release 2019.03.09

[ci skip]

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.17*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.17**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.03.09*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.03.09**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [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 2018.12.17
+[debug] youtube-dl version 2019.03.09
 [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: {}

.travis.yml

@@ -9,7 +9,6 @@ python:
   - "3.6"
   - "pypy"
   - "pypy3"
-sudo: false
 env:
   - YTDL_TEST_SET=core
   - YTDL_TEST_SET=download

CONTRIBUTING.md

@@ -153,15 +153,19 @@ 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/rg3/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/rg3/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/rg3/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://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
-9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
+8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart):
+
+        $ flake8 youtube_dl/extractor/yourextractor.py
+
+9. Make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
+10. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/extractors.py
         $ git add youtube_dl/extractor/yourextractor.py
         $ git commit -m '[yourextractor] Add new extractor'
         $ git push origin yourextractor
 
-10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
+11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
 
 In any case, thank you very much for your contributions!
 
@@ -257,11 +261,33 @@ title = meta.get('title') or self._og_search_title(webpage)
 
 This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`.
 
-### Make regular expressions flexible
+### Regular expressions
 
-When using regular expressions try to write them fuzzy and flexible.
+#### Don't capture groups you don't use
+
+Capturing group must be an indication that it's used somewhere in the code. Any group that is not used must be non capturing.
+
+##### Example
+
+Don't capture id attribute name here since you can't use it for anything anyway.
+
+Correct:
+
+```python
+r'(?:id|ID)=(?P<id>\d+)'
+```
+
+Incorrect:
+```python
+r'(id|ID)=(?P<id>\d+)'
+```
+
+
+#### Make regular expressions relaxed and flexible
+
+When using regular expressions try to write them fuzzy, relaxed and flexible, skipping insignificant parts that are more likely to change, allowing both single and double quotes for quoted values and so on.
  
-#### Example
+##### Example
 
 Say you need to extract `title` from the following HTML code:
 
@@ -294,7 +320,26 @@ title = self._search_regex(
     webpage, 'title', group='title')
 ```
 
-### Use safe conversion functions
+### Long lines policy
+
+There is a soft limit to keep lines of code under 80 characters long. This means it should be respected if possible and if it does not make readability and code maintenance worse.
+
+For example, you should **never** split long string literals like URLs or some other often copied entities over multiple lines to fit this limit:
+
+Correct:
+
+```python
+'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4'
+```
+
+Incorrect:
+
+```python
+'https://www.youtube.com/watch?v=FqZTN594JQw&list='
+'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4'
+```
+
+### Use convenience conversion and parsing functions
 
 Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
 
@@ -302,6 +347,8 @@ Use `url_or_none` for safe URL processing.
 
 Use `try_get` for safe metadata extraction from parsed JSON.
 
+Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. 
+
 Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions.
 
 #### More examples

ChangeLog

@@ -1,3 +1,267 @@
+version 2019.03.09
+
+Core
+* [extractor/common] Use compat_etree_Element
++ [compat] Introduce compat_etree_Element
+* [extractor/common] Fallback url to base URL for DASH formats
+* [extractor/common] Do not fail on invalid data while parsing F4M manifest
+  in non fatal mode
+* [extractor/common] Return MPD manifest as format's url meta field (#20242)
+* [utils] Strip #HttpOnly_ prefix from cookies files (#20219)
+
+Extractors
+* [francetv:site] Relax video id regular expression (#20268)
+* [toutv] Detect invalid login error
+* [toutv] Fix authentication (#20261)
++ [urplay] Extract timestamp (#20235)
++ [openload] Add support for oload.space (#20246)
+* [facebook] Improve uploader extraction (#20250)
+* [bbc] Use compat_etree_Element
+* [crunchyroll] Use compat_etree_Element
+* [npo] Improve ISM extraction
+* [rai] Improve extraction (#20253)
+* [paramountnetwork] Fix mgid extraction (#20241)
+* [libsyn] Improve extraction (#20229)
++ [youtube] Add more invidious instances to URL regular expression (#20228)
+* [spankbang] Fix extraction (#20023)
+* [espn] Extend URL regular expression (#20013)
+* [sixplay] Handle videos with empty assets (#20016)
++ [vimeo] Add support for Vimeo Pro portfolio protected videos (#20070)
+
+
+version 2019.03.01
+
+Core
++ [downloader/external] Add support for rate limit and retries for wget
+* [downloader/external] Fix infinite retries for curl (#19303)
+
+Extractors
+* [npo] Fix extraction (#20084)
+* [francetv:site] Extend video id regex (#20029, #20071)
++ [periscope] Extract width and height (#20015)
+* [servus] Fix extraction (#19297)
+* [bbccouk] Make subtitles non fatal (#19651)
+* [metacafe] Fix family filter bypass (#19287)
+
+
+version 2019.02.18
+
+Extractors
+* [tvp:website] Fix and improve extraction
++ [tvp] Detect unavailable videos
+* [tvp] Fix description extraction and make thumbnail optional
++ [linuxacademy] Add support for linuxacademy.com (#12207)
+* [bilibili] Update keys (#19233)
+* [udemy] Extend URL regular expressions (#14330, #15883)
+* [udemy] Update User-Agent and detect captcha (#14713, #15839, #18126)
+* [noovo] Fix extraction (#19230)
+* [rai] Relax URL regular expression (#19232)
++ [vshare] Pass Referer to download request (#19205, #19221)
++ [openload] Add support for oload.live (#19222)
+* [imgur] Use video id as title fallback (#18590)
++ [twitch] Add new source format detection approach (#19193)
+* [tvplayhome] Fix video id extraction (#19190)
+* [tvplayhome] Fix episode metadata extraction (#19190)
+* [rutube:embed] Fix extraction (#19163)
++ [rutube:embed] Add support private videos (#19163)
++ [soundcloud] Extract more metadata
++ [trunews] Add support for trunews.com (#19153)
++ [linkedin:learning] Extract chapter_number and chapter_id (#19162)
+
+
+version 2019.02.08
+
+Core
+* [utils] Improve JSON-LD regular expression (#18058)
+* [YoutubeDL] Fallback to ie_key of matching extractor while making
+  download archive id when no explicit ie_key is provided (#19022)
+
+Extractors
++ [malltv] Add support for mall.tv (#18058, #17856)
++ [spankbang:playlist] Add support for playlists (#19145)
+* [spankbang] Extend URL regular expression
+* [trutv] Fix extraction (#17336)
+* [toutv] Fix authentication (#16398, #18700)
+* [pornhub] Fix tags and categories extraction (#13720, #19135)
+* [pornhd] Fix formats extraction
++ [pornhd] Extract like count (#19123, #19125)
+* [radiocanada] Switch to the new media requests (#19115)
++ [teachable] Add support for courses.workitdaily.com (#18871)
+- [vporn] Remove extractor (#16276)
++ [soundcloud:pagedplaylist] Add ie and title to entries (#19022, #19086)
++ [drtuber] Extract duration (#19078)
+* [soundcloud] Fix paged playlists extraction, add support for albums and update client id
+* [soundcloud] Update client id
+* [drtv] Improve preference (#19079)
++ [openload] Add support for openload.pw and oload.pw (#18930)
++ [openload] Add support for oload.info (#19073)
+* [crackle] Authorize media detail request (#16931)
+
+
+version 2019.01.30.1
+
+Core
+* [postprocessor/ffmpeg] Fix avconv processing broken in #19025 (#19067)
+
+
+version 2019.01.30
+
+Core
+* [postprocessor/ffmpeg] Do not copy Apple TV chapter tracks while embedding
+  subtitles (#19024, #19042)
+* [postprocessor/ffmpeg] Disable "Last message repeated" messages (#19025)
+
+Extractors
+* [yourporn] Fix extraction and extract duration (#18815, #18852, #19061)
+* [drtv] Improve extraction (#19039)
+    + Add support for EncryptedUri videos
+    + Extract more metadata
+    * Fix subtitles extraction
++ [fox] Add support for locked videos using cookies (#19060)
+* [fox] Fix extraction for free videos (#19060)
++ [zattoo] Add support for tv.salt.ch (#19059)
+
+
+version 2019.01.27
+
+Core
++ [extractor/common] Extract season in _json_ld
+* [postprocessor/ffmpeg] Fallback to ffmpeg/avconv for audio codec detection
+  (#681)
+
+Extractors
+* [vice] Fix extraction for locked videos (#16248)
++ [wakanim] Detect DRM protected videos
++ [wakanim] Add support for wakanim.tv (#14374)
+* [usatoday] Fix extraction for videos with custom brightcove partner id
+  (#18990)
+* [drtv] Fix extraction (#18989)
+* [nhk] Extend URL regular expression (#18968)
+* [go] Fix Adobe Pass requests for Disney Now (#18901)
++ [openload] Add support for oload.club (#18969)
+
+
+version 2019.01.24
+
+Core
+* [YoutubeDL] Fix negation for string operators in format selection (#18961)
+
+
+version 2019.01.23
+
+Core
+* [utils] Fix urljoin for paths with non-http(s) schemes
+* [extractor/common] Improve jwplayer relative URL handling (#18892)
++ [YoutubeDL] Add negation support for string comparisons in format selection
+  expressions (#18600, #18805)
+* [extractor/common] Improve HLS video-only format detection (#18923)
+
+Extractors
+* [crunchyroll] Extend URL regular expression (#18955)
+* [pornhub] Bypass scrape detection (#4822, #5930, #7074, #10175, #12722,
+  #17197, #18338 #18842, #18899)
++ [vrv] Add support for authentication (#14307)
+* [videomore:season] Fix extraction
+* [videomore] Improve extraction (#18908)
++ [tnaflix] Pass Referer in metadata request (#18925)
+* [radiocanada] Relax DRM check (#18608, #18609)
+* [vimeo] Fix video password verification for videos protected by
+  Referer HTTP header
++ [hketv] Add support for hkedcity.net (#18696)
++ [streamango] Add support for fruithosts.net (#18710)
++ [instagram] Add support for tags (#18757)
++ [odnoklassniki] Detect paid videos (#18876)
+* [ted] Correct acodec for HTTP formats (#18923)
+* [cartoonnetwork] Fix extraction (#15664, #17224)
+* [vimeo] Fix extraction for password protected player URLs (#18889)
+
+
+version 2019.01.17
+
+Extractors
+* [youtube] Extend JS player signature function name regular expressions
+  (#18890, #18891, #18893)
+
+
+version 2019.01.16
+
+Core
++ [test/helper] Add support for maxcount and count collection len checkers
+* [downloader/hls] Fix uplynk ad skipping (#18824)
+* [postprocessor/ffmpeg] Improve ffmpeg version parsing (#18813)
+
+Extractors
+* [youtube] Skip unsupported adaptive stream type (#18804)
++ [youtube] Extract DASH formats from player response (#18804)
+* [funimation] Fix extraction (#14089)
+* [skylinewebcams] Fix extraction (#18853)
++ [curiositystream] Add support for non app URLs
++ [bitchute] Check formats (#18833)
+* [wistia] Extend URL regular expression (#18823)
++ [playplustv] Add support for playplus.com (#18789)
+
+
+version 2019.01.10
+
+Core
+* [extractor/common] Use episode name as title in _json_ld
++ [extractor/common] Add support for movies in _json_ld
+* [postprocessor/ffmpeg] Embed subtitles with non-standard language codes
+  (#18765)
++ [utils] Add language codes replaced in 1989 revision of ISO 639
+  to ISO639Utils (#18765)
+
+Extractors
+* [youtube] Extract live HLS URL from player response (#18799)
++ [outsidetv] Add support for outsidetv.com (#18774)
+* [jwplatform] Use JW Platform Delivery API V2 and add support for more URLs
++ [fox] Add support National Geographic (#17985, #15333, #14698)
++ [playplustv] Add support for playplus.tv (#18789)
+* [globo] Set GLBID cookie manually (#17346)
++ [gaia] Add support for gaia.com (#14605)
+* [youporn] Fix title and description extraction (#18748)
++ [hungama] Add support for hungama.com (#17402, #18771)
+* [dtube] Fix extraction (#18741)
+* [tvnow] Fix and rework extractors and prepare for a switch to the new API
+  (#17245, #18499)
+* [carambatv:page] Fix extraction (#18739)
+
+
+version 2019.01.02
+
+Extractors
+* [discovery] Use geo verification headers (#17838)
++ [packtpub] Add support for subscription.packtpub.com (#18718)
+* [yourporn] Fix extraction (#18583)
++ [acast:channel] Add support for play.acast.com (#18587)
++ [extractors] Add missing age limits (#18621)
++ [rmcdecouverte] Add support for live stream
+* [rmcdecouverte] Bypass geo restriction
+* [rmcdecouverte] Update URL regular expression (#18595, 18697)
+* [manyvids] Fix extraction (#18604, #18614)
+* [bitchute] Fix extraction (#18567)
+
+
+version 2018.12.31
+
+Extractors
++ [bbc] Add support for another embed pattern (#18643)
++ [npo:live] Add support for npostart.nl (#18644)
+* [beeg] Fix extraction (#18610, #18626)
+* [youtube] Unescape HTML for series (#18641)
++ [youtube] Extract more format metadata
+* [youtube] Detect DRM protected videos (#1774)
+* [youtube] Relax HTML5 player regular expressions (#18465, #18466)
+* [youtube] Extend HTML5 player regular expression (#17516)
++ [liveleak] Add support for another embed type and restore original
+  format extraction
++ [crackle] Extract ISM and HTTP formats
++ [twitter] Pass Referer with card request (#18579)
+* [mediasite] Extend URL regular expression (#18558)
++ [lecturio] Add support for lecturio.de (#18562)
++ [discovery] Add support for Scripps Networks watch domains (#17947)
+
+
 version 2018.12.17
 
 Extractors

README.md

@@ -496,7 +496,7 @@ The `-o` option allows users to indicate a template for the output file names.
 
 **tl;dr:** [navigate me to examples](#output-template-examples).
 
-The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are:
+The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Allowed names along with sequence type are:
 
  - `id` (string): Video identifier
  - `title` (string): Video title
@@ -667,7 +667,7 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `
  - `asr`: Audio sampling rate in Hertz
  - `fps`: Frame rate
 
-Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begins with), `$=` (ends with), `*=` (contains) and following string meta fields:
+Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields:
  - `ext`: File extension
  - `acodec`: Name of the audio codec in use
  - `vcodec`: Name of the video codec in use
@@ -675,6 +675,8 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin
  - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`)
  - `format_id`: A short description of the format
 
+Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain).
+
 Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster.
 
 Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s.
@@ -1025,15 +1027,19 @@ 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/rg3/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/rg3/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/rg3/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://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
-9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
+8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart):
+
+        $ flake8 youtube_dl/extractor/yourextractor.py
+
+9. Make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
+10. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/extractors.py
         $ git add youtube_dl/extractor/yourextractor.py
         $ git commit -m '[yourextractor] Add new extractor'
         $ git push origin yourextractor
 
-10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
+11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
 
 In any case, thank you very much for your contributions!
 
@@ -1129,11 +1135,33 @@ title = meta.get('title') or self._og_search_title(webpage)
 
 This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`.
 
-### Make regular expressions flexible
+### Regular expressions
 
-When using regular expressions try to write them fuzzy and flexible.
+#### Don't capture groups you don't use
+
+Capturing group must be an indication that it's used somewhere in the code. Any group that is not used must be non capturing.
+
+##### Example
+
+Don't capture id attribute name here since you can't use it for anything anyway.
+
+Correct:
+
+```python
+r'(?:id|ID)=(?P<id>\d+)'
+```
+
+Incorrect:
+```python
+r'(id|ID)=(?P<id>\d+)'
+```
+
+
+#### Make regular expressions relaxed and flexible
+
+When using regular expressions try to write them fuzzy, relaxed and flexible, skipping insignificant parts that are more likely to change, allowing both single and double quotes for quoted values and so on.
  
-#### Example
+##### Example
 
 Say you need to extract `title` from the following HTML code:
 
@@ -1166,7 +1194,26 @@ title = self._search_regex(
     webpage, 'title', group='title')
 ```
 
-### Use safe conversion functions
+### Long lines policy
+
+There is a soft limit to keep lines of code under 80 characters long. This means it should be respected if possible and if it does not make readability and code maintenance worse.
+
+For example, you should **never** split long string literals like URLs or some other often copied entities over multiple lines to fit this limit:
+
+Correct:
+
+```python
+'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4'
+```
+
+Incorrect:
+
+```python
+'https://www.youtube.com/watch?v=FqZTN594JQw&list='
+'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4'
+```
+
+### Use convenience conversion and parsing functions
 
 Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
 
@@ -1174,6 +1221,8 @@ Use `url_or_none` for safe URL processing.
 
 Use `try_get` for safe metadata extraction from parsed JSON.
 
+Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. 
+
 Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions.
 
