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
                 'subtitles': subtitles,
+                'alt_title': clean_html(video_data.get('subtitle')),  # attributes used e.g. by Tele5 ...
+                'genre': clean_html(video_data.get('genre')),
+                'channel': clean_html(dict_get(video_data, ('category', 'channel'))),
+                'season_number': int_or_none(video_data.get('season')),
+                'episode_number': int_or_none(video_data.get('episode')),
+                'release_year': int_or_none(video_data.get('releasedate')),
+                'age_limit': int_or_none(video_data.get('age_restriction')),
             }
             # https://github.com/jwplayer/jwplayer/blob/master/src/js/utils/validator.js#L32
             if len(formats) == 1 and re.search(r'^(?:http|//).*(?:youtube\.com|youtu\.be)/.+', formats[0]['url']):
@@ -2794,6 +2805,8 @@ class InfoExtractor(object):
                     'url': formats[0]['url'],
                 })
             else:
+                # avoid exception in case of only sttls
+                if formats:
                     self._sort_formats(formats)
                 entry['formats'] = formats
             entries.append(entry)
@@ -2804,7 +2817,7 @@ class InfoExtractor(object):
 
     def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
                                 m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
-        urls = []
+        urls = set()
         formats = []
         for source in jwplayer_sources_data:
             if not isinstance(source, dict):
@@ -2813,14 +2826,14 @@ class InfoExtractor(object):
                 base_url, self._proto_relative_url(source.get('file')))
             if not source_url or source_url in urls:
                 continue
-            urls.append(source_url)
+            urls.add(source_url)
             source_type = source.get('type') or ''
             ext = mimetype2ext(source_type) or determine_ext(source_url)
-            if source_type == 'hls' or ext == 'm3u8':
+            if source_type == 'hls' or ext == 'm3u8' or 'format=m3u8-aapl' in source_url:
                 formats.extend(self._extract_m3u8_formats(
                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',
                     m3u8_id=m3u8_id, fatal=False))
-            elif source_type == 'dash' or ext == 'mpd':
+            elif source_type == 'dash' or ext == 'mpd' or 'format=mpd-time-csf' in source_url:
                 formats.extend(self._extract_mpd_formats(
                     source_url, video_id, mpd_id=mpd_id, fatal=False))
             elif ext == 'smil':
@@ -2835,20 +2848,23 @@ class InfoExtractor(object):
                     'ext': ext,
                 })
             else:
+                format_id = str_or_none(source.get('label'))
                 height = int_or_none(source.get('height'))
-                if height is None:
+                if height is None and format_id:
                     # Often no height is provided but there is a label in
                     # format like "1080p", "720p SD", or 1080.
-                    height = int_or_none(self._search_regex(
-                        r'^(\d{3,4})[pP]?(?:\b|$)', compat_str(source.get('label') or ''),
-                        'height', default=None))
+                    height = parse_resolution(format_id).get('height')
                 a_format = {
                     'url': source_url,
                     'width': int_or_none(source.get('width')),
                     'height': height,
-                    'tbr': int_or_none(source.get('bitrate')),
+                    'tbr': int_or_none(source.get('bitrate'), scale=1000),
+                    'filesize': int_or_none(source.get('filesize')),
                     'ext': ext,
                 }
+                if format_id:
+                    a_format['format_id'] = format_id
+
                 if source_url.startswith('rtmp'):
                     a_format['ext'] = 'flv'
                     # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
@@ -2903,10 +2919,10 @@ class InfoExtractor(object):
         self._downloader.cookiejar.set_cookie(cookie)
 
     def _get_cookies(self, url):
-        """ Return a compat_cookies.SimpleCookie with the cookies for the url """
+        """ Return a compat_cookies_SimpleCookie with the cookies for the url """
         req = sanitized_Request(url)
         self._downloader.cookiejar.add_cookie_header(req)
-        return compat_cookies.SimpleCookie(req.get_header('Cookie'))
+        return compat_cookies_SimpleCookie(req.get_header('Cookie'))
 
     def _apply_first_set_cookie_header(self, url_handle, cookie):
         """

youtube_dl/extractor/cpac.py

@@ -0,0 +1,148 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    str_or_none,
+    try_get,
+    unified_timestamp,
+    update_url_query,
+    urljoin,
+)
+
+# compat_range
+try:
+    if callable(xrange):
+        range = xrange
+except (NameError, TypeError):
+    pass
+
+
+class CPACIE(InfoExtractor):
+    IE_NAME = 'cpac'
+    _VALID_URL = r'https?://(?:www\.)?cpac\.ca/(?P<fr>l-)?episode\?id=(?P<id>[\da-f]{8}(?:-[\da-f]{4}){3}-[\da-f]{12})'
+    _TEST = {
+        # 'url': 'http://www.cpac.ca/en/programs/primetime-politics/episodes/65490909',
+        'url': 'https://www.cpac.ca/episode?id=fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
+        'md5': 'e46ad699caafd7aa6024279f2614e8fa',
+        'info_dict': {
+            'id': 'fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
+            'ext': 'mp4',
+            'upload_date': '20220215',
+            'title': 'News Conference to Celebrate National Kindness Week – February 15, 2022',
+            'description': 'md5:466a206abd21f3a6f776cdef290c23fb',
+            'timestamp': 1644901200,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'hls_prefer_native': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url_lang = 'fr' if '/l-episode?' in url else 'en'
+
+        content = self._download_json(
+            'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/episode/index.xml&crafterSite=cpacca&id=' + video_id,
+            video_id)
+        video_url = try_get(content, lambda x: x['page']['details']['videoUrl'], compat_str)
+        formats = []
+        if video_url:
+            content = content['page']
+            title = str_or_none(content['details']['title_%s_t' % (url_lang, )])
+            formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', ext='mp4')
+            for fmt in formats:
+                # prefer language to match URL
+                fmt_lang = fmt.get('language')
+                if fmt_lang == url_lang:
+                    fmt['language_preference'] = 10
+                elif not fmt_lang:
+                    fmt['language_preference'] = -1
+                else:
+                    fmt['language_preference'] = -10
+
+        self._sort_formats(formats)
+
+        category = str_or_none(content['details']['category_%s_t' % (url_lang, )])
+
+        def is_live(v_type):
+            return (v_type == 'live') if v_type is not None else None
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'description': str_or_none(content['details'].get('description_%s_t' % (url_lang, ))),
+            'timestamp': unified_timestamp(content['details'].get('liveDateTime')),
+            'category': [category] if category else None,
+            'thumbnail': urljoin(url, str_or_none(content['details'].get('image_%s_s' % (url_lang, )))),
+            'is_live': is_live(content['details'].get('type')),
+        }
+
+
+class CPACPlaylistIE(InfoExtractor):
+    IE_NAME = 'cpac:playlist'
+    _VALID_URL = r'(?i)https?://(?:www\.)?cpac\.ca/(?:program|search|(?P<fr>emission|rechercher))\?(?:[^&]+&)*?(?P<id>(?:id=\d+|programId=\d+|key=[^&]+))'
+
+    _TESTS = [{
+        'url': 'https://www.cpac.ca/program?id=6',
+        'info_dict': {
+            'id': 'id=6',
+            'title': 'Headline Politics',
+            'description': 'Watch CPAC’s signature long-form coverage of the day’s pressing political events as they unfold.',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.cpac.ca/search?key=hudson&type=all&order=desc',
+        'info_dict': {
+            'id': 'key=hudson',
+            'title': 'hudson',
+        },
+        'playlist_count': 22,
+    }, {
+        'url': 'https://www.cpac.ca/search?programId=50',
+        'info_dict': {
+            'id': 'programId=50',
+            'title': '50',
+        },
+        'playlist_count': 9,
+    }, {
+        'url': 'https://www.cpac.ca/emission?id=6',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cpac.ca/rechercher?key=hudson&type=all&order=desc',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url_lang = 'fr' if any(x in url for x in ('/emission?', '/rechercher?')) else 'en'
+        pl_type, list_type = ('program', 'itemList') if any(x in url for x in ('/program?', '/emission?')) else ('search', 'searchResult')
+        api_url = (
+            'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/%s/index.xml&crafterSite=cpacca&%s'
+            % (pl_type, video_id, ))
+        content = self._download_json(api_url, video_id)
+        entries = []
+        total_pages = int_or_none(try_get(content, lambda x: x['page'][list_type]['totalPages']), default=1)
+        for page in range(1, total_pages + 1):
+            if page > 1:
+                api_url = update_url_query(api_url, {'page': '%d' % (page, ), })
+                content = self._download_json(
+                    api_url, video_id,
+                    note='Downloading continuation - %d' % (page, ),
+                    fatal=False)
+
+            for item in try_get(content, lambda x: x['page'][list_type]['item'], list) or []:
+                episode_url = urljoin(url, try_get(item, lambda x: x['url_%s_s' % (url_lang, )]))
+                if episode_url:
+                    entries.append(episode_url)
+
+        return self.playlist_result(
+            (self.url_result(entry) for entry in entries),
+            playlist_id=video_id,
+            playlist_title=try_get(content, lambda x: x['page']['program']['title_%s_t' % (url_lang, )]) or video_id.split('=')[-1],
+            playlist_description=try_get(content, lambda x: x['page']['program']['description_%s_t' % (url_lang, )]),
+        )