 #### More examples

docs/supportedsites.md

@@ -320,6 +320,7 @@
  - **Fusion**
  - **Fux**
  - **FXNetworks**
+ - **Gaia**
  - **GameInformer**
  - **GameOne**
  - **gameone:playlist**
@@ -360,6 +361,7 @@
  - **hitbox**
  - **hitbox:live**
  - **HitRecord**
+ - **hketv**: 香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau
  - **HornBunny**
  - **HotNewHipHop**
  - **hotstar**
@@ -370,6 +372,8 @@
  - **HRTiPlaylist**
  - **Huajiao**: 花椒直播
  - **HuffPost**: Huffington Post
+ - **Hungama**
+ - **HungamaSong**
  - **Hypem**
  - **Iconosquare**
  - **ign.com**
@@ -383,6 +387,7 @@
  - **IndavideoEmbed**
  - **InfoQ**
  - **Instagram**
+ - **instagram:tag**: Instagram hashtag search
  - **instagram:user**: Instagram user profile
  - **Internazionale**
  - **InternetVideoArchive**
@@ -438,6 +443,7 @@
  - **Lecture2Go**
  - **Lecturio**
  - **LecturioCourse**
+ - **LecturioDeCourse**
  - **LEGO**
  - **Lemonde**
  - **Lenta**
@@ -452,6 +458,7 @@
  - **LineTV**
  - **linkedin:learning**
  - **linkedin:learning:course**
+ - **LinuxAcademy**
  - **LiTV**
  - **LiveLeak**
  - **LiveLeakEmbed**
@@ -470,6 +477,7 @@
  - **mailru:music**: Музыка@Mail.Ru
  - **mailru:music:search**: Музыка@Mail.Ru
  - **MakerTV**
+ - **MallTV**
  - **mangomolo:live**
  - **mangomolo:video**
  - **ManyVids**
@@ -539,9 +547,8 @@
  - **MyviEmbed**
  - **MyVisionTV**
  - **n-tv.de**
- - **natgeo**
- - **natgeo:episodeguide**
  - **natgeo:video**
+ - **NationalGeographicTV**
  - **Naver**
  - **NBA**
  - **NBC**
@@ -641,6 +648,7 @@
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
  - **OsnatelTV**
+ - **OutsideTV**
  - **PacktPub**
  - **PacktPubCourse**
  - **PandaTV**: 熊猫TV
@@ -665,6 +673,7 @@
  - **Pinkbike**
  - **Pladform**
  - **play.fm**
+ - **PlayPlusTV**
  - **PlaysTV**
  - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
  - **Playvid**
@@ -770,6 +779,7 @@
  - **safari:api**
  - **safari:course**: safaribooksonline.com online courses
  - **SAKTV**
+ - **SaltTV**
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
  - **SBS**: sbs.com.au
@@ -819,6 +829,7 @@
  - **southpark.nl**
  - **southparkstudios.dk**
  - **SpankBang**
+ - **SpankBangPlaylist**
  - **Spankwire**
  - **Spiegel**
  - **Spiegel:Article**: Articles on spiegel.de
@@ -905,6 +916,7 @@
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
+ - **TruNews**
  - **TruTV**
  - **Tube8**
  - **TubiTv**
@@ -933,7 +945,9 @@
  - **TVNet**
  - **TVNoe**
  - **TVNow**
- - **TVNowList**
+ - **TVNowAnnual**
+ - **TVNowNew**
+ - **TVNowSeason**
  - **TVNowShow**
  - **tvp**: Telewizja Polska
  - **tvp:embed**: Telewizja Polska
@@ -1047,7 +1061,6 @@
  - **Voot**
  - **VoxMedia**
  - **VoxMediaVolume**
- - **Vporn**
  - **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
  - **Vrak**
  - **VRT**: deredactie.be, sporza.be, cobra.be and cobra.canvas.be
@@ -1061,6 +1074,7 @@
  - **VVVVID**
  - **VyboryMos**
  - **Vzaar**
+ - **Wakanim**
  - **Walla**
  - **WalyTV**
  - **washingtonpost**

test/helper.py

@@ -153,15 +153,27 @@ def expect_value(self, got, expected, field):
                 isinstance(got, compat_str),
                 'Expected field %s to be a unicode object, but got value %r of type %r' % (field, got, type(got)))
             got = 'md5:' + md5(got)
-        elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
+        elif isinstance(expected, compat_str) and re.match(r'^(?:min|max)?count:\d+', expected):
             self.assertTrue(
                 isinstance(got, (list, dict)),
                 'Expected field %s to be a list or a dict, but it is of type %s' % (
                     field, type(got).__name__))
-            expected_num = int(expected.partition(':')[2])
-            assertGreaterEqual(
+            op, _, expected_num = expected.partition(':')
+            expected_num = int(expected_num)
+            if op == 'mincount':
+                assert_func = assertGreaterEqual
+                msg_tmpl = 'Expected %d items in field %s, but only got %d'
+            elif op == 'maxcount':
+                assert_func = assertLessEqual
+                msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
+            elif op == 'count':
+                assert_func = assertEqual
+                msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
+            else:
+                assert False
+            assert_func(
                 self, len(got), expected_num,
-                'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got)))
+                msg_tmpl % (expected_num, field, len(got)))
             return
         self.assertEqual(
             expected, got,
@@ -237,6 +249,20 @@ def assertGreaterEqual(self, got, expected, msg=None):
         self.assertTrue(got >= expected, msg)
 
 
+def assertLessEqual(self, got, expected, msg=None):
+    if not (got <= expected):
+        if msg is None:
+            msg = '%r not less than or equal to %r' % (got, expected)
+        self.assertTrue(got <= expected, msg)
+
+
+def assertEqual(self, got, expected, msg=None):
+    if not (got == expected):
+        if msg is None:
+            msg = '%r not equal to %r' % (got, expected)
+        self.assertTrue(got == expected, msg)
+
+
 def expect_warnings(ydl, warnings_re):
     real_warning = ydl.report_warning
 

test/test_InfoExtractor.py

@@ -61,6 +61,7 @@ class TestInfoExtractor(unittest.TestCase):
             <meta content='Foo' property=og:foobar>
             <meta name="og:test1" content='foo > < bar'/>
             <meta name="og:test2" content="foo >//< bar"/>
+            <meta property=og-test3 content='Ill-formatted opengraph'/>
             '''
         self.assertEqual(ie._og_search_title(html), 'Foo')
         self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
@@ -69,6 +70,7 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
         self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
         self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
+        self.assertEqual(ie._og_search_property('test3', html), 'Ill-formatted opengraph')
         self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar')
         self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True)
         self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True)
@@ -497,7 +499,64 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'width': 1280,
                     'height': 720,
                 }]
-            )
+            ),
+            (
+                # https://github.com/rg3/youtube-dl/issues/18923
+                # https://www.ted.com/talks/boris_hesser_a_grassroots_healthcare_revolution_in_africa
+                'ted_18923',
+                'http://hls.ted.com/talks/31241.m3u8',
+                [{
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '600k-Audio',
+                    'vcodec': 'none',
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '68',
+                    'vcodec': 'none',
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '163',
+                    'acodec': 'none',
+                    'width': 320,
+                    'height': 180,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '481',
+                    'acodec': 'none',
+                    'width': 512,
+                    'height': 288,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '769',
+                    'acodec': 'none',
+                    'width': 512,
+                    'height': 288,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '984',
+                    'acodec': 'none',
+                    'width': 512,
+                    'height': 288,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '1255',
+                    'acodec': 'none',
+                    'width': 640,
+                    'height': 360,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '1693',
+                    'acodec': 'none',
+                    'width': 853,
+                    'height': 480,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '2462',
+                    'acodec': 'none',
+                    'width': 1280,
+                    'height': 720,
+                }]
+            ),
         ]
 
         for m3u8_file, m3u8_url, expected_formats in _TEST_CASES:

test/test_YoutubeDL.py

@@ -239,6 +239,76 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
 
+    def test_format_selection_string_ops(self):
+        formats = [
+            {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL},
+            {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL},
+        ]
+        info_dict = _make_result(formats)
+
+        # equals (=)
+        ydl = YDL({'format': '[format_id=abc-cba]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+        # does not equal (!=)
+        ydl = YDL({'format': '[format_id!=abc-cba]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+        ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+        # starts with (^=)
+        ydl = YDL({'format': '[format_id^=abc]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+        # does not start with (!^=)
+        ydl = YDL({'format': '[format_id!^=abc]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+        ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+        # ends with ($=)
+        ydl = YDL({'format': '[format_id$=cba]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+        # does not end with (!$=)
+        ydl = YDL({'format': '[format_id!$=cba]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+        ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+        # contains (*=)
+        ydl = YDL({'format': '[format_id*=bc-cb]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+        # does not contain (!*=)
+        ydl = YDL({'format': '[format_id!*=bc-cb]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+        ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+        ydl = YDL({'format': '[format_id!*=-]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
     def test_youtube_format_selection(self):
         order = [
             '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',

test/test_YoutubeDLCookieJar.py

@@ -29,6 +29,16 @@ class TestYoutubeDLCookieJar(unittest.TestCase):
             tf.close()
             os.remove(tf.name)
 
+    def test_strip_httponly_prefix(self):
+        cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/httponly_cookies.txt')
+        cookiejar.load(ignore_discard=True, ignore_expires=True)
+
+        def assert_cookie_has_value(key):
+            self.assertEqual(cookiejar._cookies['www.foobar.foobar']['/'][key].value, key + '_VALUE')
+
+        assert_cookie_has_value('HTTPONLY_COOKIE')
+        assert_cookie_has_value('JS_ACCESSIBLE_COOKIE')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_compat.py

@@ -13,6 +13,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from youtube_dl.compat import (
     compat_getenv,
     compat_setenv,
+    compat_etree_Element,
     compat_etree_fromstring,
     compat_expanduser,
     compat_shlex_split,
@@ -90,6 +91,12 @@ class TestCompat(unittest.TestCase):
         self.assertEqual(compat_shlex_split('-option "one\ntwo" \n -flag'), ['-option', 'one\ntwo', '-flag'])
         self.assertEqual(compat_shlex_split('-val 中文'), ['-val', '中文'])
 
+    def test_compat_etree_Element(self):
+        try:
+            compat_etree_Element.items
+        except AttributeError:
+            self.fail('compat_etree_Element is not a type')
+
     def test_compat_etree_fromstring(self):
         xml = '''
             <root foo="bar" spam="中文">

test/test_utils.py

@@ -507,6 +507,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(urljoin('http://foo.de/', ''), None)
         self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
         self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
+        self.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de')
+        self.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de')
 
     def test_url_or_none(self):
         self.assertEqual(url_or_none(None), None)

test/testdata/cookies/httponly_cookies.txt

@@ -0,0 +1,6 @@
+# Netscape HTTP Cookie File
+# http://curl.haxx.se/rfc/cookie_spec.html
+# This is a generated file!  Do not edit.
+
+#HttpOnly_www.foobar.foobar	FALSE	/	TRUE	2147483647	HTTPONLY_COOKIE	HTTPONLY_COOKIE_VALUE
+www.foobar.foobar	FALSE	/	TRUE	2147483647	JS_ACCESSIBLE_COOKIE	JS_ACCESSIBLE_COOKIE_VALUE

test/testdata/m3u8/ted_18923.m3u8

@@ -0,0 +1,28 @@
+#EXTM3U
+#EXT-X-VERSION:4
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1255659,PROGRAM-ID=1,CODECS="avc1.42c01e,mp4a.40.2",RESOLUTION=640x360
+/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=163154,PROGRAM-ID=1,CODECS="avc1.42c00c,mp4a.40.2",RESOLUTION=320x180
+/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=481701,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288
+/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=769968,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288
+/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=984037,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288
+/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1693925,PROGRAM-ID=1,CODECS="avc1.4d401f,mp4a.40.2",RESOLUTION=853x480
+/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=2462469,PROGRAM-ID=1,CODECS="avc1.640028,mp4a.40.2",RESOLUTION=1280x720
+/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=68101,PROGRAM-ID=1,CODECS="mp4a.40.2",DEFAULT=YES
+/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b
+
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=74298,PROGRAM-ID=1,CODECS="avc1.42c00c",RESOLUTION=320x180,URI="/videos/BorisHesser_2018S/video/64k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=216200,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/180k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=304717,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/320k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=350933,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/450k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=495850,PROGRAM-ID=1,CODECS="avc1.42c01e",RESOLUTION=640x360,URI="/videos/BorisHesser_2018S/video/600k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=810750,PROGRAM-ID=1,CODECS="avc1.4d401f",RESOLUTION=853x480,URI="/videos/BorisHesser_2018S/video/950k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=1273700,PROGRAM-ID=1,CODECS="avc1.640028",RESOLUTION=1280x720,URI="/videos/BorisHesser_2018S/video/1500k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+
+#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="600k",LANGUAGE="en",NAME="Audio",AUTOSELECT=YES,DEFAULT=YES,URI="/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b",BANDWIDTH=614400

youtube_dl/YoutubeDL.py

@@ -82,6 +82,7 @@ from .utils import (
     sanitize_url,
     sanitized_Request,
     std_headers,
+    str_or_none,
     subtitles_filename,
     UnavailableVideoError,
     url_basename,
@@ -1063,21 +1064,24 @@ class YoutubeDL(object):
         if not m:
             STR_OPERATORS = {
                 '=': operator.eq,
-                '!=': operator.ne,
                 '^=': lambda attr, value: attr.startswith(value),
                 '$=': lambda attr, value: attr.endswith(value),
                 '*=': lambda attr, value: value in attr,
             }
             str_operator_rex = re.compile(r'''(?x)
                 \s*(?P<key>ext|acodec|vcodec|container|protocol|format_id)
-                \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
+                \s*(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)?
                 \s*(?P<value>[a-zA-Z0-9._-]+)
                 \s*$
                 ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
             m = str_operator_rex.search(filter_spec)
             if m:
                 comparison_value = m.group('value')
-                op = STR_OPERATORS[m.group('op')]
+                str_op = STR_OPERATORS[m.group('op')]
+                if m.group('negation'):
+                    op = lambda attr, value: not str_op(attr, value)
+                else:
+                    op = str_op
 
         if not m:
             raise ValueError('Invalid filter specification %r' % filter_spec)
@@ -2057,15 +2061,24 @@ class YoutubeDL(object):
                         self.report_warning('Unable to remove downloaded original file')
 
     def _make_archive_id(self, info_dict):
+        video_id = info_dict.get('id')
+        if not video_id:
+            return
         # Future-proof against any change in case
         # and backwards compatibility with prior versions
-        extractor = info_dict.get('extractor_key')
+        extractor = info_dict.get('extractor_key') or info_dict.get('ie_key')  # key in a playlist
         if extractor is None:
-            if 'id' in info_dict:
-                extractor = info_dict.get('ie_key')  # key in a playlist
-        if extractor is None:
-            return None  # Incomplete video information
-        return extractor.lower() + ' ' + info_dict['id']
+            url = str_or_none(info_dict.get('url'))
+            if not url:
+                return
+            # Try to find matching extractor for the URL and take its ie_key
+            for ie in self._ies:
+                if ie.suitable(url):
+                    extractor = ie.ie_key()
+                    break
+            else:
+                return
+        return extractor.lower() + ' ' + video_id
 
     def in_download_archive(self, info_dict):
         fn = self.params.get('download_archive')
@@ -2073,7 +2086,7 @@ class YoutubeDL(object):
             return False
 
         vid_id = self._make_archive_id(info_dict)
-        if vid_id is None:
+        if not vid_id:
             return False  # Incomplete video information
 
         try:

youtube_dl/compat.py

@@ -2508,6 +2508,15 @@ class _TreeBuilder(etree.TreeBuilder):
         pass
 
 
+try:
+    # xml.etree.ElementTree.Element is a method in Python <=2.6 and
+    # the following will crash with:
+    #  TypeError: isinstance() arg 2 must be a class, type, or tuple of classes and types
+    isinstance(None, xml.etree.ElementTree.Element)
+    from xml.etree.ElementTree import Element as compat_etree_Element
+except TypeError:  # Python <=2.6
+    from xml.etree.ElementTree import _ElementInterface as compat_etree_Element
+
 if sys.version_info[0] >= 3:
     def compat_etree_fromstring(text):
         return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder()))
@@ -2969,6 +2978,7 @@ __all__ = [
     'compat_cookiejar',
     'compat_cookies',
     'compat_ctypes_WINFUNCTYPE',
+    'compat_etree_Element',
     'compat_etree_fromstring',
     'compat_etree_register_namespace',
     'compat_expanduser',

youtube_dl/downloader/external.py

@@ -121,7 +121,11 @@ class CurlFD(ExternalFD):
         cmd += self._valueless_option('--silent', 'noprogress')
         cmd += self._valueless_option('--verbose', 'verbose')
         cmd += self._option('--limit-rate', 'ratelimit')
-        cmd += self._option('--retry', 'retries')
+        retry = self._option('--retry', 'retries')
+        if len(retry) == 2:
+            if retry[1] in ('inf', 'infinite'):
+                retry[1] = '2147483647'
+            cmd += retry
         cmd += self._option('--max-filesize', 'max_filesize')
         cmd += self._option('--interface', 'source_address')
         cmd += self._option('--proxy', 'proxy')
@@ -160,6 +164,12 @@ class WgetFD(ExternalFD):
         cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
+        cmd += self._option('--limit-rate', 'ratelimit')
+        retry = self._option('--tries', 'retries')
+        if len(retry) == 2:
+            if retry[1] in ('inf', 'infinite'):
+                retry[1] = '0'
+            cmd += retry
         cmd += self._option('--bind-address', 'source_address')
         cmd += self._option('--proxy', 'proxy')
         cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate')

youtube_dl/downloader/hls.py

@@ -75,10 +75,14 @@ class HlsFD(FragmentFD):
                 fd.add_progress_hook(ph)
             return fd.real_download(filename, info_dict)
 
-        def is_ad_fragment(s):
+        def is_ad_fragment_start(s):
             return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or
                     s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
 
+        def is_ad_fragment_end(s):
+            return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s or
+                    s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
+
         media_frags = 0
         ad_frags = 0
         ad_frag_next = False
@@ -87,12 +91,13 @@ class HlsFD(FragmentFD):
             if not line:
                 continue
             if line.startswith('#'):
-                if is_ad_fragment(line):
-                    ad_frags += 1
+                if is_ad_fragment_start(line):
                     ad_frag_next = True
+                elif is_ad_fragment_end(line):
+                    ad_frag_next = False
                 continue
             if ad_frag_next:
-                ad_frag_next = False
+                ad_frags += 1
                 continue
             media_frags += 1
 
@@ -123,7 +128,6 @@ class HlsFD(FragmentFD):
             if line:
                 if not line.startswith('#'):
                     if ad_frag_next:
-                        ad_frag_next = False
                         continue
                     frag_index += 1
                     if frag_index <= ctx['fragment_index']:
@@ -196,8 +200,10 @@ class HlsFD(FragmentFD):
                         'start': sub_range_start,
                         'end': sub_range_start + int(splitted_byte_range[0]),
                     }
-                elif is_ad_fragment(line):
+                elif is_ad_fragment_start(line):
                     ad_frag_next = True
+                elif is_ad_fragment_end(line):
+                    ad_frag_next = False
 
         self._finish_frag_download(ctx)
 

youtube_dl/extractor/acast.py

@@ -79,17 +79,27 @@ class ACastIE(InfoExtractor):
 
 class ACastChannelIE(InfoExtractor):
     IE_NAME = 'acast:channel'
-    _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
-    _TEST = {
-        'url': 'https://www.acast.com/condenasttraveler',
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:www\.)?acast\.com/|
+                            play\.acast\.com/s/
+                        )
+                        (?P<id>[^/#?]+)
+                    '''
+    _TESTS = [{
+        'url': 'https://www.acast.com/todayinfocus',
         'info_dict': {
-            'id': '50544219-29bb-499e-a083-6087f4cb7797',
-            'title': 'Condé Nast Traveler Podcast',
-            'description': 'md5:98646dee22a5b386626ae31866638fbd',
+            'id': '4efc5294-5385-4847-98bd-519799ce5786',
+            'title': 'Today in Focus',
+            'description': 'md5:9ba5564de5ce897faeb12963f4537a64',
         },
-        'playlist_mincount': 20,
-    }
-    _API_BASE_URL = 'https://www.acast.com/api/'
+        'playlist_mincount': 35,
+    }, {
+        'url': 'http://play.acast.com/s/ft-banking-weekly',
+        'only_matching': True,
+    }]
+    _API_BASE_URL = 'https://play.acast.com/api/'
     _PAGE_SIZE = 10
 
     @classmethod
@@ -102,7 +112,7 @@ class ACastChannelIE(InfoExtractor):
             channel_slug, note='Download page %d of channel data' % page)
         for cast in casts:
             yield self.url_result(
-                'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
+                'https://play.acast.com/s/%s/%s' % (channel_slug, cast['url']),
                 'ACast', cast['id'])
 
     def _real_extract(self, url):

youtube_dl/extractor/audiomack.py

@@ -62,7 +62,7 @@ class AudiomackIE(InfoExtractor):
         # Audiomack wraps a lot of soundcloud tracks in their branded wrapper
         # if so, pass the work off to the soundcloud extractor
         if SoundcloudIE.suitable(api_response['url']):
-            return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'}
+            return self.url_result(api_response['url'], SoundcloudIE.ie_key())
 
         return {
             'id': compat_str(api_response.get('id', album_url_tag)),

youtube_dl/extractor/bbc.py

@@ -1,8 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
 import itertools
+import re
 
 from .common import InfoExtractor
 from ..utils import (
@@ -17,10 +17,12 @@ from ..utils import (
     parse_iso8601,
     try_get,
     unescapeHTML,
+    url_or_none,
     urlencode_postdata,
     urljoin,
 )
 from ..compat import (
+    compat_etree_Element,
     compat_HTTPError,
     compat_urlparse,
 )
@@ -310,7 +312,13 @@ class BBCCoUkIE(InfoExtractor):
     def _get_subtitles(self, media, programme_id):
         subtitles = {}
         for connection in self._extract_connections(media):
-            captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
+            cc_url = url_or_none(connection.get('href'))
+            if not cc_url:
+                continue
+            captions = self._download_xml(
+                cc_url, programme_id, 'Downloading captions', fatal=False)
+            if not isinstance(captions, compat_etree_Element):
+                continue
             lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
             subtitles[lang] = [
                 {
@@ -795,6 +803,15 @@ class BBCIE(BBCCoUkIE):
             'uploader': 'Radio 3',
             'uploader_id': 'bbc_radio_three',
         },
+    }, {
+        'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227',
+        'info_dict': {
+            'id': 'p06w9tws',
+            'ext': 'mp4',
+            'title': 'md5:2fabf12a726603193a2879a055f72514',
+            'description': 'Learn English words and phrases from this story',
+        },
+        'add_ie': [BBCCoUkIE.ie_key()],
     }]
 
     @classmethod
@@ -945,6 +962,15 @@ class BBCIE(BBCCoUkIE):
         if entries:
             return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
 
+        # http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227
+        group_id = self._search_regex(
+            r'<div[^>]+\bclass=["\']video["\'][^>]+\bdata-pid=["\'](%s)' % self._ID_REGEX,
+            webpage, 'group id', default=None)
+        if playlist_id:
+            return self.url_result(
+                'https://www.bbc.co.uk/programmes/%s' % group_id,
+                ie=BBCCoUkIE.ie_key())
+
         # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
         programme_id = self._search_regex(
             [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,

youtube_dl/extractor/beeg.py

@@ -1,15 +1,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_chr,
-    compat_ord,
-    compat_urllib_parse_unquote,
-)
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
-    parse_iso8601,
-    urljoin,
+    unified_timestamp,
 )
 
 
@@ -36,29 +31,9 @@ class BeegIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        cpl_url = self._search_regex(
-            r'<script[^>]+src=(["\'])(?P<url>(?:/static|(?:https?:)?//static\.beeg\.com)/cpl/\d+\.js.*?)\1',
-            webpage, 'cpl', default=None, group='url')
-
-        cpl_url = urljoin(url, cpl_url)
-
-        beeg_version, beeg_salt = [None] * 2
-
-        if cpl_url:
-            cpl = self._download_webpage(
-                self._proto_relative_url(cpl_url), video_id,
-                'Downloading cpl JS', fatal=False)
-            if cpl:
-                beeg_version = int_or_none(self._search_regex(
-                    r'beeg_version\s*=\s*([^\b]+)', cpl,
-                    'beeg version', default=None)) or self._search_regex(
-                    r'/(\d+)\.js', cpl_url, 'beeg version', default=None)
-                beeg_salt = self._search_regex(
-                    r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg salt',
-                    default=None, group='beeg_salt')
-
-        beeg_version = beeg_version or '2185'
-        beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H'
+        beeg_version = self._search_regex(
+            r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
+            default='1546225636701')
 
         for api_path in ('', 'api.'):
             video = self._download_json(
@@ -68,37 +43,6 @@ class BeegIE(InfoExtractor):
             if video:
                 break
 
-        def split(o, e):
-            def cut(s, x):
-                n.append(s[:x])
-                return s[x:]
-            n = []
-            r = len(o) % e
-            if r > 0:
-                o = cut(o, r)
-            while len(o) > e:
-                o = cut(o, e)
-            n.append(o)
-            return n
-
-        def decrypt_key(key):
-            # Reverse engineered from http://static.beeg.com/cpl/1738.js
-            a = beeg_salt
-            e = compat_urllib_parse_unquote(key)
-            o = ''.join([
-                compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)
-                for n in range(len(e))])
-            return ''.join(split(o, 3)[::-1])
-
-        def decrypt_url(encrypted_url):
-            encrypted_url = self._proto_relative_url(
-                encrypted_url.replace('{DATA_MARKERS}', ''), 'https:')
-            key = self._search_regex(
-                r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
-            if not key:
-                return encrypted_url
-            return encrypted_url.replace(key, decrypt_key(key))
-
         formats = []
         for format_id, video_url in video.items():
             if not video_url:
@@ -108,18 +52,20 @@ class BeegIE(InfoExtractor):
             if not height:
                 continue
             formats.append({
-                'url': decrypt_url(video_url),
+                'url': self._proto_relative_url(
+                    video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'),
                 'format_id': format_id,
                 'height': int(height),
             })
         self._sort_formats(formats)
 
         title = video['title']
-        video_id = video.get('id') or video_id
+        video_id = compat_str(video.get('id') or video_id)
         display_id = video.get('code')
         description = video.get('desc')
+        series = video.get('ps_name')
 
-        timestamp = parse_iso8601(video.get('date'), ' ')
+        timestamp = unified_timestamp(video.get('date'))
         duration = int_or_none(video.get('duration'))
 
         tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
@@ -129,6 +75,7 @@ class BeegIE(InfoExtractor):
             'display_id': display_id,
             'title': title,
             'description': description,
+            'series': series,
             'timestamp': timestamp,
             'duration': duration,
             'tags': tags,

youtube_dl/extractor/bilibili.py

@@ -93,8 +93,8 @@ class BiliBiliIE(InfoExtractor):
         }]
     }]
 
-    _APP_KEY = '84956560bc028eb7'
-    _BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e'
+    _APP_KEY = 'iVGUTjsxvpLeuDCf'
+    _BILIBILI_KEY = 'aHRmhWMLkdeMuILqORnYZocwMBpMEOdt'
 
     def _report_error(self, result):
         if 'message' in result:

youtube_dl/extractor/bitchute.py

@@ -5,7 +5,10 @@ import itertools
 import re
 
 from .common import InfoExtractor
-from ..utils import urlencode_postdata
+from ..utils import (
+    orderedSet,
+    urlencode_postdata,
+)
 
 
 class BitChuteIE(InfoExtractor):
@@ -43,10 +46,16 @@ class BitChuteIE(InfoExtractor):
             'description', webpage, 'title',
             default=None) or self._og_search_description(webpage)
 
+        format_urls = []
+        for mobj in re.finditer(
+                r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
+            format_urls.append(mobj.group('url'))
+        format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage))
+
         formats = [
-            {'url': mobj.group('url')}
-            for mobj in re.finditer(
-                r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage)]
+            {'url': format_url}
+            for format_url in orderedSet(format_urls)]
+        self._check_formats(formats, video_id)
         self._sort_formats(formats)
 
         description = self._html_search_regex(

youtube_dl/extractor/cammodels.py

@@ -14,6 +14,7 @@ class CamModelsIE(InfoExtractor):
     _TESTS = [{
         'url': 'https://www.cammodels.com/cam/AutumnKnight/',
         'only_matching': True,
+        'age_limit': 18
     }]
 
     def _real_extract(self, url):
@@ -93,4 +94,5 @@ class CamModelsIE(InfoExtractor):
             'title': self._live_title(user_id),
             'is_live': True,
             'formats': formats,
+            'age_limit': 18
         }

youtube_dl/extractor/camtube.py

@@ -20,6 +20,7 @@ class CamTubeIE(InfoExtractor):
             'duration': 1274,
             'timestamp': 1528018608,
             'upload_date': '20180603',
+            'age_limit': 18
         },
         'params': {
             'skip_download': True,
@@ -66,4 +67,5 @@ class CamTubeIE(InfoExtractor):
             'like_count': like_count,
             'creator': creator,
             'formats': formats,
+            'age_limit': 18
         }

youtube_dl/extractor/camwithher.py

@@ -25,6 +25,7 @@ class CamWithHerIE(InfoExtractor):
             'comment_count': int,
             'uploader': 'MileenaK',
             'upload_date': '20160322',
+            'age_limit': 18,
         },
         'params': {
             'skip_download': True,
@@ -84,4 +85,5 @@ class CamWithHerIE(InfoExtractor):
             'comment_count': comment_count,
             'uploader': uploader,
             'upload_date': upload_date,
+            'age_limit': 18
         }

youtube_dl/extractor/carambatv.py

@@ -82,6 +82,12 @@ class CarambaTVPageIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         videomore_url = VideomoreIE._extract_url(webpage)
+        if not videomore_url:
+            videomore_id = self._search_regex(
+                r'getVMCode\s*\(\s*["\']?(\d+)', webpage, 'videomore id',
+                default=None)
+            if videomore_id:
+                videomore_url = 'videomore:%s' % videomore_id
         if videomore_url:
             title = self._og_search_title(webpage)
             return {

youtube_dl/extractor/cartoonnetwork.py

@@ -1,20 +1,19 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .turner import TurnerBaseIE
+from ..utils import int_or_none
 
 
 class CartoonNetworkIE(TurnerBaseIE):
     _VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html'
     _TEST = {
-        'url': 'http://www.cartoonnetwork.com/video/teen-titans-go/starfire-the-cat-lady-clip.html',
+        'url': 'https://www.cartoonnetwork.com/video/ben-10/how-to-draw-upgrade-episode.html',
         'info_dict': {
-            'id': '8a250ab04ed07e6c014ef3f1e2f9016c',
+            'id': '6e3375097f63874ebccec7ef677c1c3845fa850e',
             'ext': 'mp4',
-            'title': 'Starfire the Cat Lady',
-            'description': 'Robin decides to become a cat so that Starfire will finally love him.',
+            'title': 'How to Draw Upgrade',
+            'description': 'md5:2061d83776db7e8be4879684eefe8c0f',
         },
         'params': {
             # m3u8 download
@@ -25,18 +24,39 @@ class CartoonNetworkIE(TurnerBaseIE):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        id_type, video_id = re.search(r"_cnglobal\.cvp(Video|Title)Id\s*=\s*'([^']+)';", webpage).groups()
-        query = ('id' if id_type == 'Video' else 'titleId') + '=' + video_id
-        return self._extract_cvp_info(
-            'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
-                'secure': {
-                    'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big',
-                    'tokenizer_src': 'https://token.vgtf.net/token/token_mobile',
-                },
-            }, {
+
+        def find_field(global_re, name, content_re=None, value_re='[^"]+', fatal=False):
+            metadata_re = ''
+            if content_re:
+                metadata_re = r'|video_metadata\.content_' + content_re
+            return self._search_regex(
+                r'(?:_cnglobal\.currentVideo\.%s%s)\s*=\s*"(%s)";' % (global_re, metadata_re, value_re),
+                webpage, name, fatal=fatal)
+
+        media_id = find_field('mediaId', 'media id', 'id', '[0-9a-f]{40}', True)
+        title = find_field('episodeTitle', 'title', '(?:episodeName|name)', fatal=True)
+
+        info = self._extract_ngtv_info(
+            media_id, {'networkId': 'cartoonnetwork'}, {
                 'url': url,
                 'site_name': 'CartoonNetwork',
-                'auth_required': self._search_regex(
-                    r'_cnglobal\.cvpFullOrPreviewAuth\s*=\s*(true|false);',
-                    webpage, 'auth required', default='false') == 'true',
+                'auth_required': find_field('authType', 'auth type') != 'unauth',
             })
+
+        series = find_field(
+            'propertyName', 'series', 'showName') or self._html_search_meta('partOfSeries', webpage)
+        info.update({
+            'id': media_id,
+            'display_id': display_id,
+            'title': title,
+            'description': self._html_search_meta('description', webpage),
+            'series': series,
+            'episode': title,
+        })
+
+        for field in ('season', 'episode'):
+            field_name = field + 'Number'
+            info[field + '_number'] = int_or_none(find_field(
+                field_name, field + ' number', value_re=r'\d+') or self._html_search_meta(field_name, webpage))
+
+        return info

youtube_dl/extractor/cnn.py

@@ -119,11 +119,7 @@ class CNNBlogsIE(InfoExtractor):
     def _real_extract(self, url):
         webpage = self._download_webpage(url, url_basename(url))
         cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
-        return {
-            '_type': 'url',
-            'url': cnn_url,
-            'ie_key': CNNIE.ie_key(),
-        }
+        return self.url_result(cnn_url, CNNIE.ie_key())
 
 
 class CNNArticleIE(InfoExtractor):
@@ -145,8 +141,4 @@ class CNNArticleIE(InfoExtractor):
     def _real_extract(self, url):
         webpage = self._download_webpage(url, url_basename(url))
         cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url')
-        return {
-            '_type': 'url',
-            'url': 'http://cnn.com/video/?/video/' + cnn_url,
-            'ie_key': CNNIE.ie_key(),
-        }
+        return self.url_result('http://cnn.com/video/?/video/' + cnn_url, CNNIE.ie_key())

youtube_dl/extractor/common.py

@@ -17,6 +17,7 @@ import math
 from ..compat import (
     compat_cookiejar,
     compat_cookies,
+    compat_etree_Element,
     compat_etree_fromstring,
     compat_getpass,
     compat_integer_types,
@@ -102,10 +103,23 @@ class InfoExtractor(object):
                     from worst to best quality.
 
                     Potential fields:
-                    * url        Mandatory. The URL of the video file
+                    * url        The mandatory URL representing the media:
+                                   for plain file media - HTTP URL of this file,
+                                   for RTMP - RTMP URL,
+                                   for HLS - URL of the M3U8 media playlist,
+                                   for HDS - URL of the F4M manifest,
+                                   for DASH - URL of the MPD manifest or
+                                              base URL representing the media
+                                              if MPD manifest is parsed from
+                                              a string,
+                                   for MSS - URL of the ISM manifest.
                     * manifest_url
                                  The URL of the manifest file in case of
-                                 fragmented media (DASH, hls, hds)
+                                 fragmented media:
+                                   for HLS - URL of the M3U8 master playlist,
+                                   for HDS - URL of the F4M manifest,
+                                   for DASH - URL of the MPD manifest,
+                                   for MSS - URL of the ISM manifest.
                     * ext        Will be calculated from URL if missing
                     * format     A human-readable description of the format
                                  ("mp4 container with h264/opus").
@@ -788,7 +802,7 @@ class InfoExtractor(object):
             fatal=True, encoding=None, data=None, headers={}, query={},
             expected_status=None):
         """
-        Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle).
+        Return a tuple (xml as an compat_etree_Element, URL handle).
 
         See _download_webpage docstring for arguments specification.
         """
@@ -809,7 +823,7 @@ class InfoExtractor(object):
             transform_source=None, fatal=True, encoding=None,
             data=None, headers={}, query={}, expected_status=None):
         """
-        Return the xml as an xml.etree.ElementTree.Element.
+        Return the xml as an compat_etree_Element.
 
         See _download_webpage docstring for arguments specification.
         """
@@ -1058,7 +1072,7 @@ class InfoExtractor(object):
     @staticmethod
     def _og_regexes(prop):
         content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))'
-        property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)'
+        property_re = (r'(?:name|property)=(?:\'og[:-]%(prop)s\'|"og[:-]%(prop)s"|\s*og[:-]%(prop)s\b)'
                        % {'prop': re.escape(prop)})
         template = r'<meta[^>]+?%s[^>]+?%s'
         return [
@@ -1239,17 +1253,30 @@ class InfoExtractor(object):
                 if expected_type is not None and expected_type != item_type:
                     return info
                 if item_type in ('TVEpisode', 'Episode'):
+                    episode_name = unescapeHTML(e.get('name'))
                     info.update({
-                        'episode': unescapeHTML(e.get('name')),
+                        'episode': episode_name,
                         'episode_number': int_or_none(e.get('episodeNumber')),
                         'description': unescapeHTML(e.get('description')),
                     })
+                    if not info.get('title') and episode_name:
+                        info['title'] = episode_name
                     part_of_season = e.get('partOfSeason')
                     if isinstance(part_of_season, dict) and part_of_season.get('@type') in ('TVSeason', 'Season', 'CreativeWorkSeason'):
-                        info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
+                        info.update({
+                            'season': unescapeHTML(part_of_season.get('name')),
+                            'season_number': int_or_none(part_of_season.get('seasonNumber')),
+                        })
                     part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries')
                     if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'):
                         info['series'] = unescapeHTML(part_of_series.get('name'))
+                elif item_type == 'Movie':
+                    info.update({
+                        'title': unescapeHTML(e.get('name')),
+                        'description': unescapeHTML(e.get('description')),
+                        'duration': parse_duration(e.get('duration')),
+                        'timestamp': unified_timestamp(e.get('dateCreated')),
+                    })
                 elif item_type in ('Article', 'NewsArticle'):
                     info.update({
                         'timestamp': parse_iso8601(e.get('datePublished')),
@@ -1441,6 +1468,9 @@ class InfoExtractor(object):
     def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None,
                            transform_source=lambda s: fix_xml_ampersands(s).strip(),
                            fatal=True, m3u8_id=None):
+        if not isinstance(manifest, compat_etree_Element) and not fatal:
+            return []
+
         # currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy
         akamai_pv = manifest.find('{http://ns.adobe.com/f4m/1.0}pv-2.0')
         if akamai_pv is not None and ';' in akamai_pv.text:
@@ -1586,6 +1616,7 @@ class InfoExtractor(object):
         # References:
         # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-21
         # 2. https://github.com/rg3/youtube-dl/issues/12211
+        # 3. https://github.com/rg3/youtube-dl/issues/18923
 
         # We should try extracting formats only from master playlists [1, 4.3.4],
         # i.e. playlists that describe available qualities. On the other hand
@@ -1657,11 +1688,16 @@ class InfoExtractor(object):
             rendition = stream_group[0]
             return rendition.get('NAME') or stream_group_id
 
+        # parse EXT-X-MEDIA tags before EXT-X-STREAM-INF in order to have the
+        # chance to detect video only formats when EXT-X-STREAM-INF tags
+        # precede EXT-X-MEDIA tags in HLS manifest such as [3].
+        for line in m3u8_doc.splitlines():
+            if line.startswith('#EXT-X-MEDIA:'):
+                extract_media(line)
+
         for line in m3u8_doc.splitlines():
             if line.startswith('#EXT-X-STREAM-INF:'):
                 last_stream_inf = parse_m3u8_attributes(line)
-            elif line.startswith('#EXT-X-MEDIA:'):
-                extract_media(line)
             elif line.startswith('#') or not line.strip():
                 continue
             else:
@@ -2101,7 +2137,8 @@ class InfoExtractor(object):
                         bandwidth = int_or_none(representation_attrib.get('bandwidth'))
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
-                            'url': base_url,
+                            # NB: mpd_url may be empty when MPD manifest is parsed from a string
+                            'url': mpd_url or base_url,
                             'manifest_url': mpd_url,
                             'ext': mimetype2ext(mime_type),
                             'width': int_or_none(representation_attrib.get('width')),
@@ -2614,7 +2651,7 @@ class InfoExtractor(object):
                 'id': this_video_id,
                 'title': unescapeHTML(video_data['title'] if require_title else video_data.get('title')),
                 'description': video_data.get('description'),
-                'thumbnail': self._proto_relative_url(video_data.get('image')),
+                'thumbnail': urljoin(base_url, self._proto_relative_url(video_data.get('image'))),
                 'timestamp': int_or_none(video_data.get('pubdate')),
                 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
                 'subtitles': subtitles,
@@ -2641,12 +2678,9 @@ class InfoExtractor(object):
         for source in jwplayer_sources_data:
             if not isinstance(source, dict):
                 continue
-            source_url = self._proto_relative_url(source.get('file'))
-            if not source_url:
-                continue
-            if base_url:
-                source_url = compat_urlparse.urljoin(base_url, source_url)
-            if source_url in urls:
+            source_url = urljoin(
+                base_url, self._proto_relative_url(source.get('file')))
+            if not source_url or source_url in urls:
                 continue
             urls.append(source_url)
             source_type = source.get('type') or ''

youtube_dl/extractor/crackle.py

@@ -1,7 +1,10 @@
 # coding: utf-8
 from __future__ import unicode_literals, division
 