youtube_dl/extractor/cspan.py

@@ -8,11 +8,14 @@ from ..utils import (
     ExtractorError,
     extract_attributes,
     find_xpath_attr,
+    get_element_by_attribute,
     get_element_by_class,
     int_or_none,
     js_to_json,
     merge_dicts,
+    parse_iso8601,
     smuggle_url,
+    str_to_int,
     unescapeHTML,
 )
 from .senateisvp import SenateISVPIE
@@ -116,8 +119,30 @@ class CSpanIE(InfoExtractor):
                 jwsetup, video_id, require_title=False, m3u8_id='hls',
                 base_url=url)
             add_referer(info['formats'])
+            for subtitles in info['subtitles'].values():
+                for subtitle in subtitles:
+                    ext = determine_ext(subtitle['url'])
+                    if ext == 'php':
+                        ext = 'vtt'
+                    subtitle['ext'] = ext
             ld_info = self._search_json_ld(webpage, video_id, default={})
-            return merge_dicts(info, ld_info)
+            title = get_element_by_class('video-page-title', webpage) or \
+                self._og_search_title(webpage)
+            description = get_element_by_attribute('itemprop', 'description', webpage) or \
+                self._html_search_meta(['og:description', 'description'], webpage)
+            return merge_dicts(info, ld_info, {
+                'title': title,
+                'thumbnail': get_element_by_attribute('itemprop', 'thumbnailUrl', webpage),
+                'description': description,
+                'timestamp': parse_iso8601(get_element_by_attribute('itemprop', 'uploadDate', webpage)),
+                'location': get_element_by_attribute('itemprop', 'contentLocation', webpage),
+                'duration': int_or_none(self._search_regex(
+                    r'jwsetup\.seclength\s*=\s*(\d+);',
+                    webpage, 'duration', fatal=False)),
+                'view_count': str_to_int(self._search_regex(
+                    r"<span[^>]+class='views'[^>]*>([\d,]+)\s+Views</span>",
+                    webpage, 'views', fatal=False)),
+            })
 
         # Obsolete
         # We first look for clipid, because clipprog always appears before

youtube_dl/extractor/curiositystream.py

@@ -25,12 +25,12 @@ class CuriosityStreamBaseIE(InfoExtractor):
             raise ExtractorError(
                 '%s said: %s' % (self.IE_NAME, error), expected=True)
 
-    def _call_api(self, path, video_id):
+    def _call_api(self, path, video_id, query=None):
         headers = {}
         if self._auth_token:
             headers['X-Auth-Token'] = self._auth_token
         result = self._download_json(
-            self._API_BASE_URL + path, video_id, headers=headers)
+            self._API_BASE_URL + path, video_id, headers=headers, query=query)
         self._handle_errors(result)
         return result['data']
 
@@ -52,27 +52,38 @@ class CuriosityStreamIE(CuriosityStreamBaseIE):
     _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)'
     _TEST = {
         'url': 'https://app.curiositystream.com/video/2',
-        'md5': '262bb2f257ff301115f1973540de8983',
         'info_dict': {
             'id': '2',
             'ext': 'mp4',
             'title': 'How Did You Develop The Internet?',
             'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
-        }
+        },
+        'params': {
+            'format': 'bestvideo',
+            # m3u8 download
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        media = self._call_api('media/' + video_id, video_id)
-        title = media['title']
 
         formats = []
+        for encoding_format in ('m3u8', 'mpd'):
+            media = self._call_api('media/' + video_id, video_id, query={
+                'encodingsNew': 'true',
+                'encodingsFormat': encoding_format,
+            })
             for encoding in media.get('encodings', []):
-            m3u8_url = encoding.get('master_playlist_url')
-            if m3u8_url:
+                playlist_url = encoding.get('master_playlist_url')
+                if encoding_format == 'm3u8':
+                    # use `m3u8` entry_protocol until EXT-X-MAP is properly supported by `m3u8_native` entry_protocol
                     formats.extend(self._extract_m3u8_formats(
-                    m3u8_url, video_id, 'mp4', 'm3u8_native',
+                        playlist_url, video_id, 'mp4',
                         m3u8_id='hls', fatal=False))
+                elif encoding_format == 'mpd':
+                    formats.extend(self._extract_mpd_formats(
+                        playlist_url, video_id, mpd_id='dash', fatal=False))
                 encoding_url = encoding.get('url')
                 file_url = encoding.get('file_url')
                 if not encoding_url and not file_url:
@@ -108,6 +119,8 @@ class CuriosityStreamIE(CuriosityStreamBaseIE):
                     formats.append(fmt)
         self._sort_formats(formats)
 
+        title = media['title']
+
         subtitles = {}
         for closed_caption in media.get('closed_captions', []):
             sub_url = closed_caption.get('file')
@@ -132,7 +145,7 @@ class CuriosityStreamIE(CuriosityStreamBaseIE):
 
 class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
     IE_NAME = 'curiositystream:collection'
-    _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collection|series)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collections?|series)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://app.curiositystream.com/collection/2',
         'info_dict': {
@@ -140,10 +153,13 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
             'title': 'Curious Minds: The Internet',
             'description': 'How is the internet shaping our lives in the 21st Century?',
         },
-        'playlist_mincount': 17,
+        'playlist_mincount': 16,
     }, {
         'url': 'https://curiositystream.com/series/2',
         'only_matching': True,
+    }, {
+        'url': 'https://curiositystream.com/collections/36',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/dispeak.py

@@ -32,6 +32,18 @@ class DigitallySpeakingIE(InfoExtractor):
         # From http://www.gdcvault.com/play/1013700/Advanced-Material
         'url': 'http://sevt.dispeak.com/ubm/gdc/eur10/xml/11256_1282118587281VNIT.xml',
         'only_matching': True,
+    }, {
+        # From https://gdcvault.com/play/1016624, empty speakerVideo
+        'url': 'https://sevt.dispeak.com/ubm/gdc/online12/xml/201210-822101_1349794556671DDDD.xml',
+        'info_dict': {
+            'id': '201210-822101_1349794556671DDDD',
+            'ext': 'flv',
+            'title': 'Pre-launch - Preparing to Take the Plunge',
+        },
+    }, {
+        # From http://www.gdcvault.com/play/1014846/Conference-Keynote-Shigeru, empty slideVideo
+        'url': 'http://events.digitallyspeaking.com/gdc/project25/xml/p25-miyamoto1999_1282467389849HSVB.xml',
+        'only_matching': True,
     }]
 
     def _parse_mp4(self, metadata):
@@ -84,25 +96,19 @@ class DigitallySpeakingIE(InfoExtractor):
                 'vcodec': 'none',
                 'format_id': audio.get('code'),
             })
-        slide_video_path = xpath_text(metadata, './slideVideo', fatal=True)
+        for video_key, format_id, preference in (
+                ('slide', 'slides', -2), ('speaker', 'speaker', -1)):
+            video_path = xpath_text(metadata, './%sVideo' % video_key)
+            if not video_path:
+                continue
             formats.append({
                 'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
-            'play_path': remove_end(slide_video_path, '.flv'),
+                'play_path': remove_end(video_path, '.flv'),
                 'ext': 'flv',
-            'format_note': 'slide deck video',
-            'quality': -2,
-            'preference': -2,
-            'format_id': 'slides',
-        })
-        speaker_video_path = xpath_text(metadata, './speakerVideo', fatal=True)
-        formats.append({
-            'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
-            'play_path': remove_end(speaker_video_path, '.flv'),
-            'ext': 'flv',
-            'format_note': 'speaker video',
-            'quality': -1,
-            'preference': -1,
-            'format_id': 'speaker',
+                'format_note': '%s video' % video_key,
+                'quality': preference,
+                'preference': preference,
+                'format_id': format_id,
             })
         return formats
 

youtube_dl/extractor/dplay.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
@@ -10,16 +11,23 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    strip_or_none,
     unified_timestamp,
 )
 
 
 class DPlayIE(InfoExtractor):
+    _PATH_REGEX = r'/(?P<id>[^/]+/[^/?#]+)'
     _VALID_URL = r'''(?x)https?://
         (?P<domain>
-            (?:www\.)?(?P<host>dplay\.(?P<country>dk|fi|jp|se|no))|
+            (?:www\.)?(?P<host>d
+                (?:
+                    play\.(?P<country>dk|fi|jp|se|no)|
+                    iscoveryplus\.(?P<plus_country>dk|es|fi|it|se|no)
+                )
+            )|
             (?P<subdomain_country>es|it)\.dplay\.com
-        )/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
+        )/[^/]+''' + _PATH_REGEX
 
     _TESTS = [{
         # non geo restricted, via secure api, unsigned download hls URL
@@ -126,23 +134,67 @@ class DPlayIE(InfoExtractor):
     }, {
         'url': 'https://www.dplay.jp/video/gold-rush/24086',
         'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.no/videoer/i-kongens-klr/sesong-1-episode-7',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.it/videos/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.es/videos/la-fiebre-del-oro/temporada-8-episodio-1',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.fi/videot/shifting-gears-with-aaron-kaufman/episode-16',
+        'only_matching': True,
     }]
 