+import hashlib
+import hmac
 import re
+import time
 
 from .common import InfoExtractor
 from ..compat import compat_HTTPError
@@ -48,6 +51,21 @@ class CrackleIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    _MEDIA_FILE_SLOTS = {
+        '360p.mp4': {
+            'width': 640,
+            'height': 360,
+        },
+        '480p.mp4': {
+            'width': 768,
+            'height': 432,
+        },
+        '480p_1mbps.mp4': {
+            'width': 852,
+            'height': 480,
+        },
+    }
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -59,13 +77,16 @@ class CrackleIE(InfoExtractor):
 
         for country in countries:
             try:
+                # Authorization generation algorithm is reverse engineered from:
+                # https://www.sonycrackle.com/static/js/main.ea93451f.chunk.js
+                media_detail_url = 'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s?disableProtocols=true' % (video_id, country)
+                timestamp = time.strftime('%Y%m%d%H%M', time.gmtime())
+                h = hmac.new(b'IGSLUQCBDFHEOIFM', '|'.join([media_detail_url, timestamp]).encode(), hashlib.sha1).hexdigest().upper()
                 media = self._download_json(
-                    'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s'
-                    % (video_id, country), video_id,
-                    'Downloading media JSON as %s' % country,
-                    'Unable to download media JSON', query={
-                        'disableProtocols': 'true',
-                        'format': 'json'
+                    media_detail_url, video_id, 'Downloading media JSON as %s' % country,
+                    'Unable to download media JSON', headers={
+                        'Accept': 'application/json',
+                        'Authorization': '|'.join([h, timestamp, '117', '1']),
                     })
             except ExtractorError as e:
                 # 401 means geo restriction, trying next country
@@ -95,6 +116,20 @@ class CrackleIE(InfoExtractor):
                 elif ext == 'mpd':
                     formats.extend(self._extract_mpd_formats(
                         format_url, video_id, mpd_id='dash', fatal=False))
+                elif format_url.endswith('.ism/Manifest'):
+                    formats.extend(self._extract_ism_formats(
+                        format_url, video_id, ism_id='mss', fatal=False))
+                else:
+                    mfs_path = e.get('Type')
+                    mfs_info = self._MEDIA_FILE_SLOTS.get(mfs_path)
+                    if not mfs_info:
+                        continue
+                    formats.append({
+                        'url': format_url,
+                        'format_id': 'http-' + mfs_path.split('.')[0],
+                        'width': mfs_info['width'],
+                        'height': mfs_info['height'],
+                    })
             self._sort_formats(formats)
 
             description = media.get('Description')

youtube_dl/extractor/crunchyroll.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 
 import re
 import json
-import xml.etree.ElementTree as etree
 import zlib
 
 from hashlib import sha1
@@ -12,6 +11,7 @@ from .common import InfoExtractor
 from .vrv import VRVIE
 from ..compat import (
     compat_b64decode,
+    compat_etree_Element,
     compat_etree_fromstring,
     compat_urllib_parse_urlencode,
     compat_urllib_request,
@@ -56,22 +56,11 @@ class CrunchyrollBaseIE(InfoExtractor):
         if username is None:
             return
 
-        self._download_webpage(
-            'https://www.crunchyroll.com/?a=formhandler',
-            None, 'Logging in', 'Wrong login info',
-            data=urlencode_postdata({
-                'formname': 'RpcApiUser_Login',
-                'next_url': 'https://www.crunchyroll.com/acct/membership',
-                'name': username,
-                'password': password,
-            }))
-
-        '''
         login_page = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login page')
 
         def is_logged(webpage):
-            return '<title>Redirecting' in webpage
+            return 'href="/logout"' in webpage
 
         # Already logged in
         if is_logged(login_page):
@@ -110,7 +99,6 @@ class CrunchyrollBaseIE(InfoExtractor):
             raise ExtractorError('Unable to login: %s' % error, expected=True)
 
         raise ExtractorError('Unable to log in')
-        '''
 
     def _real_initialize(self):
         self._login()
@@ -144,7 +132,7 @@ class CrunchyrollBaseIE(InfoExtractor):
 
 class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
     IE_NAME = 'crunchyroll'
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
         'info_dict': {
@@ -269,6 +257,9 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
     }, {
         'url': 'http://www.crunchyroll.com/media-723735',
         'only_matching': True,
+    }, {
+        'url': 'https://www.crunchyroll.com/en-gb/mob-psycho-100/episode-2-urban-legends-encountering-rumors-780921',
+        'only_matching': True,
     }]
 
     _FORMAT_IDS = {
@@ -399,7 +390,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 'Downloading subtitles for ' + sub_name, data={
                     'subtitle_script_id': sub_id,
                 })
-            if not isinstance(sub_doc, etree.Element):
+            if not isinstance(sub_doc, compat_etree_Element):
                 continue
             sid = sub_doc.get('id')
             iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
@@ -516,7 +507,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                         'video_quality': stream_quality,
                         'current_page': url,
                     })
-                if isinstance(streamdata, etree.Element):
+                if isinstance(streamdata, compat_etree_Element):
                     stream_info = streamdata.find('./{default}preload/stream_info')
                     if stream_info is not None:
                         stream_infos.append(stream_info)
@@ -527,7 +518,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                         'video_format': stream_format,
                         'video_encode_quality': stream_quality,
                     })
-                if isinstance(stream_info, etree.Element):
+                if isinstance(stream_info, compat_etree_Element):
                     stream_infos.append(stream_info)
                 for stream_info in stream_infos:
                     video_encode_id = xpath_text(stream_info, './video_encode_id')
@@ -602,7 +593,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         season = episode = episode_number = duration = thumbnail = None
 
-        if isinstance(metadata, etree.Element):
+        if isinstance(metadata, compat_etree_Element):
             season = xpath_text(metadata, 'series_title')
             episode = xpath_text(metadata, 'episode_title')
             episode_number = int_or_none(xpath_text(metadata, 'episode_number'))

youtube_dl/extractor/curiositystream.py

@@ -46,8 +46,24 @@ class CuriosityStreamBaseIE(InfoExtractor):
         self._handle_errors(result)
         self._auth_token = result['message']['auth_token']
 
-    def _extract_media_info(self, media):
-        video_id = compat_str(media['id'])
+
+class CuriosityStreamIE(CuriosityStreamBaseIE):
+    IE_NAME = 'curiositystream'
+    _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.',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        media = self._call_api('media/' + video_id, video_id)
         title = media['title']
 
         formats = []
@@ -114,38 +130,21 @@ class CuriosityStreamBaseIE(InfoExtractor):
         }
 
 
-class CuriosityStreamIE(CuriosityStreamBaseIE):
-    IE_NAME = 'curiositystream'
-    _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.',
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        media = self._call_api('media/' + video_id, video_id)
-        return self._extract_media_info(media)
-
-
 class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
     IE_NAME = 'curiositystream:collection'
-    _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collection|series)/(?P<id>\d+)'
+    _TESTS = [{
         'url': 'https://app.curiositystream.com/collection/2',
         'info_dict': {
             'id': '2',
             'title': 'Curious Minds: The Internet',
             'description': 'How is the internet shaping our lives in the 21st Century?',
         },
-        'playlist_mincount': 12,
-    }
+        'playlist_mincount': 17,
+    }, {
+        'url': 'https://curiositystream.com/series/2',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         collection_id = self._match_id(url)
@@ -153,7 +152,10 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
             'collections/' + collection_id, collection_id)
         entries = []
         for media in collection.get('media', []):
-            entries.append(self._extract_media_info(media))
+            media_id = compat_str(media.get('id'))
+            entries.append(self.url_result(
+                'https://curiositystream.com/video/' + media_id,
+                CuriosityStreamIE.ie_key(), media_id))
         return self.playlist_result(
             entries, collection_id,
             collection.get('title'), collection.get('description'))

youtube_dl/extractor/discovery.py

@@ -17,16 +17,29 @@ from ..compat import compat_HTTPError
 
 
 class DiscoveryIE(DiscoveryGoBaseIE):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>
-            discovery|
-            investigationdiscovery|
-            discoverylife|
-            animalplanet|
-            ahctv|
-            destinationamerica|
-            sciencechannel|
-            tlc|
-            velocity
+    _VALID_URL = r'''(?x)https?://
+        (?P<site>
+            (?:www\.)?
+                (?:
+                    discovery|
+                    investigationdiscovery|
+                    discoverylife|
+                    animalplanet|
+                    ahctv|
+                    destinationamerica|
+                    sciencechannel|
+                    tlc|
+                    velocity
+                )|
+            watch\.
+                (?:
+                    hgtv|
+                    foodnetwork|
+                    travelchannel|
+                    diynetwork|
+                    cookingchanneltv|
+                    motortrend
+                )
         )\.com(?P<path>/tv-shows/[^/]+/(?:video|full-episode)s/(?P<id>[^./?#]+))'''
     _TESTS = [{
         'url': 'https://www.discovery.com/tv-shows/cash-cab/videos/dave-foley',
@@ -71,7 +84,7 @@ class DiscoveryIE(DiscoveryGoBaseIE):
 
         if not access_token:
             access_token = self._download_json(
-                'https://www.%s.com/anonymous' % site, display_id, query={
+                'https://%s.com/anonymous' % site, display_id, query={
                     'authRel': 'authorization',
                     'client_id': try_get(
                         react_data, lambda x: x['application']['apiClientId'],
@@ -81,11 +94,12 @@ class DiscoveryIE(DiscoveryGoBaseIE):
                 })['access_token']
 
         try:
+            headers = self.geo_verification_headers()
+            headers['Authorization'] = 'Bearer ' + access_token
+
             stream = self._download_json(
                 'https://api.discovery.com/v1/streaming/video/' + video_id,
-                display_id, headers={
-                    'Authorization': 'Bearer ' + access_token,
-                })
+                display_id, headers=headers)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403):
                 e_description = self._parse_json(

youtube_dl/extractor/drtuber.py

@@ -4,7 +4,9 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    int_or_none,
     NO_DEFAULT,
+    parse_duration,
     str_to_int,
 )
 
@@ -65,6 +67,9 @@ class DrTuberIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
+        duration = int_or_none(video_data.get('duration')) or parse_duration(
+            video_data.get('duration_format'))
+
         title = self._html_search_regex(
             (r'<h1[^>]+class=["\']title[^>]+>([^<]+)',
              r'<title>([^<]+)\s*@\s+DrTuber',
@@ -103,4 +108,5 @@ class DrTuberIE(InfoExtractor):
             'comment_count': comment_count,
             'categories': categories,
             'age_limit': self._rta_search(webpage),
+            'duration': duration,
         }

youtube_dl/extractor/drtv.py

@@ -1,15 +1,25 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import binascii
+import hashlib
+import re
+
+
 from .common import InfoExtractor
+from ..aes import aes_cbc_decrypt
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
+    bytes_to_intlist,
     ExtractorError,
     int_or_none,
+    intlist_to_bytes,
     float_or_none,
     mimetype2ext,
-    parse_iso8601,
-    remove_end,
+    str_or_none,
+    unified_timestamp,
     update_url_query,
+    url_or_none,
 )
 
 
@@ -20,23 +30,31 @@ class DRTVIE(InfoExtractor):
     IE_NAME = 'drtv'
     _TESTS = [{
         'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
-        'md5': '7ae17b4e18eb5d29212f424a7511c184',
+        'md5': '25e659cccc9a2ed956110a299fdf5983',
         'info_dict': {
             'id': 'klassen-darlig-taber-10',
             'ext': 'mp4',
             'title': 'Klassen - Dårlig taber (10)',
             'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
-            'timestamp': 1471991907,
-            'upload_date': '20160823',
+            'timestamp': 1539085800,
+            'upload_date': '20181009',
             'duration': 606.84,
+            'series': 'Klassen',
+            'season': 'Klassen I',
+            'season_number': 1,
+            'season_id': 'urn:dr:mu:bundle:57d7e8216187a4031cfd6f6b',
+            'episode': 'Episode 10',
+            'episode_number': 10,
+            'release_year': 2016,
         },
+        'expected_warnings': ['Unable to download f4m manifest'],
     }, {
         # embed
         'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
         'info_dict': {
-            'id': 'christiania-pusher-street-ryddes-drdkrjpo',
+            'id': 'urn:dr:mu:programcard:57c926176187a50a9c6e83c6',
             'ext': 'mp4',
-            'title': 'LIVE Christianias rydning af Pusher Street er i gang',
+            'title': 'christiania pusher street ryddes drdkrjpo',
             'description': 'md5:2a71898b15057e9b97334f61d04e6eb5',
             'timestamp': 1472800279,
             'upload_date': '20160902',
@@ -45,17 +63,18 @@ class DRTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'expected_warnings': ['Unable to download f4m manifest'],
     }, {
         # with SignLanguage formats
         'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
         'info_dict': {
             'id': 'historien-om-danmark-stenalder',
             'ext': 'mp4',
-            'title': 'Historien om Danmark: Stenalder (1)',
+            'title': 'Historien om Danmark: Stenalder',
             'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
-            'timestamp': 1490401996,
-            'upload_date': '20170325',
-            'duration': 3502.04,
+            'timestamp': 1546628400,
+            'upload_date': '20190104',
+            'duration': 3502.56,
             'formats': 'mincount:20',
         },
         'params': {
@@ -74,20 +93,26 @@ class DRTVIE(InfoExtractor):
 
         video_id = self._search_regex(
             (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
-                r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
-            webpage, 'video id')
+             r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
+            webpage, 'video id', default=None)
 
-        programcard = self._download_json(
-            'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
-            video_id, 'Downloading video JSON')
-        data = programcard['Data'][0]
+        if not video_id:
+            video_id = compat_urllib_parse_unquote(self._search_regex(
+                r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)',
+                webpage, 'urn'))
 
-        title = remove_end(self._og_search_title(
-            webpage, default=None), ' | TV | DR') or data['Title']
+        data = self._download_json(
+            'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id,
+            video_id, 'Downloading video JSON', query={'expanded': 'true'})
+
+        title = str_or_none(data.get('Title')) or re.sub(
+            r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '',
+            self._og_search_title(webpage))
         description = self._og_search_description(
             webpage, default=None) or data.get('Description')
 
-        timestamp = parse_iso8601(data.get('CreatedTime'))
+        timestamp = unified_timestamp(
+            data.get('PrimaryBroadcastStartTime') or data.get('SortDateTime'))
 
         thumbnail = None
         duration = None
@@ -97,24 +122,62 @@ class DRTVIE(InfoExtractor):
         formats = []
         subtitles = {}
 
-        for asset in data['Assets']:
+        assets = []
+        primary_asset = data.get('PrimaryAsset')
+        if isinstance(primary_asset, dict):
+            assets.append(primary_asset)
+        secondary_assets = data.get('SecondaryAssets')
+        if isinstance(secondary_assets, list):
+            for secondary_asset in secondary_assets:
+                if isinstance(secondary_asset, dict):
+                    assets.append(secondary_asset)
+
+        def hex_to_bytes(hex):
+            return binascii.a2b_hex(hex.encode('ascii'))
+
+        def decrypt_uri(e):
+            n = int(e[2:10], 16)
+            a = e[10 + n:]
+            data = bytes_to_intlist(hex_to_bytes(e[10:10 + n]))
+            key = bytes_to_intlist(hashlib.sha256(
+                ('%s:sRBzYNXBzkKgnjj8pGtkACch' % a).encode('utf-8')).digest())
+            iv = bytes_to_intlist(hex_to_bytes(a))
+            decrypted = aes_cbc_decrypt(data, key, iv)
+            return intlist_to_bytes(
+                decrypted[:-decrypted[-1]]).decode('utf-8').split('?')[0]
+
+        for asset in assets:
             kind = asset.get('Kind')
             if kind == 'Image':
-                thumbnail = asset.get('Uri')
+                thumbnail = url_or_none(asset.get('Uri'))
             elif kind in ('VideoResource', 'AudioResource'):
                 duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
                 restricted_to_denmark = asset.get('RestrictedToDenmark')
                 asset_target = asset.get('Target')
                 for link in asset.get('Links', []):
                     uri = link.get('Uri')
+                    if not uri:
+                        encrypted_uri = link.get('EncryptedUri')
+                        if not encrypted_uri:
+                            continue
+                        try:
+                            uri = decrypt_uri(encrypted_uri)
+                        except Exception:
+                            self.report_warning(
+                                'Unable to decrypt EncryptedUri', video_id)
+                            continue
+                    uri = url_or_none(uri)
                     if not uri:
                         continue
                     target = link.get('Target')
                     format_id = target or ''
-                    preference = None
-                    if asset_target in ('SpokenSubtitles', 'SignLanguage'):
+                    if asset_target in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
                         preference = -1
                         format_id += '-%s' % asset_target
+                    elif asset_target == 'Default':
+                        preference = 1
+                    else:
+                        preference = None
                     if target == 'HDS':
                         f4m_formats = self._extract_f4m_formats(
                             uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
@@ -140,19 +203,22 @@ class DRTVIE(InfoExtractor):
                             'vcodec': 'none' if kind == 'AudioResource' else None,
                             'preference': preference,
                         })
-                subtitles_list = asset.get('SubtitlesList')
-                if isinstance(subtitles_list, list):
-                    LANGS = {
-                        'Danish': 'da',
-                    }
-                    for subs in subtitles_list:
-                        if not subs.get('Uri'):
-                            continue
-                        lang = subs.get('Language') or 'da'
-                        subtitles.setdefault(LANGS.get(lang, lang), []).append({
-                            'url': subs['Uri'],
-                            'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
-                        })
+            subtitles_list = asset.get('SubtitlesList') or asset.get('Subtitleslist')
+            if isinstance(subtitles_list, list):
+                LANGS = {
+                    'Danish': 'da',
+                }
+                for subs in subtitles_list:
+                    if not isinstance(subs, dict):
+                        continue
+                    sub_uri = url_or_none(subs.get('Uri'))
+                    if not sub_uri:
+                        continue
+                    lang = subs.get('Language') or 'da'
+                    subtitles.setdefault(LANGS.get(lang, lang), []).append({
+                        'url': sub_uri,
+                        'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
+                    })
 
         if not formats and restricted_to_denmark:
             self.raise_geo_restricted(
@@ -170,6 +236,13 @@ class DRTVIE(InfoExtractor):
             'duration': duration,
             'formats': formats,
             'subtitles': subtitles,
+            'series': str_or_none(data.get('SeriesTitle')),
+            'season': str_or_none(data.get('SeasonTitle')),
+            'season_number': int_or_none(data.get('SeasonNumber')),
+            'season_id': str_or_none(data.get('SeasonUrn')),
+            'episode': str_or_none(data.get('EpisodeTitle')),
+            'episode_number': int_or_none(data.get('EpisodeNumber')),
+            'release_year': int_or_none(data.get('ProductionYear')),
         }
 
 

youtube_dl/extractor/dtube.py

@@ -15,16 +15,16 @@ from ..utils import (
 class DTubeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?d\.tube/(?:#!/)?v/(?P<uploader_id>[0-9a-z.-]+)/(?P<id>[0-9a-z]{8})'
     _TEST = {
-        'url': 'https://d.tube/#!/v/benswann/zqd630em',
-        'md5': 'a03eaa186618ffa7a3145945543a251e',
+        'url': 'https://d.tube/#!/v/broncnutz/x380jtr1',
+        'md5': '9f29088fa08d699a7565ee983f56a06e',
         'info_dict': {
-            'id': 'zqd630em',
+            'id': 'x380jtr1',
             'ext': 'mp4',
-            'title': 'Reality Check: FDA\'s Disinformation Campaign on Kratom',
-            'description': 'md5:700d164e066b87f9eac057949e4227c2',
-            'uploader_id': 'benswann',
-            'upload_date': '20180222',
-            'timestamp': 1519328958,
+            'title': 'Lefty 3-Rings is Back Baby!! NCAA Picks',
+            'description': 'md5:60be222088183be3a42f196f34235776',
+            'uploader_id': 'broncnutz',
+            'upload_date': '20190107',
+            'timestamp': 1546854054,
         },
         'params': {
             'format': '480p',
@@ -48,7 +48,7 @@ class DTubeIE(InfoExtractor):
         def canonical_url(h):
             if not h:
                 return None
-            return 'https://ipfs.io/ipfs/' + h
+            return 'https://video.dtube.top/ipfs/' + h
 
         formats = []
         for q in ('240', '480', '720', '1080', ''):

youtube_dl/extractor/espn.py

@@ -29,7 +29,8 @@ class ESPNIE(OnceIE):
                                     (?:
                                         .*?\?.*?\bid=|
                                         /_/id/
-                                    )
+                                    )|
+                                    [^/]+/video/
                                 )
                             )|
                             (?:www\.)espnfc\.(?:com|us)/(?:video/)?[^/]+/\d+/video/
@@ -94,6 +95,9 @@ class ESPNIE(OnceIE):
     }, {
         'url': 'http://www.espnfc.com/english-premier-league/23/video/3324163/premier-league-in-90-seconds-golden-tweets',
         'only_matching': True,
+    }, {
+        'url': 'http://www.espn.com/espnw/video/26066627/arkansas-gibson-completes-hr-cycle-four-innings',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/extractors.py

@@ -411,6 +411,7 @@ from .funk import (
 from .funnyordie import FunnyOrDieIE
 from .fusion import FusionIE
 from .fxnetworks import FXNetworksIE
+from .gaia import GaiaIE
 from .gameinformer import GameInformerIE
 from .gameone import (
     GameOneIE,
@@ -451,6 +452,7 @@ from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
 from .hgtv import HGTVComShowIE
+from .hketv import HKETVIE
 from .hidive import HiDiveIE
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
@@ -469,6 +471,10 @@ from .hrti import (
 )
 from .huajiao import HuajiaoIE
 from .huffpost import HuffPostIE
+from .hungama import (
+    HungamaIE,
+    HungamaSongIE,
+)
 from .hypem import HypemIE
 from .iconosquare import IconosquareIE
 from .ign import (
@@ -489,7 +495,11 @@ from .ina import InaIE
 from .inc import IncIE
 from .indavideo import IndavideoEmbedIE
 from .infoq import InfoQIE
-from .instagram import InstagramIE, InstagramUserIE
+from .instagram import (
+    InstagramIE,
+    InstagramUserIE,
+    InstagramTagIE,
+)
 from .internazionale import InternazionaleIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
@@ -557,6 +567,7 @@ from .lecture2go import Lecture2GoIE
 from .lecturio import (
     LecturioIE,
     LecturioCourseIE,
+    LecturioDeCourseIE,
 )
 from .leeco import (
     LeIE,
@@ -582,6 +593,7 @@ from .linkedin import (
     LinkedInLearningIE,
     LinkedInLearningCourseIE,
 )
+from .linuxacademy import LinuxAcademyIE
 from .litv import LiTVIE
 from .liveleak import (
     LiveLeakIE,
@@ -608,6 +620,7 @@ from .mailru import (
     MailRuMusicSearchIE,
 )
 from .makertv import MakerTVIE
+from .malltv import MallTVIE
 from .mangomolo import (
     MangomoloVideoIE,
     MangomoloLiveIE,
@@ -683,8 +696,7 @@ from .myvi import (
 from .myvidster import MyVidsterIE
 from .nationalgeographic import (
     NationalGeographicVideoIE,
-    NationalGeographicIE,
-    NationalGeographicEpisodeGuideIE,
+    NationalGeographicTVIE,
 )
 from .naver import NaverIE
 from .nba import NBAIE
@@ -827,6 +839,7 @@ from .orf import (
     ORFOE1IE,
     ORFIPTVIE,
 )
+from .outsidetv import OutsideTVIE
 from .packtpub import (
     PacktPubIE,
     PacktPubCourseIE,
@@ -855,6 +868,7 @@ from .piksel import PikselIE
 from .pinkbike import PinkbikeIE
 from .pladform import PladformIE
 from .playfm import PlayFMIE
+from .playplustv import PlayPlusTVIE
 from .plays import PlaysTVIE
 from .playtvak import PlaytvakIE
 from .playvid import PlayvidIE
@@ -1046,7 +1060,10 @@ from .southpark import (
     SouthParkEsIE,
     SouthParkNlIE
 )
-from .spankbang import SpankBangIE
+from .spankbang import (
+    SpankBangIE,
+    SpankBangPlaylistIE,
+)
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
@@ -1155,6 +1172,7 @@ from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
+from .trunews import TruNewsIE
 from .trutv import TruTVIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
@@ -1192,13 +1210,15 @@ from .tvnet import TVNetIE
 from .tvnoe import TVNoeIE
 from .tvnow import (
     TVNowIE,
-    TVNowListIE,
+    TVNowNewIE,
+    TVNowSeasonIE,
+    TVNowAnnualIE,
     TVNowShowIE,
 )
 from .tvp import (
     TVPEmbedIE,
     TVPIE,
-    TVPSeriesIE,
+    TVPWebsiteIE,
 )
 from .tvplay import (
     TVPlayIE,
@@ -1348,7 +1368,6 @@ from .voxmedia import (
     VoxMediaVolumeIE,
     VoxMediaIE,
 )
-from .vporn import VpornIE
 from .vrt import VRTIE
 from .vrak import VrakIE
 from .vrv import (
@@ -1362,6 +1381,7 @@ from .vuclip import VuClipIE
 from .vvvvid import VVVVIDIE
 from .vyborymos import VyboryMosIE
 from .vzaar import VzaarIE
+from .wakanim import WakanimIE
 from .walla import WallaIE
 from .washingtonpost import (
     WashingtonPostIE,
@@ -1485,6 +1505,7 @@ from .zattoo import (
     QuantumTVIE,
     QuicklineIE,
     QuicklineLiveIE,
+    SaltTVIE,
     SAKTVIE,
     VTXTVIE,
     WalyTVIE,

youtube_dl/extractor/facebook.py

@@ -424,7 +424,7 @@ class FacebookIE(InfoExtractor):
         uploader = clean_html(get_element_by_id(
             'fbPhotoPageAuthorName', webpage)) or self._search_regex(
             r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader',
-            fatal=False) or self._og_search_title(webpage, fatal=False)
+            default=None) or self._og_search_title(webpage, fatal=False)
         timestamp = int_or_none(self._search_regex(
             r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
             'timestamp', default=None))

youtube_dl/extractor/fox.py

@@ -1,17 +1,20 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
+import uuid
+
 from .adobepass import AdobePassIE
-from .uplynk import UplynkPreplayIE
-from ..compat import compat_str
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_unquote,
+)
 from ..utils import (
-    HEADRequest,
     int_or_none,
     parse_age_limit,
     parse_duration,
     try_get,
     unified_timestamp,
-    update_url_query,
 )
 
 
@@ -31,6 +34,7 @@ class FOXIE(AdobePassIE):
             'upload_date': '20170901',
             'creator': 'FOX',
             'series': 'Gotham',
+            'age_limit': 14,
         },
         'params': {
             'skip_download': True,
@@ -44,48 +48,54 @@ class FOXIE(AdobePassIE):
         'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
         'only_matching': True,
     }]
+    _HOME_PAGE_URL = 'https://www.fox.com/'
+    _API_KEY = 'abdcbed02c124d393b39e818a4312055'
+    _access_token = None
+
+    def _call_api(self, path, video_id, data=None):
+        headers = {
+            'X-Api-Key': self._API_KEY,
+        }
+        if self._access_token:
+            headers['Authorization'] = 'Bearer ' + self._access_token
+        return self._download_json(
+            'https://api2.fox.com/v2.0/' + path,
+            video_id, data=data, headers=headers)
+
+    def _real_initialize(self):
+        if not self._access_token:
+            mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth')
+            if mvpd_auth:
+                self._access_token = (self._parse_json(compat_urllib_parse_unquote(
+                    mvpd_auth.value), None, fatal=False) or {}).get('accessToken')
+            if not self._access_token:
+                self._access_token = self._call_api(
+                    'login', None, json.dumps({
+                        'deviceId': compat_str(uuid.uuid4()),
+                    }).encode())['accessToken']
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        video = self._download_json(
-            'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id,
-            video_id, headers={
-                'apikey': 'abdcbed02c124d393b39e818a4312055',
-                'Content-Type': 'application/json',
-                'Referer': url,
-            })
+        video = self._call_api('vodplayer/' + video_id, video_id)
 
         title = video['name']
-        release_url = video['videoRelease']['url']
-
-        description = video.get('description')
-        duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
-            video.get('duration')) or parse_duration(video.get('duration'))
-        timestamp = unified_timestamp(video.get('datePublished'))
-        rating = video.get('contentRating')
-        age_limit = parse_age_limit(rating)
+        release_url = video['url']
+        m3u8_url = self._download_json(release_url, video_id)['playURL']
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
 
         data = try_get(
             video, lambda x: x['trackingData']['properties'], dict) or {}
 
+        duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
+            video.get('duration')) or parse_duration(video.get('duration'))
+        timestamp = unified_timestamp(video.get('datePublished'))
         creator = data.get('brand') or data.get('network') or video.get('network')
-
         series = video.get('seriesName') or data.get(
             'seriesName') or data.get('show')
-        season_number = int_or_none(video.get('seasonNumber'))
-        episode = video.get('name')
-        episode_number = int_or_none(video.get('episodeNumber'))
-        release_year = int_or_none(video.get('releaseYear'))
-
-        if data.get('authRequired'):
-            resource = self._get_mvpd_resource(
-                'fbc-fox', title, video.get('guid'), rating)
-            release_url = update_url_query(
-                release_url, {
-                    'auth': self._extract_mvpd_auth(
-                        url, video_id, 'fbc-fox', resource)
-                })
 
         subtitles = {}
         for doc_rel in video.get('documentReleases', []):
@@ -98,36 +108,19 @@ class FOXIE(AdobePassIE):
             }]
             break
 
-        info = {
+        return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'formats': formats,
+            'description': video.get('description'),
             'duration': duration,
             'timestamp': timestamp,
-            'age_limit': age_limit,
+            'age_limit': parse_age_limit(video.get('contentRating')),
             'creator': creator,
             'series': series,
-            'season_number': season_number,
-            'episode': episode,
-            'episode_number': episode_number,
-            'release_year': release_year,
+            'season_number': int_or_none(video.get('seasonNumber')),
+            'episode': video.get('name'),
+            'episode_number': int_or_none(video.get('episodeNumber')),
+            'release_year': int_or_none(video.get('releaseYear')),
             'subtitles': subtitles,
         }
-
-        urlh = self._request_webpage(HEADRequest(release_url), video_id)
-        video_url = compat_str(urlh.geturl())
-
-        if UplynkPreplayIE.suitable(video_url):
-            info.update({
-                '_type': 'url_transparent',
-                'url': video_url,
-                'ie_key': UplynkPreplayIE.ie_key(),
-            })
-        else:
-            m3u8_url = self._download_json(release_url, video_id)['playURL']
-            formats = self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4',
-                entry_protocol='m3u8_native', m3u8_id='hls')
-            self._sort_formats(formats)
-            info['formats'] = formats
-        return info

youtube_dl/extractor/francetv.py

@@ -215,7 +215,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
     _TESTS = [{
         'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
         'info_dict': {
-            'id': '162311093',
+            'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1',
             'ext': 'mp4',
             'title': '13h15, le dimanche... - Les mystères de Jésus',
             'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
@@ -271,7 +271,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
 
         catalogue = None
         video_id = self._search_regex(
-            r'data-main-video=(["\'])(?P<id>(?:(?!\1).)+)\1',
+            r'(?:data-main-video\s*=|videoId["\']?\s*[:=])\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
             webpage, 'video id', default=None, group='id')
 
         if not video_id:

youtube_dl/extractor/freespeech.py

@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 
 
 class FreespeechIE(InfoExtractor):
@@ -27,8 +28,4 @@ class FreespeechIE(InfoExtractor):
             r'data-video-url="([^"]+)"',
             webpage, 'youtube url')
 
-        return {
-            '_type': 'url',
-            'url': youtube_url,
-            'ie_key': 'Youtube',
-        }
+        return self.url_result(youtube_url, YoutubeIE.ie_key())

youtube_dl/extractor/funimation.py

@@ -1,6 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import random
+import string
+
 from .common import InfoExtractor
 from ..compat import compat_HTTPError
 from ..utils import (
@@ -87,7 +90,7 @@ class FunimationIE(InfoExtractor):
 
         video_id = title_data.get('id') or self._search_regex([
             r"KANE_customdimensions.videoID\s*=\s*'(\d+)';",
-            r'<iframe[^>]+src="/player/(\d+)"',
+            r'<iframe[^>]+src="/player/(\d+)',
         ], webpage, 'video_id', default=None)
         if not video_id:
             player_url = self._html_search_meta([
@@ -108,8 +111,10 @@ class FunimationIE(InfoExtractor):
             if self._TOKEN:
                 headers['Authorization'] = 'Token %s' % self._TOKEN
             sources = self._download_json(
-                'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id,
-                video_id, headers=headers)['items']
+                'https://www.funimation.com/api/showexperience/%s/' % video_id,
+                video_id, headers=headers, query={
+                    'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]),
+                })['items']
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
                 error = self._parse_json(e.cause.read(), video_id)['errors'][0]

youtube_dl/extractor/gaia.py

@@ -0,0 +1,98 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    str_or_none,
+    strip_or_none,
+    try_get,
+)
+
+
+class GaiaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gaia\.com/video/(?P<id>[^/?]+).*?\bfullplayer=(?P<type>feature|preview)'
+    _TESTS = [{
+        'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=feature',
+        'info_dict': {
+            'id': '89356',
+            'ext': 'mp4',
+            'title': 'Connecting with Universal Consciousness',
+            'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
+            'upload_date': '20151116',
+            'timestamp': 1447707266,
+            'duration': 936,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=preview',
+        'info_dict': {
+            'id': '89351',
+            'ext': 'mp4',
+            'title': 'Connecting with Universal Consciousness',
+            'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
+            'upload_date': '20151116',
+            'timestamp': 1447707266,
+            'duration': 53,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id, vtype = re.search(self._VALID_URL, url).groups()
+        node_id = self._download_json(
+            'https://brooklyn.gaia.com/pathinfo', display_id, query={
+                'path': 'video/' + display_id,
+            })['id']
+        node = self._download_json(
+            'https://brooklyn.gaia.com/node/%d' % node_id, node_id)
+        vdata = node[vtype]
+        media_id = compat_str(vdata['nid'])
+        title = node['title']
+
+        media = self._download_json(
+            'https://brooklyn.gaia.com/media/' + media_id, media_id)
+        formats = self._extract_m3u8_formats(
+            media['mediaUrls']['bcHLS'], media_id, 'mp4')
+        self._sort_formats(formats)
+
+        subtitles = {}
+        text_tracks = media.get('textTracks', {})
+        for key in ('captions', 'subtitles'):
+            for lang, sub_url in text_tracks.get(key, {}).items():
+                subtitles.setdefault(lang, []).append({
+                    'url': sub_url,
+                })
+
+        fivestar = node.get('fivestar', {})
+        fields = node.get('fields', {})
+
+        def get_field_value(key, value_key='value'):
+            return try_get(fields, lambda x: x[key][0][value_key])
+
+        return {
+            'id': media_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'description': strip_or_none(get_field_value('body') or get_field_value('teaser')),
+            'timestamp': int_or_none(node.get('created')),
+            'subtitles': subtitles,
+            'duration': int_or_none(vdata.get('duration')),
+            'like_count': int_or_none(try_get(fivestar, lambda x: x['up_count']['value'])),
+            'dislike_count': int_or_none(try_get(fivestar, lambda x: x['down_count']['value'])),
+            'comment_count': int_or_none(node.get('comment_count')),
+            'series': try_get(node, lambda x: x['series']['title'], compat_str),
+            'season_number': int_or_none(get_field_value('season')),
+            'season_id': str_or_none(get_field_value('series_nid', 'nid')),
+            'episode_number': int_or_none(get_field_value('episode')),
+        }

youtube_dl/extractor/generic.py

@@ -2197,10 +2197,7 @@ class GenericIE(InfoExtractor):
 
     def _real_extract(self, url):
         if url.startswith('//'):
-            return {
-                '_type': 'url',
-                'url': self.http_scheme() + url,
-            }
+            return self.url_result(self.http_scheme() + url)
 