+    def _process_errors(self, e, geo_countries):
+        info = self._parse_json(e.cause.read().decode('utf-8'), None)
+        error = info['errors'][0]
+        error_code = error.get('code')
+        if error_code == 'access.denied.geoblocked':
+            self.raise_geo_restricted(countries=geo_countries)
+        elif error_code in ('access.denied.missingpackage', 'invalid.token'):
+            raise ExtractorError(
+                'This video is only available for registered users. You may want to use --cookies.', expected=True)
+        raise ExtractorError(info['errors'][0]['detail'], expected=True)
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers['Authorization'] = 'Bearer ' + self._download_json(
+            disco_base + 'token', display_id, 'Downloading token',
+            query={
+                'realm': realm,
+            })['data']['attributes']['token']
+
+    def _download_video_playback_info(self, disco_base, video_id, headers):
+        streaming = self._download_json(
+            disco_base + 'playback/videoPlaybackInfo/' + video_id,
+            video_id, headers=headers)['data']['attributes']['streaming']
+        streaming_list = []
+        for format_id, format_dict in streaming.items():
+            streaming_list.append({
+                'type': format_id,
+                'url': format_dict.get('url'),
+            })
+        return streaming_list
+
     def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
         geo_countries = [country.upper()]
         self._initialize_geo_bypass({
             'countries': geo_countries,
         })
         disco_base = 'https://%s/' % disco_host
-        token = self._download_json(
-            disco_base + 'token', display_id, 'Downloading token',
-            query={
-                'realm': realm,
-            })['data']['attributes']['token']
         headers = {
             'Referer': url,
-            'Authorization': 'Bearer ' + token,
         }
+        self._update_disco_api_headers(headers, disco_base, display_id, realm)
+        try:
             video = self._download_json(
                 disco_base + 'content/videos/' + display_id, display_id,
                 headers=headers, query={
@@ -153,31 +205,28 @@ class DPlayIE(InfoExtractor):
                     'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
                     'include': 'images,primaryChannel,show,tags'
                 })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
+                self._process_errors(e, geo_countries)
+            raise
         video_id = video['data']['id']
         info = video['data']['attributes']
         title = info['name'].strip()
         formats = []
         try:
-            streaming = self._download_json(
-                disco_base + 'playback/videoPlaybackInfo/' + video_id,
-                display_id, headers=headers)['data']['attributes']['streaming']
+            streaming = self._download_video_playback_info(
+                disco_base, video_id, headers)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
-                info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
-                error = info['errors'][0]
-                error_code = error.get('code')
-                if error_code == 'access.denied.geoblocked':
-                    self.raise_geo_restricted(countries=geo_countries)
-                elif error_code == 'access.denied.missingpackage':
-                    self.raise_login_required()
-                raise ExtractorError(info['errors'][0]['detail'], expected=True)
+                self._process_errors(e, geo_countries)
             raise
-        for format_id, format_dict in streaming.items():
+        for format_dict in streaming:
             if not isinstance(format_dict, dict):
                 continue
             format_url = format_dict.get('url')
             if not format_url:
                 continue
+            format_id = format_dict.get('type')
             ext = determine_ext(format_url)
             if format_id == 'dash' or ext == 'mpd':
                 formats.extend(self._extract_mpd_formats(
@@ -225,7 +274,7 @@ class DPlayIE(InfoExtractor):
             'id': video_id,
             'display_id': display_id,
             'title': title,
-            'description': info.get('description'),
+            'description': strip_or_none(info.get('description')),
             'duration': float_or_none(info.get('videoDuration'), 1000),
             'timestamp': unified_timestamp(info.get('publishStart')),
             'series': series,
@@ -241,7 +290,80 @@ class DPlayIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         display_id = mobj.group('id')
         domain = mobj.group('domain').lstrip('www.')
-        country = mobj.group('country') or mobj.group('subdomain_country')
-        host = 'disco-api.' + domain if domain.startswith('dplay.') else 'eu2-prod.disco-api.com'
+        country = mobj.group('country') or mobj.group('subdomain_country') or mobj.group('plus_country')
+        host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com'
         return self._get_disco_api_info(
             url, display_id, host, 'dplay' + country, country)
+
+
+class DiscoveryPlusIE(DPlayIE):
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/video' + DPlayIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
+        'info_dict': {
+            'id': '1140794',
+            'display_id': 'property-brothers-forever-home/food-and-family',
+            'ext': 'mp4',
+            'title': 'Food and Family',
+            'description': 'The brothers help a Richmond family expand their single-level home.',
+            'duration': 2583.113,
+            'timestamp': 1609304400,
+            'upload_date': '20201230',
+            'creator': 'HGTV',
+            'series': 'Property Brothers: Forever Home',
+            'season_number': 1,
+            'episode_number': 1,
+        },
+        'skip': 'Available for Premium users',
+    }]
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers['x-disco-client'] = 'WEB:UNKNOWN:dplus_us:15.0.0'
+
+    def _download_video_playback_info(self, disco_base, video_id, headers):
+        return self._download_json(
+            disco_base + 'playback/v3/videoPlaybackInfo',
+            video_id, headers=headers, data=json.dumps({
+                'deviceInfo': {
+                    'adBlocker': False,
+                },
+                'videoId': video_id,
+                'wisteriaProperties': {
+                    'platform': 'desktop',
+                    'product': 'dplus_us',
+                },
+            }).encode('utf-8'))['data']['attributes']['streaming']
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        return self._get_disco_api_info(
+            url, display_id, 'us1-prod-direct.discoveryplus.com', 'go', 'us')
+
+
+class HGTVDeIE(DPlayIE):
+    _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
+        'info_dict': {
+            'id': '151205',
+            'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
+            'ext': 'mp4',
+            'title': 'Wer braucht schon eine Toilette',
+            'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
+            'duration': 1177.024,
+            'timestamp': 1595705400,
+            'upload_date': '20200725',
+            'creator': 'HGTV',
+            'series': 'Tiny House - klein, aber oho',
+            'season_number': 3,
+            'episode_number': 3,
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        return self._get_disco_api_info(
+            url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')

youtube_dl/extractor/dreisat.py

@@ -1,193 +1,43 @@
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    unified_strdate,
-    xpath_text,
-    determine_ext,
-    float_or_none,
-    ExtractorError,
-)
+from .zdf import ZDFIE
 
 
-class DreiSatIE(InfoExtractor):
+class DreiSatIE(ZDFIE):
     IE_NAME = '3sat'
-    _GEO_COUNTRIES = ['DE']
-    _VALID_URL = r'https?://(?:www\.)?3sat\.de/mediathek/(?:(?:index|mediathek)\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)'
-    _TESTS = [
-        {
-            'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
-            'md5': 'be37228896d30a88f315b638900a026e',
+    _VALID_URL = r'https?://(?:www\.)?3sat\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
+    _TESTS = [{
+        # Same as https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html
+        'url': 'https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html',
+        'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
         'info_dict': {
-                'id': '45918',
+            'id': '141007_ab18_10wochensommer_film',
+            'ext': 'mp4',
+            'title': 'Ab 18! - 10 Wochen Sommer',
+            'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
+            'duration': 2660,
+            'timestamp': 1608604200,
+            'upload_date': '20201222',
+        },
+    }, {
+        'url': 'https://www.3sat.de/gesellschaft/schweizweit/waidmannsheil-100.html',
+        'info_dict': {
+            'id': '140913_sendung_schweizweit',
             'ext': 'mp4',
             'title': 'Waidmannsheil',
             'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
-                'uploader': 'SCHWEIZWEIT',
-                'uploader_id': '100000210',
+            'timestamp': 1410623100,
             'upload_date': '20140913'
         },
         'params': {
-                'skip_download': True,  # m3u8 downloads
+            'skip_download': True,
         }
-        },
-        {
-            'url': 'http://www.3sat.de/mediathek/mediathek.php?mode=play&obj=51066',
+    }, {
+        # Same as https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html
+        'url': 'https://www.3sat.de/film/spielfilm/der-hauptmann-100.html',
         'only_matching': True,
-        },
-    ]
-
-    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
-        param_groups = {}
-        for param_group in smil.findall(self._xpath_ns('./head/paramGroup', namespace)):
-            group_id = param_group.get(self._xpath_ns(
-                'id', 'http://www.w3.org/XML/1998/namespace'))
-            params = {}
-            for param in param_group:
-                params[param.get('name')] = param.get('value')
-            param_groups[group_id] = params
-
-        formats = []
-        for video in smil.findall(self._xpath_ns('.//video', namespace)):
-            src = video.get('src')
-            if not src:
-                continue
-            bitrate = int_or_none(self._search_regex(r'_(\d+)k', src, 'bitrate', None)) or float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
-            group_id = video.get('paramGroup')
-            param_group = param_groups[group_id]
-            for proto in param_group['protocols'].split(','):
-                formats.append({
-                    'url': '%s://%s' % (proto, param_group['host']),
-                    'app': param_group['app'],
-                    'play_path': src,
-                    'ext': 'flv',
-                    'format_id': '%s-%d' % (proto, bitrate),
-                    'tbr': bitrate,
-                })
-        self._sort_formats(formats)
-        return formats
-
-    def extract_from_xml_url(self, video_id, xml_url):
-        doc = self._download_xml(
-            xml_url, video_id,
-            note='Downloading video info',
-            errnote='Failed to download video info')
-
-        status_code = xpath_text(doc, './status/statuscode')
-        if status_code and status_code != 'ok':
-            if status_code == 'notVisibleAnymore':
-                message = 'Video %s is not available' % video_id
-            else:
-                message = '%s returned error: %s' % (self.IE_NAME, status_code)
-            raise ExtractorError(message, expected=True)
-
-        title = xpath_text(doc, './/information/title', 'title', True)
-
-        urls = []
-        formats = []
-        for fnode in doc.findall('.//formitaeten/formitaet'):
-            video_url = xpath_text(fnode, 'url')
-            if not video_url or video_url in urls:
-                continue
-            urls.append(video_url)
-
-            is_available = 'http://www.metafilegenerator' not in video_url
-            geoloced = 'static_geoloced_online' in video_url
-            if not is_available or geoloced:
-                continue
-
-            format_id = fnode.attrib['basetype']
-            format_m = re.match(r'''(?x)
-                (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
-                (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
-            ''', format_id)
-
-            ext = determine_ext(video_url, None) or format_m.group('container')
-
-            if ext == 'meta':
-                continue
-            elif ext == 'smil':
-                formats.extend(self._extract_smil_formats(
-                    video_url, video_id, fatal=False))
-            elif ext == 'm3u8':
-                # the certificates are misconfigured (see
-                # https://github.com/ytdl-org/youtube-dl/issues/8665)
-                if video_url.startswith('https://'):
-                    continue
-                formats.extend(self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id=format_id, fatal=False))
-            elif ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    video_url, video_id, f4m_id=format_id, fatal=False))
-            else:
-                quality = xpath_text(fnode, './quality')
-                if quality:
-                    format_id += '-' + quality
-
-                abr = int_or_none(xpath_text(fnode, './audioBitrate'), 1000)
-                vbr = int_or_none(xpath_text(fnode, './videoBitrate'), 1000)
-
-                tbr = int_or_none(self._search_regex(
-                    r'_(\d+)k', video_url, 'bitrate', None))
-                if tbr and vbr and not abr:
-                    abr = tbr - vbr
-
-                formats.append({
-                    'format_id': format_id,
-                    'url': video_url,
-                    'ext': ext,
-                    'acodec': format_m.group('acodec'),
-                    'vcodec': format_m.group('vcodec'),
-                    'abr': abr,
-                    'vbr': vbr,
-                    'tbr': tbr,
-                    'width': int_or_none(xpath_text(fnode, './width')),
-                    'height': int_or_none(xpath_text(fnode, './height')),
-                    'filesize': int_or_none(xpath_text(fnode, './filesize')),
-                    'protocol': format_m.group('proto').lower(),
-                })
-
-        geolocation = xpath_text(doc, './/details/geolocation')
-        if not formats and geolocation and geolocation != 'none':
-            self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
-
-        self._sort_formats(formats)
-
-        thumbnails = []
-        for node in doc.findall('.//teaserimages/teaserimage'):
-            thumbnail_url = node.text
-            if not thumbnail_url:
-                continue
-            thumbnail = {
-                'url': thumbnail_url,
-            }
-            thumbnail_key = node.get('key')
-            if thumbnail_key:
-                m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
-                if m:
-                    thumbnail['width'] = int(m.group(1))
-                    thumbnail['height'] = int(m.group(2))
-            thumbnails.append(thumbnail)
-
-        upload_date = unified_strdate(xpath_text(doc, './/details/airtime'))
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': xpath_text(doc, './/information/detail'),
-            'duration': int_or_none(xpath_text(doc, './/details/lengthSec')),
-            'thumbnails': thumbnails,
-            'uploader': xpath_text(doc, './/details/originChannelTitle'),
-            'uploader_id': xpath_text(doc, './/details/originChannelId'),
-            'upload_date': upload_date,
-            'formats': formats,
-        }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?id=%s' % video_id
-        return self.extract_from_xml_url(video_id, details_url)
+    }, {
+        # Same as https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
+        'url': 'https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html',
+        'only_matching': True,
+    }]