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:

youtube_dl/extractor/globo.py

@@ -72,7 +72,7 @@ class GloboIE(InfoExtractor):
             return
 
         try:
-            self._download_json(
+            glb_id = (self._download_json(
                 'https://login.globo.com/api/authentication', None, data=json.dumps({
                     'payload': {
                         'email': email,
@@ -81,7 +81,9 @@ class GloboIE(InfoExtractor):
                     },
                 }).encode(), headers={
                     'Content-Type': 'application/json; charset=utf-8',
-                })
+                }) or {}).get('glbId')
+            if glb_id:
+                self._set_cookie('.globo.com', 'GLBID', glb_id)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
                 resp = self._parse_json(e.cause.read(), None)

youtube_dl/extractor/go.py

@@ -25,15 +25,15 @@ class GoIE(AdobePassIE):
         },
         'watchdisneychannel': {
             'brand': '004',
-            'requestor_id': 'Disney',
+            'resource_id': 'Disney',
         },
         'watchdisneyjunior': {
             'brand': '008',
-            'requestor_id': 'DisneyJunior',
+            'resource_id': 'DisneyJunior',
         },
         'watchdisneyxd': {
             'brand': '009',
-            'requestor_id': 'DisneyXD',
+            'resource_id': 'DisneyXD',
         }
     }
     _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
@@ -130,8 +130,8 @@ class GoIE(AdobePassIE):
                     'device': '001',
                 }
                 if video_data.get('accesslevel') == '1':
-                    requestor_id = site_info['requestor_id']
-                    resource = self._get_mvpd_resource(
+                    requestor_id = site_info.get('requestor_id', 'DisneyChannels')
+                    resource = site_info.get('resource_id') or self._get_mvpd_resource(
                         requestor_id, title, video_id, None)
                     auth = self._extract_mvpd_auth(
                         url, video_id, requestor_id, resource)

youtube_dl/extractor/hketv.py

@@ -0,0 +1,191 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    int_or_none,
+    merge_dicts,
+    parse_count,
+    str_or_none,
+    try_get,
+    unified_strdate,
+    urlencode_postdata,
+    urljoin,
+)
+
+
+class HKETVIE(InfoExtractor):
+    IE_NAME = 'hketv'
+    IE_DESC = '香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau'
+    _GEO_BYPASS = False
+    _GEO_COUNTRIES = ['HK']
+    _VALID_URL = r'https?://(?:www\.)?hkedcity\.net/etv/resource/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.hkedcity.net/etv/resource/2932360618',
+        'md5': 'f193712f5f7abb208ddef3c5ea6ed0b7',
+        'info_dict': {
+            'id': '2932360618',
+            'ext': 'mp4',
+            'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)',
+            'description': 'md5:d5286d05219ef50e0613311cbe96e560',
+            'upload_date': '20181024',
+            'duration': 900,
+            'subtitles': 'count:2',
+        },
+        'skip': 'Geo restricted to HK',
+    }, {
+        'url': 'https://www.hkedcity.net/etv/resource/972641418',
+        'md5': '1ed494c1c6cf7866a8290edad9b07dc9',
+        'info_dict': {
+            'id': '972641418',
+            'ext': 'mp4',
+            'title': '衣冠楚楚 (天使系列之一)',
+            'description': 'md5:10bb3d659421e74f58e5db5691627b0f',
+            'upload_date': '20070109',
+            'duration': 907,
+            'subtitles': {},
+        },
+        'params': {
+            'geo_verification_proxy': '<HK proxy here>',
+        },
+        'skip': 'Geo restricted to HK',
+    }]
+
+    _CC_LANGS = {
+        '中文（繁體中文）': 'zh-Hant',
+        '中文（简体中文）': 'zh-Hans',
+        'English': 'en',
+        'Bahasa Indonesia': 'id',
+        '\u0939\u093f\u0928\u094d\u0926\u0940': 'hi',
+        '\u0928\u0947\u092a\u093e\u0932\u0940': 'ne',
+        'Tagalog': 'tl',
+        '\u0e44\u0e17\u0e22': 'th',
+        '\u0627\u0631\u062f\u0648': 'ur',
+    }
+    _FORMAT_HEIGHTS = {
+        'SD': 360,
+        'HD': 720,
+    }
+    _APPS_BASE_URL = 'https://apps.hkedcity.net'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = (
+            self._html_search_meta(
+                ('ed_title', 'search.ed_title'), webpage, default=None) or
+            self._search_regex(
+                r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'title', default=None, group='url') or
+            self._html_search_regex(
+                r'<h1>([^<]+)</h1>', webpage, 'title', default=None) or
+            self._og_search_title(webpage)
+        )
+
+        file_id = self._search_regex(
+            r'post_var\[["\']file_id["\']\s*\]\s*=\s*(.+?);',
+            webpage, 'file ID')
+        curr_url = self._search_regex(
+            r'post_var\[["\']curr_url["\']\s*\]\s*=\s*"(.+?)";',
+            webpage, 'curr URL')
+        data = {
+            'action': 'get_info',
+            'curr_url': curr_url,
+            'file_id': file_id,
+            'video_url': file_id,
+        }
+
+        response = self._download_json(
+            self._APPS_BASE_URL + '/media/play/handler.php', video_id,
+            data=urlencode_postdata(data),
+            headers=merge_dicts({
+                'Content-Type': 'application/x-www-form-urlencoded'},
+                self.geo_verification_headers()))
+
+        result = response['result']
+
+        if not response.get('success') or not response.get('access'):
+            error = clean_html(response.get('access_err_msg'))
+            if 'Video streaming is not available in your country' in error:
+                self.raise_geo_restricted(
+                    msg=error, countries=self._GEO_COUNTRIES)
+            else:
+                raise ExtractorError(error, expected=True)
+
+        formats = []
+
+        width = int_or_none(result.get('width'))
+        height = int_or_none(result.get('height'))
+
+        playlist0 = result['playlist'][0]
+        for fmt in playlist0['sources']:
+            file_url = urljoin(self._APPS_BASE_URL, fmt.get('file'))
+            if not file_url:
+                continue
+            # If we ever wanted to provide the final resolved URL that
+            # does not require cookies, albeit with a shorter lifespan:
+            #     urlh = self._downloader.urlopen(file_url)
+            #     resolved_url = urlh.geturl()
+            label = fmt.get('label')
+            h = self._FORMAT_HEIGHTS.get(label)
+            w = h * width // height if h and width and height else None
+            formats.append({
+                'format_id': label,
+                'ext': fmt.get('type'),
+                'url': file_url,
+                'width': w,
+                'height': h,
+            })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        tracks = try_get(playlist0, lambda x: x['tracks'], list) or []
+        for track in tracks:
+            if not isinstance(track, dict):
+                continue
+            track_kind = str_or_none(track.get('kind'))
+            if not track_kind or not isinstance(track_kind, compat_str):
+                continue
+            if track_kind.lower() not in ('captions', 'subtitles'):
+                continue
+            track_url = urljoin(self._APPS_BASE_URL, track.get('file'))
+            if not track_url:
+                continue
+            track_label = track.get('label')
+            subtitles.setdefault(self._CC_LANGS.get(
+                track_label, track_label), []).append({
+                    'url': self._proto_relative_url(track_url),
+                    'ext': 'srt',
+                })
+
+        # Likes
+        emotion = self._download_json(
+            'https://emocounter.hkedcity.net/handler.php', video_id,
+            data=urlencode_postdata({
+                'action': 'get_emotion',
+                'data[bucket_id]': 'etv',
+                'data[identifier]': video_id,
+            }),
+            headers={'Content-Type': 'application/x-www-form-urlencoded'},
+            fatal=False) or {}
+        like_count = int_or_none(try_get(
+            emotion, lambda x: x['data']['emotion_data'][0]['count']))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta(
+                'description', webpage, fatal=False),
+            'upload_date': unified_strdate(self._html_search_meta(
+                'ed_date', webpage, fatal=False), day_first=False),
+            'duration': int_or_none(result.get('length')),
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnail': urljoin(self._APPS_BASE_URL, result.get('image')),
+            'view_count': parse_count(result.get('view_count')),
+            'like_count': like_count,
+        }

youtube_dl/extractor/hungama.py

@@ -0,0 +1,117 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    urlencode_postdata,
+)
+
+
+class HungamaIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?hungama\.com/
+                        (?:
+                            (?:video|movie)/[^/]+/|
+                            tv-show/(?:[^/]+/){2}\d+/episode/[^/]+/
+                        )
+                        (?P<id>\d+)
+                    '''
+    _TESTS = [{
+        'url': 'http://www.hungama.com/video/krishna-chants/39349649/',
+        'md5': 'a845a6d1ebd08d80c1035126d49bd6a0',
+        'info_dict': {
+            'id': '2931166',
+            'ext': 'mp4',
+            'title': 'Lucky Ali - Kitni Haseen Zindagi',
+            'track': 'Kitni Haseen Zindagi',
+            'artist': 'Lucky Ali',
+            'album': 'Aks',
+            'release_year': 2000,
+        }
+    }, {
+        'url': 'https://www.hungama.com/movie/kahaani-2/44129919/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.hungama.com/tv-show/padded-ki-pushup/season-1/44139461/episode/ep-02-training-sasu-pathlaag-karing/44139503/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        info = self._search_json_ld(webpage, video_id)
+
+        m3u8_url = self._download_json(
+            'https://www.hungama.com/index.php', video_id,
+            data=urlencode_postdata({'content_id': video_id}), headers={
+                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                'X-Requested-With': 'XMLHttpRequest',
+            }, query={
+                'c': 'common',
+                'm': 'get_video_mdn_url',
+            })['stream_url']
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+        self._sort_formats(formats)
+
+        info.update({
+            'id': video_id,
+            'formats': formats,
+        })
+        return info
+
+
+class HungamaSongIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/',
+        'md5': 'a845a6d1ebd08d80c1035126d49bd6a0',
+        'info_dict': {
+            'id': '2931166',
+            'ext': 'mp4',
+            'title': 'Lucky Ali - Kitni Haseen Zindagi',
+            'track': 'Kitni Haseen Zindagi',
+            'artist': 'Lucky Ali',
+            'album': 'Aks',
+            'release_year': 2000,
+        }
+    }
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+
+        data = self._download_json(
+            'https://www.hungama.com/audio-player-data/track/%s' % audio_id,
+            audio_id, query={'_country': 'IN'})[0]
+
+        track = data['song_name']
+        artist = data.get('singer_name')
+
+        m3u8_url = self._download_json(
+            data.get('file') or data['preview_link'],
+            audio_id)['response']['media_url']
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, audio_id, ext='mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+        self._sort_formats(formats)
+
+        title = '%s - %s' % (artist, track) if artist else track
+        thumbnail = data.get('img_src') or data.get('album_image')
+
+        return {
+            'id': audio_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'track': track,
+            'artist': artist,
+            'album': data.get('album_name'),
+            'release_year': int_or_none(data.get('date')),
+            'formats': formats,
+        }

youtube_dl/extractor/imgur.py

@@ -27,6 +27,10 @@ class ImgurIE(InfoExtractor):
     }, {
         'url': 'https://i.imgur.com/crGpqCV.mp4',
         'only_matching': True,
+    }, {
+        # no title
+        'url': 'https://i.imgur.com/jxBXAMC.gifv',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -87,7 +91,7 @@ class ImgurIE(InfoExtractor):
         return {
             'id': video_id,
             'formats': formats,
-            'title': self._og_search_title(webpage),
+            'title': self._og_search_title(webpage, default=video_id),
         }
 
 

youtube_dl/extractor/instagram.py

@@ -227,44 +227,37 @@ class InstagramIE(InfoExtractor):
         }
 
 
-class InstagramUserIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])'
-    IE_DESC = 'Instagram user profile'
-    IE_NAME = 'instagram:user'
-    _TEST = {
-        'url': 'https://instagram.com/porsche',
-        'info_dict': {
-            'id': 'porsche',
-            'title': 'porsche',
-        },
-        'playlist_count': 5,
-        'params': {
-            'extract_flat': True,
-            'skip_download': True,
-            'playlistend': 5,
-        }
-    }
+class InstagramPlaylistIE(InfoExtractor):
+    # A superclass for handling any kind of query based on GraphQL which
+    # results in a playlist.
 
-    _gis_tmpl = None
+    _gis_tmpl = None  # used to cache GIS request type
 
-    def _entries(self, data):
+    def _parse_graphql(self, webpage, item_id):
+        # Reads a webpage and returns its GraphQL data.
+        return self._parse_json(
+            self._search_regex(
+                r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'),
+            item_id)
+
+    def _extract_graphql(self, data, url):
+        # Parses GraphQL queries containing videos and generates a playlist.
         def get_count(suffix):
             return int_or_none(try_get(
                 node, lambda x: x['edge_media_' + suffix]['count']))
 
-        uploader_id = data['entry_data']['ProfilePage'][0]['graphql']['user']['id']
+        uploader_id = self._match_id(url)
         csrf_token = data['config']['csrf_token']
         rhx_gis = data.get('rhx_gis') or '3c7ca9dcefcf966d11dacf1f151335e8'
 
-        self._set_cookie('instagram.com', 'ig_pr', '1')
-
         cursor = ''
         for page_num in itertools.count(1):
-            variables = json.dumps({
-                'id': uploader_id,
+            variables = {
                 'first': 12,
                 'after': cursor,
-            })
+            }
+            variables.update(self._query_vars_for(data))
+            variables = json.dumps(variables)
 
             if self._gis_tmpl:
                 gis_tmpls = [self._gis_tmpl]
@@ -276,21 +269,26 @@ class InstagramUserIE(InfoExtractor):
                     '%s:%s:%s' % (rhx_gis, csrf_token, std_headers['User-Agent']),
                 ]
 
+            # try all of the ways to generate a GIS query, and not only use the
+            # first one that works, but cache it for future requests
             for gis_tmpl in gis_tmpls:
                 try:
-                    media = self._download_json(
+                    json_data = self._download_json(
                         'https://www.instagram.com/graphql/query/', uploader_id,
                         'Downloading JSON page %d' % page_num, headers={
                             'X-Requested-With': 'XMLHttpRequest',
                             'X-Instagram-GIS': hashlib.md5(
                                 ('%s:%s' % (gis_tmpl, variables)).encode('utf-8')).hexdigest(),
                         }, query={
-                            'query_hash': '42323d64886122307be10013ad2dcc44',
+                            'query_hash': self._QUERY_HASH,
                             'variables': variables,
-                        })['data']['user']['edge_owner_to_timeline_media']
+                        })
+                    media = self._parse_timeline_from(json_data)
                     self._gis_tmpl = gis_tmpl
                     break
                 except ExtractorError as e:
+                    # if it's an error caused by a bad query, and there are
+                    # more GIS templates to try, ignore it and keep trying
                     if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
                         if gis_tmpl != gis_tmpls[-1]:
                             continue
@@ -348,14 +346,80 @@ class InstagramUserIE(InfoExtractor):
                 break
 
     def _real_extract(self, url):
-        username = self._match_id(url)
+        user_or_tag = self._match_id(url)
+        webpage = self._download_webpage(url, user_or_tag)
+        data = self._parse_graphql(webpage, user_or_tag)
 
-        webpage = self._download_webpage(url, username)
-
-        data = self._parse_json(
-            self._search_regex(
-                r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'),
-            username)
+        self._set_cookie('instagram.com', 'ig_pr', '1')
 
         return self.playlist_result(
-            self._entries(data), username, username)
+            self._extract_graphql(data, url), user_or_tag, user_or_tag)
+
+
+class InstagramUserIE(InstagramPlaylistIE):
+    _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])'
+    IE_DESC = 'Instagram user profile'
+    IE_NAME = 'instagram:user'
+    _TEST = {
+        'url': 'https://instagram.com/porsche',
+        'info_dict': {
+            'id': 'porsche',
+            'title': 'porsche',
+        },
+        'playlist_count': 5,
+        'params': {
+            'extract_flat': True,
+            'skip_download': True,
+            'playlistend': 5,
+        }
+    }
+
+    _QUERY_HASH = '42323d64886122307be10013ad2dcc44',
+
+    @staticmethod
+    def _parse_timeline_from(data):
+        # extracts the media timeline data from a GraphQL result
+        return data['data']['user']['edge_owner_to_timeline_media']
+
+    @staticmethod
+    def _query_vars_for(data):
+        # returns a dictionary of variables to add to the timeline query based
+        # on the GraphQL of the original page
+        return {
+            'id': data['entry_data']['ProfilePage'][0]['graphql']['user']['id']
+        }
+
+
+class InstagramTagIE(InstagramPlaylistIE):
+    _VALID_URL = r'https?://(?:www\.)?instagram\.com/explore/tags/(?P<id>[^/]+)'
+    IE_DESC = 'Instagram hashtag search'
+    IE_NAME = 'instagram:tag'
+    _TEST = {
+        'url': 'https://instagram.com/explore/tags/lolcats',
+        'info_dict': {
+            'id': 'lolcats',
+            'title': 'lolcats',
+        },
+        'playlist_count': 50,
+        'params': {
+            'extract_flat': True,
+            'skip_download': True,
+            'playlistend': 50,
+        }
+    }
+
+    _QUERY_HASH = 'f92f56d47dc7a55b606908374b43a314',
+
+    @staticmethod
+    def _parse_timeline_from(data):
+        # extracts the media timeline data from a GraphQL result
+        return data['data']['hashtag']['edge_hashtag_to_media']
+
+    @staticmethod
+    def _query_vars_for(data):
+        # returns a dictionary of variables to add to the timeline query based
+        # on the GraphQL of the original page
+        return {
+            'tag_name':
+                data['entry_data']['TagPage'][0]['graphql']['hashtag']['name']
+        }

youtube_dl/extractor/jwplatform.py

@@ -7,8 +7,8 @@ from .common import InfoExtractor
 
 
 class JWPlatformIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
-    _TEST = {
+    _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
+    _TESTS = [{
         'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
         'md5': 'fa8899fa601eb7c83a64e9d568bdf325',
         'info_dict': {
@@ -19,7 +19,10 @@ class JWPlatformIE(InfoExtractor):
             'upload_date': '20081127',
             'timestamp': 1227796140,
         }
-    }
+    }, {
+        'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js',
+        'only_matching': True,
+    }]
 
     @staticmethod
     def _extract_url(webpage):
@@ -34,5 +37,5 @@ class JWPlatformIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id)
+        json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id)
         return self._parse_jwplayer_data(json_data, video_id)

youtube_dl/extractor/lecturio.py

@@ -64,8 +64,14 @@ class LecturioBaseIE(InfoExtractor):
 
 
 class LecturioIE(LecturioBaseIE):
-    _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture'
-    _TEST = {
+    _VALID_URL = r'''(?x)
+                    https://
+                        (?:
+                            app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture|
+                            (?:www\.)?lecturio\.de/[^/]+/(?P<id_de>[^/?#&]+)\.vortrag
+                        )
+                    '''
+    _TESTS = [{
         'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
         'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870',
         'info_dict': {
@@ -74,7 +80,10 @@ class LecturioIE(LecturioBaseIE):
             'title': 'Important Concepts and Terms – Introduction to Microbiology',
         },
         'skip': 'Requires lecturio account credentials',
-    }
+    }, {
+        'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
+        'only_matching': True,
+    }]
 
     _CC_LANGS = {
         'German': 'de',
@@ -86,7 +95,8 @@ class LecturioIE(LecturioBaseIE):
     }
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id') or mobj.group('id_de')
 
         webpage = self._download_webpage(
             'https://app.lecturio.com/en/lecture/%s/player.html' % display_id,
@@ -190,3 +200,30 @@ class LecturioCourseIE(LecturioBaseIE):
             'title', default=None)
 
         return self.playlist_result(entries, display_id, title)
+
+
+class LecturioDeCourseIE(LecturioBaseIE):
+    _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
+    _TEST = {
+        'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        entries = []
+        for mobj in re.finditer(
+                r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
+                webpage):
+            lecture_url = urljoin(url, mobj.group('url'))
+            lecture_id = mobj.group('id')
+            entries.append(self.url_result(
+                lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
+
+        title = self._search_regex(
+            r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)
+
+        return self.playlist_result(entries, display_id, title)

youtube_dl/extractor/libsyn.py

@@ -1,12 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
+    clean_html,
+    get_element_by_class,
     parse_duration,
+    strip_or_none,
     unified_strdate,
 )
 