youtube_dl/extractor/egghead.py

@@ -12,26 +12,35 @@ from ..utils import (
 )
 
 
-class EggheadCourseIE(InfoExtractor):
+class EggheadBaseIE(InfoExtractor):
+    def _call_api(self, path, video_id, resource, fatal=True):
+        return self._download_json(
+            'https://app.egghead.io/api/v1/' + path,
+            video_id, 'Downloading %s JSON' % resource, fatal=fatal)
+
+
+class EggheadCourseIE(EggheadBaseIE):
     IE_DESC = 'egghead.io course'
     IE_NAME = 'egghead:course'
-    _VALID_URL = r'https://egghead\.io/courses/(?P<id>[^/?#&]+)'
-    _TEST = {
+    _VALID_URL = r'https://(?:app\.)?egghead\.io/(?:course|playlist)s/(?P<id>[^/?#&]+)'
+    _TESTS = [{
         'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
         'playlist_count': 29,
         'info_dict': {
-            'id': '72',
+            'id': '432655',
             'title': 'Professor Frisby Introduces Composable Functional JavaScript',
             'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
         },
-    }
+    }, {
+        'url': 'https://app.egghead.io/playlists/professor-frisby-introduces-composable-functional-javascript',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
-
-        lessons = self._download_json(
-            'https://egghead.io/api/v1/series/%s/lessons' % playlist_id,
-            playlist_id, 'Downloading course lessons JSON')
+        series_path = 'series/' + playlist_id
+        lessons = self._call_api(
+            series_path + '/lessons', playlist_id, 'course lessons')
 
         entries = []
         for lesson in lessons:
@@ -44,9 +53,8 @@ class EggheadCourseIE(InfoExtractor):
             entries.append(self.url_result(
                 lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
 
-        course = self._download_json(
-            'https://egghead.io/api/v1/series/%s' % playlist_id,
-            playlist_id, 'Downloading course JSON', fatal=False) or {}
+        course = self._call_api(
+            series_path, playlist_id, 'course', False) or {}
 
         playlist_id = course.get('id')
         if playlist_id:
@@ -57,10 +65,10 @@ class EggheadCourseIE(InfoExtractor):
             course.get('description'))
 
 
-class EggheadLessonIE(InfoExtractor):
+class EggheadLessonIE(EggheadBaseIE):
     IE_DESC = 'egghead.io lesson'
     IE_NAME = 'egghead:lesson'
-    _VALID_URL = r'https://egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https://(?:app\.)?egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
         'info_dict': {
@@ -74,7 +82,7 @@ class EggheadLessonIE(InfoExtractor):
             'upload_date': '20161209',
             'duration': 304,
             'view_count': 0,
-            'tags': ['javascript', 'free'],
+            'tags': 'count:2',
         },
         'params': {
             'skip_download': True,
@@ -83,13 +91,16 @@ class EggheadLessonIE(InfoExtractor):
     }, {
         'url': 'https://egghead.io/api/v1/lessons/react-add-redux-to-a-react-application',
         'only_matching': True,
+    }, {
+        'url': 'https://app.egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
-        lesson = self._download_json(
-            'https://egghead.io/api/v1/lessons/%s' % display_id, display_id)
+        lesson = self._call_api(
+            'lessons/' + display_id, display_id, 'lesson')
 
         lesson_id = compat_str(lesson['id'])
         title = lesson['title']

youtube_dl/extractor/eroprofile.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlencode
 from ..utils import (
     ExtractorError,
-    unescapeHTML
+    merge_dicts,
 )
 
 
@@ -24,7 +24,8 @@ class EroProfileIE(InfoExtractor):
             'title': 'sexy babe softcore',
             'thumbnail': r're:https?://.*\.jpg',
             'age_limit': 18,
-        }
+        },
+        'skip': 'Video not found',
     }, {
         'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
         'md5': '1baa9602ede46ce904c431f5418d8916',
@@ -77,19 +78,15 @@ class EroProfileIE(InfoExtractor):
             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
             webpage, 'video id', default=None)
 
-        video_url = unescapeHTML(self._search_regex(
-            r'<source src="([^"]+)', webpage, 'video url'))
         title = self._html_search_regex(
-            r'Title:</th><td>([^<]+)</td>', webpage, 'title')
-        thumbnail = self._search_regex(
-            r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
-            webpage, 'thumbnail', fatal=False)
+            (r'Title:</th><td>([^<]+)</td>', r'<h1[^>]*>(.+?)</h1>'),
+            webpage, 'title')
 
-        return {
+        info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+
+        return merge_dicts(info, {
             'id': video_id,
             'display_id': display_id,
-            'url': video_url,
             'title': title,
-            'thumbnail': thumbnail,
             'age_limit': 18,
-        }
+        })

youtube_dl/extractor/extractors.py

@@ -42,12 +42,19 @@ from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
 from .amara import AmaraIE
 from .amcnetworks import AMCNetworksIE
-from .americastestkitchen import AmericasTestKitchenIE
+from .americastestkitchen import (
+    AmericasTestKitchenIE,
+    AmericasTestKitchenSeasonIE,
+)
 from .animeondemand import AnimeOnDemandIE
 from .anvato import AnvatoIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aliexpress import AliExpressLiveIE
+from .alsace20tv import (
+    Alsace20TVIE,
+    Alsace20TVEmbedIE,
+)
 from .apa import APAIE
 from .aparat import AparatIE
 from .appleconnect import AppleConnectIE
@@ -55,6 +62,7 @@ from .appletrailers import (
     AppleTrailersIE,
     AppleTrailersSectionIE,
 )
+from .applepodcasts import ApplePodcastsIE
 from .archiveorg import ArchiveOrgIE
 from .arcpublishing import ArcPublishingIE
 from .arkena import ArkenaIE
@@ -67,7 +75,9 @@ from .arte import (
     ArteTVIE,
     ArteTVEmbedIE,
     ArteTVPlaylistIE,
+    ArteTVCategoryIE,
 )
+from .arnes import ArnesIE
 from .asiancrush import (
     AsianCrushIE,
     AsianCrushPlaylistIE,
@@ -86,11 +96,13 @@ from .awaan import (
 )
 from .azmedien import AZMedienIE
 from .baidu import BaiduVideoIE
+from .bandaichannel import BandaiChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
 from .bbc import (
     BBCCoUkIE,
     BBCCoUkArticleIE,
-    BBCCoUkIPlayerPlaylistIE,
+    BBCCoUkIPlayerEpisodesIE,
+    BBCCoUkIPlayerGroupIE,
     BBCCoUkPlaylistIE,
     BBCIE,
 )
@@ -100,7 +112,14 @@ from .bellmedia import BellMediaIE
 from .beatport import BeatportIE
 from .bet import BetIE
 from .bfi import BFIPlayerIE
+from .bfmtv import (
+    BFMTVIE,
+    BFMTVLiveIE,
+    BFMTVArticleIE,
+)
+from .bibeltv import BibelTVIE
 from .bigflix import BigflixIE
+from .bigo import BigoIE
 from .bild import BildIE
 from .bilibili import (
     BiliBiliIE,
@@ -119,7 +138,6 @@ from .bleacherreport import (
     BleacherReportIE,
     BleacherReportCMSIE,
 )
-from .blinkx import BlinkxIE
 from .bloomberg import BloombergIE
 from .bokecc import BokeCCIE
 from .bongacams import BongaCamsIE
@@ -153,6 +171,7 @@ from .canvas import (
     CanvasIE,
     CanvasEenIE,
     VrtNUIE,
+    DagelijkseKostIE,
 )
 from .carambatv import (
     CarambaTVIE,
@@ -177,7 +196,11 @@ from .cbsnews import (
     CBSNewsIE,
     CBSNewsLiveVideoIE,
 )
-from .cbssports import CBSSportsIE
+from .cbssports import (
+    CBSSportsEmbedIE,
+    CBSSportsIE,
+    TwentyFourSevenSportsIE,
+)
 from .ccc import (
     CCCIE,
     CCCPlaylistIE,
@@ -185,10 +208,7 @@ from .ccc import (
 from .ccma import CCMAIE
 from .cctv import CCTVIE
 from .cda import CDAIE
-from .ceskatelevize import (
-    CeskaTelevizeIE,
-    CeskaTelevizePoradyIE,
-)
+from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .charlierose import CharlieRoseIE
 from .chaturbate import ChaturbateIE
@@ -225,11 +245,8 @@ from .cnn import (
 )
 from .coub import CoubIE
 from .comedycentral import (
-    ComedyCentralFullEpisodesIE,
     ComedyCentralIE,
-    ComedyCentralShortnameIE,
     ComedyCentralTVIE,
-    ToshIE,
 )
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .commonprotocols import (
@@ -239,6 +256,10 @@ from .commonprotocols import (
 from .condenast import CondeNastIE
 from .contv import CONtvIE
 from .corus import CorusIE
+from .cpac import (
+    CPACIE,
+    CPACPlaylistIE,
+)
 from .cracked import CrackedIE
 from .crackle import CrackleIE
 from .crooksandliars import CrooksAndLiarsIE
@@ -280,7 +301,11 @@ from .douyutv import (
     DouyuShowIE,
     DouyuTVIE,
 )
-from .dplay import DPlayIE
+from .dplay import (
+    DPlayIE,
+    DiscoveryPlusIE,
+    HGTVDeIE,
+)
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
@@ -409,6 +434,7 @@ from .gamestar import GameStarIE
 from .gaskrank import GaskrankIE
 from .gazeta import GazetaIE
 from .gdcvault import GDCVaultIE
+from .gedidigital import GediDigitalIE
 from .generic import GenericIE
 from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
@@ -422,7 +448,10 @@ from .go import GoIE
 from .godtube import GodTubeIE
 from .golem import GolemIE
 from .googledrive import GoogleDriveIE
-from .googleplus import GooglePlusIE
+from .googlepodcasts import (
+    GooglePodcastsIE,
+    GooglePodcastsFeedIE,
+)
 from .googlesearch import GoogleSearchIE
 from .goshgay import GoshgayIE
 from .gputechconf import GPUTechConfIE
@@ -447,6 +476,7 @@ from .hotstar import (
 )
 from .howcast import HowcastIE
 from .howstuffworks import HowStuffWorksIE
+from .hrfernsehen import HRFernsehenIE
 from .hrti import (
     HRTiIE,
     HRTiPlaylistIE,
@@ -460,8 +490,12 @@ from .hungama import (
 from .hypem import HypemIE
 from .ign import (
     IGNIE,
-    OneUPIE,
-    PCMagIE,
+    IGNVideoIE,
+    IGNArticleIE,
+)
+from .iheart import (
+    IHeartRadioIE,
+    IHeartRadioPodcastIE,
 )
 from .imdb import (
     ImdbIE,
@@ -512,12 +546,16 @@ from .karaoketv import KaraoketvIE
 from .karrierevideos import KarriereVideosIE
 from .keezmovies import KeezMoviesIE
 from .ketnet import KetnetIE
-from .khanacademy import KhanAcademyIE
+from .khanacademy import (
+    KhanAcademyIE,
+    KhanAcademyUnitIE,
+)
 from .kickstarter import KickStarterIE
 from .kinja import KinjaEmbedIE
 from .kinopoisk import KinoPoiskIE
 from .konserthusetplay import KonserthusetPlayIE
 from .krasview import KrasViewIE
+from .kth import KTHIE
 from .ku6 import Ku6IE
 from .kusi import KUSIIE
 from .kuwo import (
@@ -569,7 +607,11 @@ from .limelight import (
     LimelightChannelIE,
     LimelightChannelListIE,
 )
-from .line import LineTVIE
+from .line import (
+    LineTVIE,
+    LineLiveIE,
+    LineLiveChannelIE,
+)
 from .linkedin import (
     LinkedInLearningIE,
     LinkedInLearningCourseIE,
@@ -577,10 +619,6 @@ from .linkedin import (
 from .linuxacademy import LinuxAcademyIE
 from .litv import LiTVIE
 from .livejournal import LiveJournalIE
-from .liveleak import (
-    LiveLeakIE,
-    LiveLeakEmbedIE,
-)
 from .livestream import (
     LivestreamIE,
     LivestreamOriginalIE,
@@ -606,6 +644,7 @@ from .mangomolo import (
     MangomoloLiveIE,
 )
 from .manyvids import ManyVidsIE
+from .maoritv import MaoriTVIE
 from .markiza import (
     MarkizaIE,
     MarkizaPageIE,
@@ -634,6 +673,11 @@ from .microsoftvirtualacademy import (
     MicrosoftVirtualAcademyIE,
     MicrosoftVirtualAcademyCourseIE,
 )
+from .minds import (
+    MindsIE,
+    MindsChannelIE,
+    MindsGroupIE,
+)
 from .ministrygrid import MinistryGridIE
 from .minoto import MinotoIE
 from .miomio import MioMioIE
@@ -644,7 +688,10 @@ from .mixcloud import (
     MixcloudUserIE,
     MixcloudPlaylistIE,
 )
-from .mlb import MLBIE
+from .mlb import (
+    MLBIE,
+    MLBVideoIE,
+)
 from .mnet import MnetIE
 from .moevideo import MoeVideoIE
 from .mofosex import (
@@ -751,7 +798,14 @@ from .nick import (
     NickNightIE,
     NickRuIE,
 )
-from .niconico import NiconicoIE, NiconicoPlaylistIE
+from .niconico import (
+    NiconicoIE,
+    NiconicoPlaylistIE,
+    NiconicoUserIE,
+    NicovideoSearchIE,
+    NicovideoSearchDateIE,
+    NicovideoSearchURLIE,
+)
 from .ninecninemedia import NineCNineMediaIE
 from .ninegag import NineGagIE
 from .ninenow import NineNowIE
@@ -845,11 +899,20 @@ from .packtpub import (
     PacktPubIE,
     PacktPubCourseIE,
 )
+from .palcomp3 import (
+    PalcoMP3IE,
+    PalcoMP3ArtistIE,
+    PalcoMP3VideoIE,
+)
 from .pandoratv import PandoraTVIE
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
 from .pearvideo import PearVideoIE
+from .peekvids import (
+    PeekVidsIE,
+    PlayVidsIE,
+)
 from .peertube import PeerTubeIE
 from .people import PeopleIE
 from .performgroup import PerformGroupIE
@@ -878,6 +941,7 @@ from .platzi import (
 from .playfm import PlayFMIE
 from .playplustv import PlayPlusTVIE
 from .plays import PlaysTVIE
+from .playstuff import PlayStuffIE
 from .playtvak import PlaytvakIE
 from .playvid import PlayvidIE
 from .playwire import PlaywireIE
@@ -1002,6 +1066,7 @@ from .safari import (
     SafariApiIE,
     SafariCourseIE,
 )
+from .samplefocus import SampleFocusIE
 from .sapo import SapoIE
 from .savefrom import SaveFromIE
 from .sbs import SBSIE
@@ -1034,6 +1099,11 @@ from .shared import (
     VivoIE,
 )
 from .showroomlive import ShowRoomLiveIE
+from .simplecast import (
+    SimplecastIE,
+    SimplecastEpisodeIE,
+    SimplecastPodcastIE,
+)
 from .sina import SinaIE
 from .sixplay import SixPlayIE
 from .skyit import (
@@ -1092,10 +1162,17 @@ from .spike import (
     BellatorIE,
     ParamountNetworkIE,
 )
-from .stitcher import StitcherIE
+from .stitcher import (
+    StitcherIE,
+    StitcherShowIE,
+)
 from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
+from .spotify import (
+    SpotifyIE,
+    SpotifyShowIE,
+)
 from .spreaker import (
     SpreakerIE,
     SpreakerPageIE,
@@ -1111,6 +1188,11 @@ from .srgssr import (
 from .srmediathek import SRMediathekIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
+from .storyfire import (
+    StoryFireIE,
+    StoryFireUserIE,
+    StoryFireSeriesIE,
+)
 from .streamable import StreamableIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
@@ -1183,6 +1265,11 @@ from .theweatherchannel import TheWeatherChannelIE
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .thisoldhouse import ThisOldHouseIE
+from .thisvid import (
+    ThisVidIE,
+    ThisVidMemberIE,
+    ThisVidPlaylistIE,
+)
 from .threeqsdn import ThreeQSDNIE
 from .tiktok import (
     TikTokIE,
@@ -1209,6 +1296,10 @@ from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
+from .trovo import (
+    TrovoIE,
+    TrovoVodIE,
+)
 from .trunews import TruNewsIE
 from .trutv import TruTVIE
 from .tube8 import Tube8IE
@@ -1227,6 +1318,7 @@ from .tv2 import (
     TV2IE,
     TV2ArticleIE,
     KatsomoIE,
+    MTVUutisetArticleIE,
 )
 from .tv2dk import (
     TV2DKIE,
@@ -1365,7 +1457,6 @@ from .vidme import (
     VidmeUserIE,
     VidmeUserLikesIE,
 )
-from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
 from .viewlift import (
     ViewLiftIE,
@@ -1425,6 +1516,7 @@ from .vrv import (
     VRVSeriesIE,
 )
 from .vshare import VShareIE
+from .vtm import VTMIE
 from .medialaan import MedialaanIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
@@ -1539,7 +1631,7 @@ from .youtube import (
     YoutubeRecommendedIE,
     YoutubeSearchDateIE,
     YoutubeSearchIE,
-    #YoutubeSearchURLIE,
+    YoutubeSearchURLIE,
     YoutubeSubscriptionsIE,
     YoutubeTruncatedIDIE,
     YoutubeTruncatedURLIE,
@@ -1568,5 +1660,10 @@ from .zattoo import (
     ZattooLiveIE,
 )
 from .zdf import ZDFIE, ZDFChannelIE
-from .zingmp3 import ZingMp3IE
+from .zhihu import ZhihuIE
+from .zingmp3 import (
+    ZingMp3IE,
+    ZingMp3AlbumIE,
+)
+from .zoom import ZoomIE
 from .zype import ZypeIE