@@ -21,7 +23,9 @@ class LibsynIE(InfoExtractor):
             'id': '6385796',
             'ext': 'mp3',
             'title': "Champion Minded - Developing a Growth Mindset",
-            'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
+            # description fetched using another request:
+            # http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
+            # 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
             'upload_date': '20180320',
             'thumbnail': 're:^https?://.*',
         },
@@ -38,22 +42,36 @@ class LibsynIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('id')
-        url = m.group('mainurl')
+        url, video_id = re.match(self._VALID_URL, url).groups()
         webpage = self._download_webpage(url, video_id)
 
-        podcast_title = self._search_regex(
-            r'<h3>([^<]+)</h3>', webpage, 'podcast title', default=None)
-        if podcast_title:
-            podcast_title = podcast_title.strip()
-        episode_title = self._search_regex(
-            r'(?:<div class="episode-title">|<h4>)([^<]+)</', webpage, 'episode title')
-        if episode_title:
-            episode_title = episode_title.strip()
+        data = self._parse_json(self._search_regex(
+            r'var\s+playlistItem\s*=\s*({.+?});',
+            webpage, 'JSON data block'), video_id)
+
+        episode_title = data.get('item_title') or get_element_by_class('episode-title', webpage)
+        if not episode_title:
+            self._search_regex(
+                [r'data-title="([^"]+)"', r'<title>(.+?)</title>'],
+                webpage, 'episode title')
+        episode_title = episode_title.strip()
+
+        podcast_title = strip_or_none(clean_html(self._search_regex(
+            r'<h3>([^<]+)</h3>', webpage, 'podcast title',
+            default=None) or get_element_by_class('podcast-title', webpage)))
 
         title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
 
+        formats = []
+        for k, format_id in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')):
+            f_url = data.get(k)
+            if not f_url:
+                continue
+            formats.append({
+                'url': f_url,
+                'format_id': format_id,
+            })
+
         description = self._html_search_regex(
             r'<p\s+id="info_text_body">(.+?)</p>', webpage,
             'description', default=None)
@@ -61,27 +79,15 @@ class LibsynIE(InfoExtractor):
             # Strip non-breaking and normal spaces
             description = description.replace('\u00A0', ' ').strip()
         release_date = unified_strdate(self._search_regex(
-            r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
-
-        data_json = self._search_regex(r'var\s+playlistItem\s*=\s*(\{.*?\});\n', webpage, 'JSON data block')
-        data = json.loads(data_json)
-
-        formats = [{
-            'url': data['media_url'],
-            'format_id': 'main',
-        }, {
-            'url': data['media_url_libsyn'],
-            'format_id': 'libsyn',
-        }]
-        thumbnail = data.get('thumbnail_url')
-        duration = parse_duration(data.get('duration'))
+            r'<div class="release_date">Released: ([^<]+)<',
+            webpage, 'release date', default=None) or data.get('release_date'))
 
         return {
             'id': video_id,
             'title': title,
             'description': description,
-            'thumbnail': thumbnail,
+            'thumbnail': data.get('thumbnail_url'),
             'upload_date': release_date,
-            'duration': duration,
+            'duration': parse_duration(data.get('duration')),
             'formats': formats,
         }

youtube_dl/extractor/linkedin.py

@@ -34,12 +34,15 @@ class LinkedInLearningBaseIE(InfoExtractor):
                 'Csrf-Token': self._get_cookies(api_url)['JSESSIONID'].value,
             }, query=query)['elements'][0]
 
-    def _get_video_id(self, urn, course_slug, video_slug):
+    def _get_urn_id(self, video_data):
+        urn = video_data.get('urn')
         if urn:
             mobj = re.search(r'urn:li:lyndaCourse:\d+,(\d+)', urn)
             if mobj:
                 return mobj.group(1)
-        return '%s/%s' % (course_slug, video_slug)
+
+    def _get_video_id(self, video_data, course_slug, video_slug):
+        return self._get_urn_id(video_data) or '%s/%s' % (course_slug, video_slug)
 
     def _real_initialize(self):
         email, password = self._get_login_info()
@@ -123,7 +126,7 @@ class LinkedInLearningIE(LinkedInLearningBaseIE):
         self._sort_formats(formats, ('width', 'height', 'source_preference', 'tbr', 'abr'))
 
         return {
-            'id': self._get_video_id(video_data.get('urn'), course_slug, video_slug),
+            'id': self._get_video_id(video_data, course_slug, video_slug),
             'title': title,
             'formats': formats,
             'thumbnail': video_data.get('defaultThumbnail'),
@@ -154,18 +157,21 @@ class LinkedInLearningCourseIE(LinkedInLearningBaseIE):
         course_data = self._call_api(course_slug, 'chapters,description,title')
 
         entries = []
-        for chapter in course_data.get('chapters', []):
+        for chapter_number, chapter in enumerate(course_data.get('chapters', []), 1):
             chapter_title = chapter.get('title')
+            chapter_id = self._get_urn_id(chapter)
             for video in chapter.get('videos', []):
                 video_slug = video.get('slug')
                 if not video_slug:
                     continue
                 entries.append({
                     '_type': 'url_transparent',
-                    'id': self._get_video_id(video.get('urn'), course_slug, video_slug),
+                    'id': self._get_video_id(video, course_slug, video_slug),
                     'title': video.get('title'),
                     'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug),
                     'chapter': chapter_title,
+                    'chapter_number': chapter_number,
+                    'chapter_id': chapter_id,
                     'ie_key': LinkedInLearningIE.ie_key(),
                 })
 

youtube_dl/extractor/linuxacademy.py

@@ -0,0 +1,174 @@
+from __future__ import unicode_literals
+
+import json
+import random
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_b64decode,
+    compat_HTTPError,
+    compat_str,
+)
+from ..utils import (
+    ExtractorError,
+    orderedSet,
+    unescapeHTML,
+    urlencode_postdata,
+    urljoin,
+)
+
+
+class LinuxAcademyIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?linuxacademy\.com/cp/
+                        (?:
+                            courses/lesson/course/(?P<chapter_id>\d+)/lesson/(?P<lesson_id>\d+)|
+                            modules/view/id/(?P<course_id>\d+)
+                        )
+                    '''
+    _TESTS = [{
+        'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2/module/154',
+        'info_dict': {
+            'id': '1498-2',
+            'ext': 'mp4',
+            'title': "Introduction to the Practitioner's Brief",
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'skip': 'Requires Linux Academy account credentials',
+    }, {
+        'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2',
+        'only_matching': True,
+    }, {
+        'url': 'https://linuxacademy.com/cp/modules/view/id/154',
+        'info_dict': {
+            'id': '154',
+            'title': 'AWS Certified Cloud Practitioner',
+            'description': 'md5:039db7e60e4aac9cf43630e0a75fa834',
+        },
+        'playlist_count': 41,
+        'skip': 'Requires Linux Academy account credentials',
+    }]
+
+    _AUTHORIZE_URL = 'https://login.linuxacademy.com/authorize'
+    _ORIGIN_URL = 'https://linuxacademy.com'
+    _CLIENT_ID = 'KaWxNn1C2Gc7n83W9OFeXltd8Utb5vvx'
+    _NETRC_MACHINE = 'linuxacademy'
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        username, password = self._get_login_info()
+        if username is None:
+            return
+
+        def random_string():
+            return ''.join([
+                random.choice('0123456789ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz-._~')
+                for _ in range(32)])
+
+        webpage, urlh = self._download_webpage_handle(
+            self._AUTHORIZE_URL, None, 'Downloading authorize page', query={
+                'client_id': self._CLIENT_ID,
+                'response_type': 'token id_token',
+                'redirect_uri': self._ORIGIN_URL,
+                'scope': 'openid email user_impersonation profile',
+                'audience': self._ORIGIN_URL,
+                'state': random_string(),
+                'nonce': random_string(),
+            })
+
+        login_data = self._parse_json(
+            self._search_regex(
+                r'atob\(\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+                'login info', group='value'), None,
+            transform_source=lambda x: compat_b64decode(x).decode('utf-8')
+        )['extraParams']
+
+        login_data.update({
+            'client_id': self._CLIENT_ID,
+            'redirect_uri': self._ORIGIN_URL,
+            'tenant': 'lacausers',
+            'connection': 'Username-Password-Authentication',
+            'username': username,
+            'password': password,
+            'sso': 'true',
+        })
+
+        login_state_url = compat_str(urlh.geturl())
+
+        try:
+            login_page = self._download_webpage(
+                'https://login.linuxacademy.com/usernamepassword/login', None,
+                'Downloading login page', data=json.dumps(login_data).encode(),
+                headers={
+                    'Content-Type': 'application/json',
+                    'Origin': 'https://login.linuxacademy.com',
+                    'Referer': login_state_url,
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                error = self._parse_json(e.cause.read(), None)
+                message = error.get('description') or error['code']
+                raise ExtractorError(
+                    '%s said: %s' % (self.IE_NAME, message), expected=True)
+            raise
+
+        callback_page, urlh = self._download_webpage_handle(
+            'https://login.linuxacademy.com/login/callback', None,
+            'Downloading callback page',
+            data=urlencode_postdata(self._hidden_inputs(login_page)),
+            headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+                'Origin': 'https://login.linuxacademy.com',
+                'Referer': login_state_url,
+            })
+
+        access_token = self._search_regex(
+            r'access_token=([^=&]+)', compat_str(urlh.geturl()),
+            'access token')
+
+        self._download_webpage(
+            'https://linuxacademy.com/cp/login/tokenValidateLogin/token/%s'
+            % access_token, None, 'Downloading token validation page')
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        chapter_id, lecture_id, course_id = mobj.group('chapter_id', 'lesson_id', 'course_id')
+        item_id = course_id if course_id else '%s-%s' % (chapter_id, lecture_id)
+
+        webpage = self._download_webpage(url, item_id)
+
+        # course path
+        if course_id:
+            entries = [
+                self.url_result(
+                    urljoin(url, lesson_url), ie=LinuxAcademyIE.ie_key())
+                for lesson_url in orderedSet(re.findall(
+                    r'<a[^>]+\bhref=["\'](/cp/courses/lesson/course/\d+/lesson/\d+/module/\d+)',
+                    webpage))]
+            title = unescapeHTML(self._html_search_regex(
+                (r'class=["\']course-title["\'][^>]*>(?P<value>[^<]+)',
+                 r'var\s+title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'),
+                webpage, 'title', default=None, group='value'))
+            description = unescapeHTML(self._html_search_regex(
+                r'var\s+description\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+                webpage, 'description', default=None, group='value'))
+            return self.playlist_result(entries, course_id, title, description)
+
+        # single video path
+        info = self._extract_jwplayer_data(
+            webpage, item_id, require_title=False, m3u8_id='hls',)
+        title = self._search_regex(
+            (r'>Lecture\s*:\s*(?P<value>[^<]+)',
+             r'lessonName\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+            'title', group='value')
+        info.update({
+            'id': item_id,
+            'title': title,
+        })
+        return info

youtube_dl/extractor/liveleak.py

@@ -87,7 +87,7 @@ class LiveLeakIE(InfoExtractor):
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"',
+            r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[ift]=[\w_]+[^"]+)"',
             webpage)
 
     def _real_extract(self, url):
@@ -120,13 +120,27 @@ class LiveLeakIE(InfoExtractor):
             }
 
         for idx, info_dict in enumerate(entries):
+            formats = []
             for a_format in info_dict['formats']:
                 if not a_format.get('height'):
                     a_format['height'] = int_or_none(self._search_regex(
                         r'([0-9]+)p\.mp4', a_format['url'], 'height label',
                         default=None))
+                formats.append(a_format)
 
-            self._sort_formats(info_dict['formats'])
+                # Removing '.*.mp4' gives the raw video, which is essentially
+                # the same video without the LiveLeak logo at the top (see
+                # https://github.com/rg3/youtube-dl/pull/4768)
+                orig_url = re.sub(r'\.mp4\.[^.]+', '', a_format['url'])
+                if a_format['url'] != orig_url:
+                    format_id = a_format.get('format_id')
+                    formats.append({
+                        'format_id': 'original' + ('-' + format_id if format_id else ''),
+                        'url': orig_url,
+                        'preference': 1,
+                    })
+            self._sort_formats(formats)
+            info_dict['formats'] = formats
 
             # Don't append entry ID for one-video pages to keep backward compatibility
             if len(entries) > 1:
@@ -146,7 +160,7 @@ class LiveLeakIE(InfoExtractor):
 
 
 class LiveLeakEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[if])=(?P<id>[\w_]+)'
+    _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[ift])=(?P<id>[\w_]+)'
 
     # See generic.py for actual test cases
     _TESTS = [{
@@ -158,15 +172,14 @@ class LiveLeakEmbedIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        kind, video_id = mobj.group('kind', 'id')
+        kind, video_id = re.match(self._VALID_URL, url).groups()
 
         if kind == 'f':
             webpage = self._download_webpage(url, video_id)
             liveleak_url = self._search_regex(
-                r'logourl\s*:\s*(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL,
+                r'(?:logourl\s*:\s*|window\.open\()(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL,
                 webpage, 'LiveLeak URL', group='url')
-        elif kind == 'i':
-            liveleak_url = 'http://www.liveleak.com/view?i=%s' % video_id
+        else:
+            liveleak_url = 'http://www.liveleak.com/view?%s=%s' % (kind, video_id)
 
         return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key())

youtube_dl/extractor/livestream.py

@@ -363,7 +363,4 @@ class LivestreamShortenerIE(InfoExtractor):
         id = mobj.group('id')
         webpage = self._download_webpage(url, id)
 
-        return {
-            '_type': 'url',
-            'url': self._og_search_url(webpage),
-        }
+        return self.url_result(self._og_search_url(webpage))

youtube_dl/extractor/malltv.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import merge_dicts
+
+
+class MallTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
+        'md5': '1c4a37f080e1f3023103a7b43458e518',
+        'info_dict': {
+            'id': 't0zzt0',
+            'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
+            'ext': 'mp4',
+            'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
+            'description': 'md5:25fc0ec42a72ba602b602c683fa29deb',
+            'duration': 216,
+            'timestamp': 1538870400,
+            'upload_date': '20181007',
+            'view_count': int,
+        }
+    }, {
+        'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            url, display_id, headers=self.geo_verification_headers())
+
+        SOURCE_RE = r'(<source[^>]+\bsrc=(?:(["\'])(?:(?!\2).)+|[^\s]+)/(?P<id>[\da-z]+)/index)\b'
+        video_id = self._search_regex(
+            SOURCE_RE, webpage, 'video id', group='id')
+
+        media = self._parse_html5_media_entries(
+            url, re.sub(SOURCE_RE, r'\1.m3u8', webpage), video_id,
+            m3u8_id='hls', m3u8_entry_protocol='m3u8_native')[0]
+
+        info = self._search_json_ld(webpage, video_id, default={})
+
+        return merge_dicts(media, info, {
+            'id': video_id,
+            'display_id': display_id,
+            'title': self._og_search_title(webpage, default=None) or display_id,
+            'description': self._og_search_description(webpage, default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+        })

youtube_dl/extractor/manyvids.py

@@ -2,12 +2,18 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    str_to_int,
+    urlencode_postdata,
+)
 
 
 class ManyVidsIE(InfoExtractor):
     _VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
+        # preview video
         'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/',
         'md5': '03f11bb21c52dd12a05be21a5c7dcc97',
         'info_dict': {
@@ -17,7 +23,18 @@ class ManyVidsIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
         },
-    }
+    }, {
+        # full video
+        'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/',
+        'md5': 'f3e8f7086409e9b470e2643edb96bdcc',
+        'info_dict': {
+            'id': '935718',
+            'ext': 'mp4',
+            'title': 'MY FACE REVEAL',
+            'view_count': int,
+            'like_count': int,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -28,12 +45,41 @@ class ManyVidsIE(InfoExtractor):
             r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1',
             webpage, 'video URL', group='url')
 
-        title = '%s (Preview)' % self._html_search_regex(
-            r'<h2[^>]+class="m-a-0"[^>]*>([^<]+)', webpage, 'title')
+        title = self._html_search_regex(
+            (r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
+             r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
+            webpage, 'title', default=None) or self._html_search_meta(
+            'twitter:title', webpage, 'title', fatal=True)
+
+        if any(p in webpage for p in ('preview_videos', '_preview.mp4')):
+            title += ' (Preview)'
+
+        mv_token = self._search_regex(
+            r'data-mvtoken=(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+            'mv token', default=None, group='value')
+
+        if mv_token:
+            # Sets some cookies
+            self._download_webpage(
+                'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php',
+                video_id, fatal=False, data=urlencode_postdata({
+                    'mvtoken': mv_token,
+                    'vid': video_id,
+                }), headers={
+                    'Referer': url,
+                    'X-Requested-With': 'XMLHttpRequest'
+                })
+
+        if determine_ext(video_url) == 'm3u8':
+            formats = self._extract_m3u8_formats(
+                video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls')
+        else:
+            formats = [{'url': video_url}]
 
         like_count = int_or_none(self._search_regex(
             r'data-likes=["\'](\d+)', webpage, 'like count', default=None))
-        view_count = int_or_none(self._html_search_regex(
+        view_count = str_to_int(self._html_search_regex(
             r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage,
             'view count', default=None))
 
@@ -42,7 +88,5 @@ class ManyVidsIE(InfoExtractor):
             'title': title,
             'view_count': view_count,
             'like_count': like_count,
-            'formats': [{
-                'url': video_url,
-            }],
+            'formats': formats,
         }

youtube_dl/extractor/mediasite.py

@@ -21,7 +21,7 @@ from ..utils import (
 
 
 class MediasiteIE(InfoExtractor):
-    _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/Play/(?P<id>[0-9a-f]{32,34})(?P<query>\?[^#]+|)'
+    _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/(?:default|livebroadcast)/Presentation)/(?P<id>[0-9a-f]{32,34})(?P<query>\?[^#]+|)'
     _TESTS = [
         {
             'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d',
@@ -84,7 +84,15 @@ class MediasiteIE(InfoExtractor):
                 'timestamp': 1333983600,
                 'duration': 7794,
             }
-        }
+        },
+        {
+            'url': 'https://collegerama.tudelft.nl/Mediasite/Showcase/livebroadcast/Presentation/ada7020854f743c49fbb45c9ec7dbb351d',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://mediasite.ntnu.no/Mediasite/Showcase/default/Presentation/7d8b913259334b688986e970fae6fcb31d',
+            'only_matching': True,
+        },
     ]
 
     # look in Mediasite.Core.js (Mediasite.ContentStreamType[*])

youtube_dl/extractor/metacafe.py

@@ -1,12 +1,13 @@
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
+    compat_urllib_parse,
     compat_urllib_parse_unquote,
-    compat_urllib_parse_urlencode,
 )
 from ..utils import (
     determine_ext,
@@ -144,7 +145,7 @@ class MetacafeIE(InfoExtractor):
 
         headers = {
             # Disable family filter
-            'Cookie': 'user=%s; ' % compat_urllib_parse_urlencode({'ffilter': False})
+            'Cookie': 'user=%s; ' % compat_urllib_parse.quote(json.dumps({'ffilter': False}))
         }
 