youtube_dl/extractor/facebook.py

@@ -521,7 +521,10 @@ class FacebookIE(InfoExtractor):
                 raise ExtractorError(
                     'The video is not available, Facebook said: "%s"' % m_msg.group(1),
                     expected=True)
-            elif '>You must log in to continue' in webpage:
+            elif any(p in webpage for p in (
+                    '>You must log in to continue',
+                    'id="login_form"',
+                    'id="loginbutton"')):
                 self.raise_login_required()
 
         if not video_data and '/watchparty/' in url:

youtube_dl/extractor/formula1.py

@@ -5,29 +5,23 @@ from .common import InfoExtractor
 
 
 class Formula1IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?formula1\.com/(?:content/fom-website/)?en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html'
-    _TESTS = [{
-        'url': 'http://www.formula1.com/content/fom-website/en/video/2016/5/Race_highlights_-_Spain_2016.html',
-        'md5': '8c79e54be72078b26b89e0e111c0502b',
+    _VALID_URL = r'https?://(?:www\.)?formula1\.com/en/latest/video\.[^.]+\.(?P<id>\d+)\.html'
+    _TEST = {
+        'url': 'https://www.formula1.com/en/latest/video.race-highlights-spain-2016.6060988138001.html',
+        'md5': 'be7d3a8c2f804eb2ab2aa5d941c359f8',
         'info_dict': {
-            'id': 'JvYXJpMzE6pArfHWm5ARp5AiUmD-gibV',
+            'id': '6060988138001',
             'ext': 'mp4',
             'title': 'Race highlights - Spain 2016',
+            'timestamp': 1463332814,
+            'upload_date': '20160515',
+            'uploader_id': '6057949432001',
         },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-        'add_ie': ['Ooyala'],
-    }, {
-        'url': 'http://www.formula1.com/en/video/2016/5/Race_highlights_-_Spain_2016.html',
-        'only_matching': True,
-    }]
+        'add_ie': ['BrightcoveNew'],
+    }
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/6057949432001/S1WMrhjlh_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        ooyala_embed_code = self._search_regex(
-            r'data-videoid="([^"]+)"', webpage, 'ooyala embed code')
+        bc_id = self._match_id(url)
         return self.url_result(
-            'ooyala:%s' % ooyala_embed_code, 'Ooyala', ooyala_embed_code)
+            self.BRIGHTCOVE_URL_TEMPLATE % bc_id, 'BrightcoveNew', bc_id)

youtube_dl/extractor/franceculture.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 class FranceCultureIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
         'info_dict': {
             'id': 'rendez-vous-au-pays-des-geeks',
@@ -20,10 +20,14 @@ class FranceCultureIE(InfoExtractor):
             'title': 'Rendez-vous au pays des geeks',
             'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20140301',
-            'timestamp': 1393642916,
+            'timestamp': 1393700400,
             'vcodec': 'none',
         }
-    }
+    }, {
+        # no thumbnail
+        'url': 'https://www.franceculture.fr/emissions/la-recherche-montre-en-main/la-recherche-montre-en-main-du-mercredi-10-octobre-2018',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -36,19 +40,19 @@ class FranceCultureIE(InfoExtractor):
                     </h1>|
                     <div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>
                 ).*?
-                (<button[^>]+data-asset-source="[^"]+"[^>]+>)
+                (<button[^>]+data-(?:url|asset-source)="[^"]+"[^>]+>)
             ''',
             webpage, 'video data'))
 
-        video_url = video_data['data-asset-source']
-        title = video_data.get('data-asset-title') or self._og_search_title(webpage)
+        video_url = video_data.get('data-url') or video_data['data-asset-source']
+        title = video_data.get('data-asset-title') or video_data.get('data-diffusion-title') or self._og_search_title(webpage)
 
         description = self._html_search_regex(
             r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>',
             webpage, 'description', default=None)
         thumbnail = self._search_regex(
             r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"',
-            webpage, 'thumbnail', fatal=False)
+            webpage, 'thumbnail', default=None)
         uploader = self._html_search_regex(
             r'(?s)<span class="author">(.*?)</span>',
             webpage, 'uploader', default=None)
@@ -64,6 +68,6 @@ class FranceCultureIE(InfoExtractor):
             'ext': ext,
             'vcodec': 'none' if ext == 'mp3' else None,
             'uploader': uploader,
-            'timestamp': int_or_none(video_data.get('data-asset-created-date')),
+            'timestamp': int_or_none(video_data.get('data-start-time')) or int_or_none(video_data.get('data-asset-created-date')),
             'duration': int_or_none(video_data.get('data-duration')),
         }

youtube_dl/extractor/francetv.py

@@ -383,6 +383,10 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
     }, {
         'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
         'only_matching': True,
+    }, {
+        # "<figure id=" pattern (#28792)
+        'url': 'https://www.francetvinfo.fr/culture/patrimoine/incendie-de-notre-dame-de-paris/notre-dame-de-paris-de-l-incendie-de-la-cathedrale-a-sa-reconstruction_4372291.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -399,7 +403,8 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
         video_id = self._search_regex(
             (r'player\.load[^;]+src:\s*["\']([^"\']+)',
              r'id-video=([^@]+@[^"]+)',
-             r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
+             r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"',
+             r'(?:data-id|<figure[^<]+\bid)=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'),
             webpage, 'video id')
 
         return self._make_url_result(video_id)

youtube_dl/extractor/fujitv.py

@@ -17,7 +17,7 @@ class FujiTVFODPlus7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         formats = self._extract_m3u8_formats(
-            self._BASE_URL + 'abr/pc_html5/%s.m3u8' % video_id, video_id)
+            self._BASE_URL + 'abr/pc_html5/%s.m3u8' % video_id, video_id, 'mp4')
         for f in formats:
             wh = self._BITRATE_MAP.get(f.get('tbr'))
             if wh:

youtube_dl/extractor/funimation.py

@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class FunimationIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?:[^/]+/)?shows/[^/]+/(?P<id>[^/?#&]+)'
 
     _NETRC_MACHINE = 'funimation'
     _TOKEN = None
@@ -51,6 +51,10 @@ class FunimationIE(InfoExtractor):
     }, {
         'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
         'only_matching': True,
+    }, {
+        # with lang code
+        'url': 'https://www.funimation.com/en/shows/hacksign/role-play/',
+        'only_matching': True,
     }]
 
     def _login(self):

youtube_dl/extractor/gdcvault.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from .kaltura import KalturaIE
 from ..utils import (
     HEADRequest,
+    remove_start,
     sanitized_Request,
     smuggle_url,
     urlencode_postdata,
@@ -102,6 +103,26 @@ class GDCVaultIE(InfoExtractor):
                 'format': 'mp4-408',
             },
         },
+        {
+            # Kaltura embed, whitespace between quote and embedded URL in iframe's src
+            'url': 'https://www.gdcvault.com/play/1025699',
+            'info_dict': {
+                'id': '0_zagynv0a',
+                'ext': 'mp4',
+                'title': 'Tech Toolbox',
+                'upload_date': '20190408',
+                'uploader_id': 'joe@blazestreaming.com',
+                'timestamp': 1554764629,
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            # HTML5 video
+            'url': 'http://www.gdcvault.com/play/1014846/Conference-Keynote-Shigeru',
+            'only_matching': True,
+        },
     ]
 
     def _login(self, webpage_url, display_id):
@@ -175,7 +196,18 @@ class GDCVaultIE(InfoExtractor):
 
             xml_name = self._html_search_regex(
                 r'<iframe src=".*?\?xml(?:=|URL=xml/)(.+?\.xml).*?".*?</iframe>',
-                start_page, 'xml filename')
+                start_page, 'xml filename', default=None)
+            if not xml_name:
+                info = self._parse_html5_media_entries(url, start_page, video_id)[0]
+                info.update({
+                    'title': remove_start(self._search_regex(
+                        r'>Session Name:\s*<.*?>\s*<td>(.+?)</td>', start_page,
+                        'title', default=None) or self._og_search_title(
+                        start_page, default=None), 'GDC Vault - '),
+                    'id': video_id,
+                    'display_id': display_id,
+                })
+                return info
             embed_url = '%s/xml/%s' % (xml_root, xml_name)
             ie_key = 'DigitallySpeaking'
 

youtube_dl/extractor/gedidigital.py

@@ -0,0 +1,161 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+)
+
+
+class GediDigitalIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://video\.
+        (?:
+            (?:
+                (?:espresso\.)?repubblica
+                |lastampa
+                |ilsecoloxix
+            )|
+            (?:
+                iltirreno
+                |messaggeroveneto
+                |ilpiccolo
+                |gazzettadimantova
+                |mattinopadova
+                |laprovinciapavese
+                |tribunatreviso
+                |nuovavenezia
+                |gazzettadimodena
+                |lanuovaferrara
+                |corrierealpi
+                |lasentinella
+            )\.gelocal
+        )\.it(?:/[^/]+){2,3}?/(?P<id>\d+)(?:[/?&#]|$)'''
+    _TESTS = [{
+        'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
+        'md5': '84658d7fb9e55a6e57ecc77b73137494',
+        'info_dict': {
+            'id': '121559',
+            'ext': 'mp4',
+            'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso',
+            'description': 'md5:de7f4d6eaaaf36c153b599b10f8ce7ca',
+            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-full-.+?\.jpg$',
+            'duration': 125,
+        },
+    }, {
+        'url': 'https://video.espresso.repubblica.it/embed/tutti-i-video/01-ted-villa/14772/14870&width=640&height=360',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.iltirreno.gelocal.it/sport/dentro-la-notizia-ferrari-cosa-succede-a-maranello/141059/142723',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.messaggeroveneto.gelocal.it/locale/maria-giovanna-elmi-covid-vaccino/138155/139268',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.ilpiccolo.gelocal.it/dossier/big-john/dinosauro-big-john-al-via-le-visite-guidate-a-trieste/135226/135751',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.gazzettadimantova.gelocal.it/locale/dal-ponte-visconteo-di-valeggio-l-and-8217sos-dei-ristoratori-aprire-anche-a-cena/137310/137818',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.mattinopadova.gelocal.it/dossier/coronavirus-in-veneto/covid-a-vo-un-anno-dopo-un-cuore-tricolore-per-non-dimenticare/138402/138964',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.laprovinciapavese.gelocal.it/locale/mede-zona-rossa-via-alle-vaccinazioni-per-gli-over-80/137545/138120',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.tribunatreviso.gelocal.it/dossier/coronavirus-in-veneto/ecco-le-prima-vaccinazioni-di-massa-nella-marca/134485/135024',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.nuovavenezia.gelocal.it/locale/camion-troppo-alto-per-il-ponte-ferroviario-perde-il-carico/135734/136266',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.gazzettadimodena.gelocal.it/locale/modena-scoperta-la-proteina-che-predice-il-livello-di-gravita-del-covid/139109/139796',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.lanuovaferrara.gelocal.it/locale/due-bombole-di-gpl-aperte-e-abbandonate-i-vigili-bruciano-il-gas/134391/134957',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.corrierealpi.gelocal.it/dossier/cortina-2021-i-mondiali-di-sci-alpino/mondiali-di-sci-il-timelapse-sulla-splendida-olympia/133760/134331',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.lasentinella.gelocal.it/locale/vestigne-centra-un-auto-e-si-ribalta/138931/139466',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.espresso.repubblica.it/tutti-i-video/01-ted-villa/14772',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_meta(
+            ['twitter:title', 'og:title'], webpage, fatal=True)
+        player_data = re.findall(
+            r"PlayerFactory\.setParam\('(?P<type>format|param)',\s*'(?P<name>[^']+)',\s*'(?P<val>[^']+)'\);",
+            webpage)
+
+        formats = []
+        duration = thumb = None
+        for t, n, v in player_data:
+            if t == 'format':
+                if n in ('video-hds-vod-ec', 'video-hls-vod-ec', 'video-viralize', 'video-youtube-pfp'):
+                    continue
+                elif n.endswith('-vod-ak'):
+                    formats.extend(self._extract_akamai_formats(
+                        v, video_id, {'http': 'media.gedidigital.it'}))
+                else:
+                    ext = determine_ext(v)
+                    if ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            v, video_id, 'mp4', 'm3u8_native', m3u8_id=n, fatal=False))
+                        continue
+                    f = {
+                        'format_id': n,
+                        'url': v,
+                    }
+                    if ext == 'mp3':
+                        abr = int_or_none(self._search_regex(
+                            r'-mp3-audio-(\d+)', v, 'abr', default=None))
+                        f.update({
+                            'abr': abr,
+                            'tbr': abr,
+                            'vcodec': 'none'
+                        })
+                    else:
+                        mobj = re.match(r'^video-rrtv-(\d+)(?:-(\d+))?$', n)
+                        if mobj:
+                            f.update({
+                                'height': int(mobj.group(1)),
+                                'vbr': int_or_none(mobj.group(2)),
+                            })
+                        if not f.get('vbr'):
+                            f['vbr'] = int_or_none(self._search_regex(
+                                r'-video-rrtv-(\d+)', v, 'abr', default=None))
+                    formats.append(f)
+            elif t == 'param':
+                if n in ['image_full', 'image']:
+                    thumb = v
+                elif n == 'videoDuration':
+                    duration = int_or_none(v)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta(
+                ['twitter:description', 'og:description', 'description'], webpage),
+            'thumbnail': thumb or self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'duration': duration,
+        }

youtube_dl/extractor/generic.py

@@ -28,6 +28,7 @@ from ..utils import (
     mimetype2ext,
     orderedSet,
     parse_duration,
+    parse_resolution,
     sanitized_Request,
     smuggle_url,
     unescapeHTML,
@@ -35,6 +36,7 @@ from ..utils import (
     unsmuggle_url,
     UnsupportedError,
     url_or_none,
+    urljoin,
     xpath_attr,
     xpath_text,
     xpath_with_ns,
@@ -84,7 +86,6 @@ from .jwplatform import JWPlatformIE
 from .digiteka import DigitekaIE
 from .arkena import ArkenaIE
 from .instagram import InstagramIE
-from .liveleak import LiveLeakIE
 from .threeqsdn import ThreeQSDNIE
 from .theplatform import ThePlatformIE
 from .kaltura import KalturaIE
@@ -126,8 +127,11 @@ from .viqeo import ViqeoIE
 from .expressen import ExpressenIE
 from .zype import ZypeIE
 from .odnoklassniki import OdnoklassnikiIE
+from .vk import VKIE
 from .kinja import KinjaEmbedIE
 from .arcpublishing import ArcPublishingIE
+from .medialaan import MedialaanIE
+from .simplecast import SimplecastIE
 
 
 class GenericIE(InfoExtractor):
@@ -1626,31 +1630,6 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20160409',
             },
         },
-        # LiveLeak embed
-        {
-            'url': 'http://www.wykop.pl/link/3088787/',
-            'md5': '7619da8c820e835bef21a1efa2a0fc71',
-            'info_dict': {
-                'id': '874_1459135191',
-                'ext': 'mp4',
-                'title': 'Man shows poor quality of new apartment building',
-                'description': 'The wall is like a sand pile.',
-                'uploader': 'Lake8737',
-            },
-            'add_ie': [LiveLeakIE.ie_key()],
-        },
-        # Another LiveLeak embed pattern (#13336)
-        {
-            'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
-            'info_dict': {
-                'id': '2eb_1496309988',
-                'ext': 'mp4',
-                'title': 'Thief robs place where everyone was armed',
-                'description': 'md5:694d73ee79e535953cf2488562288eee',
-                'uploader': 'brazilwtf',
-            },
-            'add_ie': [LiveLeakIE.ie_key()],
-        },
         # Duplicated embedded video URLs
         {
             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
@@ -2223,6 +2202,125 @@ class GenericIE(InfoExtractor):
                 'duration': 1581,
             },
         },
+        {
+            # MyChannels SDK embed
+            # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
+            'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
+            'md5': '90c0699c37006ef18e198c032d81739c',
+            'info_dict': {
+                'id': '194165',
+                'ext': 'mp4',
+                'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
+                'timestamp': 1611740340,
+                'upload_date': '20210127',
+                'duration': 159,
+            },
+        },
+        {
+            # Simplecast player embed
+            'url': 'https://www.bio.org/podcast',
+            'info_dict': {
+                'id': 'podcast',
+                'title': 'I AM BIO Podcast | BIO',
+            },
+            'playlist_mincount': 52,
+        },
+        {
+            # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
+            'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
+            'only_matching': True,
+        }, {
+            # KVS Player
+            'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
+            'info_dict': {
+                'id': '105',
+                'display_id': 'kelis-4th-of-july',
+                'ext': 'mp4',
+                'title': 'Kelis - 4th Of July',
+                'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
+            },
+        }, {
+            # KVS Player
+            'url': 'https://www.kvs-demo.com/embed/105/',
+            'info_dict': {
+                'id': '105',
+                'display_id': 'kelis-4th-of-july',
+                'ext': 'mp4',
+                'title': 'Kelis - 4th Of July / Embed Player',
+                'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        }, {
+            # KVS Player (tested also in thisvid.py)
+            'url': 'https://youix.com/video/leningrad-zoj/',
+            'md5': '94f96ba95706dc3880812b27b7d8a2b8',
+            'info_dict': {
+                'id': '18485',
+                'display_id': 'leningrad-zoj',
+                'ext': 'mp4',
+                'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
+                'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
+            },
+        }, {
+            # KVS Player
+            'url': 'https://youix.com/embed/18485',
+            'md5': '94f96ba95706dc3880812b27b7d8a2b8',
+            'info_dict': {
+                'id': '18485',
+                'display_id': 'leningrad-zoj',
+                'ext': 'mp4',
+                'title': 'Ленинград - ЗОЖ',
+                'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
+            },
+        }, {
+            # KVS Player
+            'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
+            'md5': '94166bdb26b4cb1fb9214319a629fc51',
+            'info_dict': {
+                'id': '21217',
+                'display_id': '40-nochey-2016',
+                'ext': 'mp4',
+                'title': '40 ночей (2016) - BogMedia.org',
+                'description': 'md5:4e6d7d622636eb7948275432eb256dc3',
+                'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
+            },
+        }, {
+            # KVS Player (for sites that serve kt_player.js via non-https urls)
+            'url': 'http://www.camhub.world/embed/389508',
+            'md5': 'fbe89af4cfb59c8fd9f34a202bb03e32',
+            'info_dict': {
+                'id': '389508',
+                'display_id': 'syren-de-mer-onlyfans-05-07-2020have-a-happy-safe-holiday5f014e68a220979bdb8cd-source',
+                'ext': 'mp4',
+                'title': 'Syren De Mer  onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер',
+                'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg',
+            },
+        }, {
+            'url': 'https://mrdeepfakes.com/video/5/selena-gomez-pov-deep-fakes',
+            'md5': 'fec4ad5ec150f655e0c74c696a4a2ff4',
+            'info_dict': {
+                'id': '5',
+                'display_id': 'selena-gomez-pov-deep-fakes',
+                'ext': 'mp4',
+                'title': 'Selena Gomez POV (Deep Fakes) DeepFake Porn - MrDeepFakes',
+                'description': 'md5:17d1f84b578c9c26875ac5ef9a932354',
+                'height': 720,
+                'age_limit': 18,
+            },
+        }, {
+            'url': 'https://shooshtime.com/videos/284002/just-out-of-the-shower-joi/',
+            'md5': 'e2f0a4c329f7986280b7328e24036d60',
+            'info_dict': {
+                'id': '284002',
+                'display_id': 'just-out-of-the-shower-joi',
+                'ext': 'mp4',
+                'title': 'Just Out Of The Shower JOI - Shooshtime',
+                'height': 720,
+                'age_limit': 18,
+            },
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -2327,6 +2425,88 @@ class GenericIE(InfoExtractor):
             'title': title,
         }
 
+    def _extract_kvs(self, url, webpage, video_id):
+
+        def getlicensetoken(license):
+            modlicense = license.replace('$', '').replace('0', '1')
+            center = int(len(modlicense) / 2)
+            fronthalf = int(modlicense[:center + 1])
+            backhalf = int(modlicense[center:])
+
+            modlicense = compat_str(4 * abs(fronthalf - backhalf))
+
+            def parts():
+                for o in range(0, center + 1):
+                    for i in range(1, 5):
+                        yield compat_str((int(license[o + i]) + int(modlicense[o])) % 10)
+
+            return ''.join(parts())
+
+        def getrealurl(video_url, license_code):
+            if not video_url.startswith('function/0/'):
+                return video_url  # not obfuscated
+
+            url_path, _, url_query = video_url.partition('?')
+            urlparts = url_path.split('/')[2:]
+            license = getlicensetoken(license_code)
+            newmagic = urlparts[5][:32]
+
+            def spells(x, o):
+                l = (o + sum(int(n) for n in license[o:])) % 32
+                for i in range(0, len(x)):
+                    yield {l: x[o], o: x[l]}.get(i, x[i])
+
+            for o in range(len(newmagic) - 1, -1, -1):
+                newmagic = ''.join(spells(newmagic, o))
+
+            urlparts[5] = newmagic + urlparts[5][32:]
+            return '/'.join(urlparts) + '?' + url_query
+
+        flashvars = self._search_regex(
+            r'(?s)<script\b[^>]*>.*?var\s+flashvars\s*=\s*(\{.+?\});.*?</script>',
+            webpage, 'flashvars')
+        flashvars = self._parse_json(flashvars, video_id, transform_source=js_to_json)
+
+        # extract the part after the last / as the display_id from the
+        # canonical URL.
+        display_id = self._search_regex(
+            r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
+            r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
+            webpage, 'display_id', fatal=False
+        )
+        title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
+
+        thumbnail = flashvars['preview_url']
+        if thumbnail.startswith('//'):
+            protocol, _, _ = url.partition('/')
+            thumbnail = protocol + thumbnail
+
+        url_keys = list(filter(re.compile(r'^video_(?:url|alt_url\d*)$').match, flashvars.keys()))
+        formats = []
+        for key in url_keys:
+            if '/get_file/' not in flashvars[key]:
+                continue
+            format_id = flashvars.get(key + '_text', key)
+            formats.append(merge_dicts(
+                parse_resolution(format_id) or parse_resolution(flashvars[key]), {
+                    'url': urljoin(url, getrealurl(flashvars[key], flashvars['license_code'])),
+                    'format_id': format_id,
+                    'ext': 'mp4',
+                    'http_headers': {'Referer': url},
+                }))
+            if not formats[-1].get('height'):
+                formats[-1]['quality'] = 1
+
+        self._sort_formats(formats)
+
+        return {
+            'id': flashvars['video_id'],
+            'display_id': display_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }
+
     def _real_extract(self, url):
         if url.startswith('//'):
             return self.url_result(self.http_scheme() + url)
@@ -2462,6 +2642,9 @@ class GenericIE(InfoExtractor):
         webpage = self._webpage_read_content(
             full_response, url, video_id, prefix=first_bytes)
 
+        if '<title>DPG Media Privacy Gate</title>' in webpage:
+            webpage = self._download_webpage(url, video_id)
+
         self.report_extraction(video_id)
 
         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
@@ -2532,9 +2715,16 @@ class GenericIE(InfoExtractor):
         # but actually don't.
         AGE_LIMIT_MARKERS = [
             r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
+            r'>[^<]*you acknowledge you are at least (\d+) years old',
+            r'>\s*(?:18\s+U(?:\.S\.C\.|SC)\s+)?(?:§+\s*)?2257\b',
         ]
-        if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
-            age_limit = 18
+        for marker in AGE_LIMIT_MARKERS:
+            m = re.search(marker, webpage)
+            if not m:
+                continue
+            age_limit = max(
+                age_limit or 0,
+                int_or_none(m.groups() and m.group(1), default=18))
 
         # video uploader is domain name
         video_uploader = self._search_regex(
@@ -2593,6 +2783,11 @@ class GenericIE(InfoExtractor):
         if arc_urls:
             return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
 
+        mychannels_urls = MedialaanIE._extract_urls(webpage)
+        if mychannels_urls:
+            return self.playlist_from_matches(
+                mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
+
         # Look for embedded rtl.nl player
         matches = re.findall(
             r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
@@ -2744,6 +2939,11 @@ class GenericIE(InfoExtractor):
         if odnoklassniki_url:
             return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
 
+        # Look for sibnet embedded player
+        sibnet_urls = VKIE._extract_sibnet_urls(webpage)
+        if sibnet_urls:
+            return self.playlist_from_matches(sibnet_urls, video_id, video_title)
+
         # Look for embedded ivi player
         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
         if mobj is not None:
@@ -2769,6 +2969,12 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
 
+        # Look for Simplecast embeds
+        simplecast_urls = SimplecastIE._extract_urls(webpage)
+        if simplecast_urls:
+            return self.playlist_from_matches(
+                simplecast_urls, video_id, video_title)
+
         # Look for BBC iPlayer embed
         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
         if matches:
@@ -2914,7 +3120,7 @@ class GenericIE(InfoExtractor):
             webpage)
         if not mobj:
             mobj = re.search(
-                r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
+                r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
                 webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'MLB')
@@ -3129,11 +3335,6 @@ class GenericIE(InfoExtractor):
             return self.url_result(
                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
 
-        # Look for LiveLeak embeds
-        liveleak_urls = LiveLeakIE._extract_urls(webpage)
-        if liveleak_urls:
-            return self.playlist_from_matches(liveleak_urls, video_id, video_title)
-
         # Look for 3Q SDN embeds
         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
         if threeqsdn_url:
@@ -3361,12 +3562,29 @@ class GenericIE(InfoExtractor):
                         'url': src,
                         'ext': (mimetype2ext(src_type)
                                 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
+                        'http_headers': {
+                            'Referer': full_response.geturl(),
+                        },
                     })
             if formats:
                 self._sort_formats(formats)
                 info_dict['formats'] = formats
                 return info_dict
 
+        # Look for generic KVS player (before ld+json for tests)
+        found = self._search_regex(
+            (r'<script\b[^>]+?\bsrc\s*=\s*(["\'])https?://(?:\S+?/)+kt_player\.js\?v=(?P<ver>\d+(?:\.\d+)+)\1[^>]*>',
+             # kt_player('kt_player', 'https://i.shoosh.co/player/kt_player.swf?v=5.5.1', ...
+             r'kt_player\s*\(\s*(["\'])(?:(?!\1)[\w\W])+\1\s*,\s*(["\'])https?://(?:\S+?/)+kt_player\.swf\?v=(?P<ver>\d+(?:\.\d+)+)\2\s*,',
+             ), webpage, 'KVS player', group='ver', default=False)
+        if found:
+            self.report_extraction('%s: KVS Player' % (video_id, ))
+            if found.split('.')[0] not in ('4', '5', '6'):
+                self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found, ))
+            return merge_dicts(
+                self._extract_kvs(url, webpage, video_id),
+                info_dict)
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')
@@ -3429,7 +3647,7 @@ class GenericIE(InfoExtractor):
             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
-                found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
+                found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
         if not found:
             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
             found = re.search(