         # AnyClip videos require the flashversion cookie so that we get the link

youtube_dl/extractor/nationalgeographic.py

@@ -1,15 +1,10 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from .adobepass import AdobePassIE
-from .theplatform import ThePlatformIE
+from .fox import FOXIE
 from ..utils import (
     smuggle_url,
     url_basename,
-    update_url_query,
-    get_element_by_class,
 )
 
 
@@ -66,130 +61,22 @@ class NationalGeographicVideoIE(InfoExtractor):
         }
 
 
-class NationalGeographicIE(ThePlatformIE, AdobePassIE):
-    IE_NAME = 'natgeo'
-    _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:(?:(?:wild/)?[^/]+/)?(?:videos|episodes)|u)/(?P<id>[^/?]+)'
-
-    _TESTS = [
-        {
-            'url': 'http://channel.nationalgeographic.com/u/kdi9Ld0PN2molUUIMSBGxoeDhD729KRjQcnxtetilWPMevo8ZwUBIDuPR0Q3D2LVaTsk0MPRkRWDB8ZhqWVeyoxfsZZm36yRp1j-zPfsHEyI_EgAeFY/',
-            'md5': '518c9aa655686cf81493af5cc21e2a04',
-            'info_dict': {
-                'id': 'vKInpacll2pC',
-                'ext': 'mp4',
-                'title': 'Uncovering a Universal Knowledge',
-                'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a',
-                'timestamp': 1458680907,
-                'upload_date': '20160322',
-                'uploader': 'NEWA-FNG-NGTV',
-            },
-            'add_ie': ['ThePlatform'],
+class NationalGeographicTVIE(FOXIE):
+    _VALID_URL = r'https?://(?:www\.)?nationalgeographic\.com/tv/watch/(?P<id>[\da-fA-F]+)'
+    _TESTS = [{
+        'url': 'https://www.nationalgeographic.com/tv/watch/6a875e6e734b479beda26438c9f21138/',
+        'info_dict': {
+            'id': '6a875e6e734b479beda26438c9f21138',
+            'ext': 'mp4',
+            'title': 'Why Nat Geo? Valley of the Boom',
+            'description': 'The lives of prominent figures in the tech world, including their friendships, rivalries, victories and failures.',
+            'timestamp': 1542662458,
+            'upload_date': '20181119',
+            'age_limit': 14,
         },
-        {
-            'url': 'http://channel.nationalgeographic.com/u/kdvOstqYaBY-vSBPyYgAZRUL4sWUJ5XUUPEhc7ISyBHqoIO4_dzfY3K6EjHIC0hmFXoQ7Cpzm6RkET7S3oMlm6CFnrQwSUwo/',
-            'md5': 'c4912f656b4cbe58f3e000c489360989',
-            'info_dict': {
-                'id': 'Pok5lWCkiEFA',
-                'ext': 'mp4',
-                'title': 'The Stunning Red Bird of Paradise',
-                'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c',
-                'timestamp': 1459362152,
-                'upload_date': '20160330',
-                'uploader': 'NEWA-FNG-NGTV',
-            },
-            'add_ie': ['ThePlatform'],
+        'params': {
+            'skip_download': True,
         },
-        {
-            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/videos/treasures-rediscovered/',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/',
-            'only_matching': True,
-        }
-    ]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        release_url = self._search_regex(
-            r'video_auth_playlist_url\s*=\s*"([^"]+)"',
-            webpage, 'release url')
-        theplatform_path = self._search_regex(r'https?://link\.theplatform\.com/s/([^?]+)', release_url, 'theplatform path')
-        video_id = theplatform_path.split('/')[-1]
-        query = {
-            'mbr': 'true',
-        }
-        is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False)
-        if is_auth == 'auth':
-            auth_resource_id = self._search_regex(
-                r"video_auth_resourceId\s*=\s*'([^']+)'",
-                webpage, 'auth resource id')
-            query['auth'] = self._extract_mvpd_auth(url, video_id, 'natgeo', auth_resource_id)
-
-        formats = []
-        subtitles = {}
-        for key, value in (('switch', 'http'), ('manifest', 'm3u')):
-            tp_query = query.copy()
-            tp_query.update({
-                key: value,
-            })
-            tp_formats, tp_subtitles = self._extract_theplatform_smil(
-                update_url_query(release_url, tp_query), video_id, 'Downloading %s SMIL data' % value)
-            formats.extend(tp_formats)
-            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
-        self._sort_formats(formats)
-
-        info = self._extract_theplatform_metadata(theplatform_path, display_id)
-        info.update({
-            'id': video_id,
-            'formats': formats,
-            'subtitles': subtitles,
-            'display_id': display_id,
-        })
-        return info
-
-
-class NationalGeographicEpisodeGuideIE(InfoExtractor):
-    IE_NAME = 'natgeo:episodeguide'
-    _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide'
-    _TESTS = [
-        {
-            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/',
-            'info_dict': {
-                'id': 'the-story-of-god-with-morgan-freeman-season-1',
-                'title': 'The Story of God with Morgan Freeman - Season 1',
-            },
-            'playlist_mincount': 6,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2',
-            'info_dict': {
-                'id': 'underworld-inc-season-2',
-                'title': 'Underworld, Inc. - Season 2',
-            },
-            'playlist_mincount': 7,
-        },
-    ]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        show = get_element_by_class('show', webpage)
-        selected_season = self._search_regex(
-            r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>',
-            webpage, 'selected season')
-        entries = [
-            self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic')
-            for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)]
-        return self.playlist_result(
-            entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')),
-            '%s - %s' % (show, selected_season))
+    }]
+    _HOME_PAGE_URL = 'https://www.nationalgeographic.com/tv/'
+    _API_KEY = '238bb0a0c2aba67922c48709ce0c06fd'

youtube_dl/extractor/nhk.py

@@ -5,8 +5,8 @@ from ..utils import ExtractorError
 
 
 class NhkVodIE(InfoExtractor):
-    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>[^/]+/[^/?#&]+)'
-    _TEST = {
+    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/(?:vod|ondemand)/(?P<id>[^/]+/[^/?#&]+)'
+    _TESTS = [{
         # Videos available only for a limited period of time. Visit
         # http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
         'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815',
@@ -19,7 +19,10 @@ class NhkVodIE(InfoExtractor):
             'episode': 'The Kimono as Global Fashion',
         },
         'skip': 'Videos available only for a limited period of time',
-    }
+    }, {
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
+        'only_matching': True,
+    }]
     _API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k'
 
     def _real_extract(self, url):

youtube_dl/extractor/noovo.py

@@ -57,7 +57,8 @@ class NoovoIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        bc_url = BrightcoveNewIE._extract_url(self, webpage)
+        brightcove_id = self._search_regex(
+            r'data-video-id=["\'](\d+)', webpage, 'brightcove id')
 
         data = self._parse_json(
             self._search_regex(
@@ -89,7 +90,10 @@ class NoovoIE(InfoExtractor):
         return {
             '_type': 'url_transparent',
             'ie_key': BrightcoveNewIE.ie_key(),
-            'url': smuggle_url(bc_url, {'geo_countries': ['CA']}),
+            'url': smuggle_url(
+                self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+                {'geo_countries': ['CA']}),
+            'id': brightcove_id,
             'title': title,
             'description': description,
             'series': series,

youtube_dl/extractor/npo.py

@@ -12,11 +12,16 @@ from ..utils import (
     ExtractorError,
     fix_xml_ampersands,
     int_or_none,
+    merge_dicts,
     orderedSet,
     parse_duration,
     qualities,
+    str_or_none,
     strip_jsonp,
     unified_strdate,
+    unified_timestamp,
+    url_or_none,
+    urlencode_postdata,
 )
 
 
@@ -176,9 +181,118 @@ class NPOIE(NPOBaseIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        return self._get_info(video_id)
+        try:
+            return self._get_info(url, video_id)
+        except ExtractorError:
+            return self._get_old_info(video_id)
 
-    def _get_info(self, video_id):
+    def _get_info(self, url, video_id):
+        token = self._download_json(
+            'https://www.npostart.nl/api/token', video_id,
+            'Downloading token', headers={
+                'Referer': url,
+                'X-Requested-With': 'XMLHttpRequest',
+            })['token']
+
+        player = self._download_json(
+            'https://www.npostart.nl/player/%s' % video_id, video_id,
+            'Downloading player JSON', data=urlencode_postdata({
+                'autoplay': 0,
+                'share': 1,
+                'pageUrl': url,
+                'hasAdConsent': 0,
+                '_token': token,
+            }))
+
+        player_token = player['token']
+
+        format_urls = set()
+        formats = []
+        for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
+            streams = self._download_json(
+                'https://start-player.npo.nl/video/%s/streams' % video_id,
+                video_id, 'Downloading %s profile JSON' % profile, fatal=False,
+                query={
+                    'profile': profile,
+                    'quality': 'npo',
+                    'tokenId': player_token,
+                    'streamType': 'broadcast',
+                })
+            if not streams:
+                continue
+            stream = streams.get('stream')
+            if not isinstance(stream, dict):
+                continue
+            stream_url = url_or_none(stream.get('src'))
+            if not stream_url or stream_url in format_urls:
+                continue
+            format_urls.add(stream_url)
+            if stream.get('protection') is not None:
+                continue
+            stream_type = stream.get('type')
+            stream_ext = determine_ext(stream_url)
+            if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    stream_url, video_id, mpd_id='dash', fatal=False))
+            elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url, video_id, ext='mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+            elif re.search(r'\.isml?/Manifest', stream_url):
+                formats.extend(self._extract_ism_formats(
+                    stream_url, video_id, ism_id='mss', fatal=False))
+            else:
+                formats.append({
+                    'url': stream_url,
+                })
+
+        self._sort_formats(formats)
+
+        info = {
+            'id': video_id,
+            'title': video_id,
+            'formats': formats,
+        }
+
+        embed_url = url_or_none(player.get('embedUrl'))
+        if embed_url:
+            webpage = self._download_webpage(
+                embed_url, video_id, 'Downloading embed page', fatal=False)
+            if webpage:
+                video = self._parse_json(
+                    self._search_regex(
+                        r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
+                        default='{}'), video_id)
+                if video:
+                    title = video.get('episodeTitle')
+                    subtitles = {}
+                    subtitles_list = video.get('subtitles')
+                    if isinstance(subtitles_list, list):
+                        for cc in subtitles_list:
+                            cc_url = url_or_none(cc.get('src'))
+                            if not cc_url:
+                                continue
+                            lang = str_or_none(cc.get('language')) or 'nl'
+                            subtitles.setdefault(lang, []).append({
+                                'url': cc_url,
+                            })
+                    return merge_dicts({
+                        'title': title,
+                        'description': video.get('description'),
+                        'thumbnail': url_or_none(
+                            video.get('still_image_url') or video.get('orig_image_url')),
+                        'duration': int_or_none(video.get('duration')),
+                        'timestamp': unified_timestamp(video.get('broadcastDate')),
+                        'creator': video.get('channel'),
+                        'series': video.get('title'),
+                        'episode': title,
+                        'episode_number': int_or_none(video.get('episodeNumber')),
+                        'subtitles': subtitles,
+                    }, info)
+
+        return info
+
+    def _get_old_info(self, video_id):
         metadata = self._download_json(
             'http://e.omroep.nl/metadata/%s' % video_id,
             video_id,
@@ -280,7 +394,7 @@ class NPOIE(NPOBaseIE):
             # JSON
             else:
                 video_url = stream_info.get('url')
-            if not video_url or video_url in urls:
+            if not video_url or 'vodnotavailable.' in video_url or video_url in urls:
                 continue
             urls.add(video_url)
             if determine_ext(video_url) == 'm3u8':
@@ -363,7 +477,7 @@ class NPOIE(NPOBaseIE):
 
 class NPOLiveIE(NPOBaseIE):
     IE_NAME = 'npo.nl:live'
-    _VALID_URL = r'https?://(?:www\.)?npo\.nl/live(?:/(?P<id>[^/?#&]+))?'
+    _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
 
     _TESTS = [{
         'url': 'http://www.npo.nl/live/npo-1',
@@ -380,6 +494,9 @@ class NPOLiveIE(NPOBaseIE):
     }, {
         'url': 'http://www.npo.nl/live',
         'only_matching': True,
+    }, {
+        'url': 'https://www.npostart.nl/live/npo-1',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/odnoklassniki.py

@@ -115,6 +115,10 @@ class OdnoklassnikiIE(InfoExtractor):
     }, {
         'url': 'https://m.ok.ru/dk?st.cmd=movieLayer&st.discId=863789452017&st.retLoc=friend&st.rtu=%2Fdk%3Fst.cmd%3DfriendMovies%26st.mode%3Down%26st.mrkId%3D%257B%2522uploadedMovieMarker%2522%253A%257B%2522marker%2522%253A%25221519410114503%2522%252C%2522hasMore%2522%253Atrue%257D%252C%2522sharedMovieMarker%2522%253A%257B%2522marker%2522%253Anull%252C%2522hasMore%2522%253Afalse%257D%257D%26st.friendId%3D561722190321%26st.frwd%3Don%26_prevCmd%3DfriendMovies%26tkn%3D7257&st.discType=MOVIE&st.mvId=863789452017&_prevCmd=friendMovies&tkn=3648#lst#',
         'only_matching': True,
+    }, {
+        # Paid video
+        'url': 'https://ok.ru/video/954886983203',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -244,6 +248,11 @@ class OdnoklassnikiIE(InfoExtractor):
                 'ext': 'flv',
             })
 
+        if not formats:
+            payment_info = metadata.get('paymentInfo')
+            if payment_info:
+                raise ExtractorError('This video is paid, subscribe to download it', expected=True)
+
         self._sort_formats(formats)
 
         info['formats'] = formats

youtube_dl/extractor/openload.py

@@ -248,8 +248,8 @@ class OpenloadIE(InfoExtractor):
                         (?P<host>
                             (?:www\.)?
                             (?:
-                                openload\.(?:co|io|link)|
-                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun)
+                                openload\.(?:co|io|link|pw)|
+                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space)
                             )
                         )/
                         (?:f|embed)/
@@ -334,6 +334,24 @@ class OpenloadIE(InfoExtractor):
     }, {
         'url': 'https://oload.fun/f/gb6G1H4sHXY',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.club/f/Nr1L-aZ2dbQ',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.info/f/5NEAbI2BDSk',
+        'only_matching': True,
+    }, {
+        'url': 'https://openload.pw/f/WyKgK8s94N0',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.pw/f/WyKgK8s94N0',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.live/f/-Z58UZ-GR4M',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.space/f/IY4eZSst3u8/',
+        'only_matching': True,
     }]
 
     _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'

youtube_dl/extractor/outsidetv.py

@@ -0,0 +1,28 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class OutsideTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?outsidetv\.com/(?:[^/]+/)*?play/[a-zA-Z0-9]{8}/\d+/\d+/(?P<id>[a-zA-Z0-9]{8})'
+    _TESTS = [{
+        'url': 'http://www.outsidetv.com/category/snow/play/ZjQYboH6/1/10/Hdg0jukV/4',
+        'md5': '192d968fedc10b2f70ec31865ffba0da',
+        'info_dict': {
+            'id': 'Hdg0jukV',
+            'ext': 'mp4',
+            'title': 'Home - Jackson Ep 1 | Arbor Snowboards',
+            'description': 'md5:41a12e94f3db3ca253b04bb1e8d8f4cd',
+            'upload_date': '20181225',
+            'timestamp': 1545742800,
+        }
+    }, {
+        'url': 'http://www.outsidetv.com/home/play/ZjQYboH6/1/10/Hdg0jukV/4',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        jw_media_id = self._match_id(url)
+        return self.url_result(
+            'jwplatform:' + jw_media_id, 'JWPlatform', jw_media_id)

youtube_dl/extractor/packtpub.py

@@ -24,9 +24,9 @@ class PacktPubBaseIE(InfoExtractor):
 
 
 class PacktPubIE(PacktPubBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
         'md5': '1e74bd6cfd45d7d07666f4684ef58f70',
         'info_dict': {
@@ -37,7 +37,10 @@ class PacktPubIE(PacktPubBaseIE):
             'timestamp': 1490918400,
             'upload_date': '20170331',
         },
-    }
+    }, {
+        'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro',
+        'only_matching': True,
+    }]
     _NETRC_MACHINE = 'packtpub'
     _TOKEN = None
 
@@ -110,15 +113,18 @@ class PacktPubIE(PacktPubBaseIE):
 
 
 class PacktPubCourseIE(PacktPubBaseIE):
-    _VALID_URL = r'(?P<url>https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<id>\d+))'
-    _TEST = {
+    _VALID_URL = r'(?P<url>https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<id>\d+))'
+    _TESTS = [{
         'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215',
         'info_dict': {
             'id': '9781787122215',
             'title': 'Learn Nodejs by building 12 projects [Video]',
         },
         'playlist_count': 90,
-    }
+    }, {
+        'url': 'https://subscription.packtpub.com/video/web_development/9781787122215',
+        'only_matching': True,
+    }]
 
     @classmethod
     def suitable(cls, url):

youtube_dl/extractor/periscope.py

@@ -5,6 +5,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    int_or_none,
     parse_iso8601,
     unescapeHTML,
 )
@@ -75,6 +76,14 @@ class PeriscopeIE(PeriscopeBaseIE):
             'url': broadcast[image],
         } for image in ('image_url', 'image_url_small') if broadcast.get(image)]
 
+        width = int_or_none(broadcast.get('width'))
+        height = int_or_none(broadcast.get('height'))
+
+        def add_width_and_height(f):
+            for key, val in (('width', width), ('height', height)):
+                if not f.get(key):
+                    f[key] = val
+
         video_urls = set()
         formats = []
         for format_id in ('replay', 'rtmp', 'hls', 'https_hls', 'lhls', 'lhlsweb'):
@@ -83,16 +92,21 @@ class PeriscopeIE(PeriscopeBaseIE):
                 continue
             video_urls.add(video_url)
             if format_id != 'rtmp':
-                formats.extend(self._extract_m3u8_formats(
+                m3u8_formats = self._extract_m3u8_formats(
                     video_url, token, 'mp4',
                     entry_protocol='m3u8_native'
                     if state in ('ended', 'timed_out') else 'm3u8',
-                    m3u8_id=format_id, fatal=False))
+                    m3u8_id=format_id, fatal=False)
+                if len(m3u8_formats) == 1:
+                    add_width_and_height(m3u8_formats[0])
+                formats.extend(m3u8_formats)
                 continue
-            formats.append({
+            rtmp_format = {
                 'url': video_url,
                 'ext': 'flv' if format_id == 'rtmp' else 'mp4',
-            })
+            }
+            add_width_and_height(rtmp_format)
+            formats.append(rtmp_format)
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/playplustv.py

@@ -0,0 +1,109 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_HTTPError
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    int_or_none,
+    PUTRequest,
+)
+
+
+class PlayPlusTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?playplus\.(?:com|tv)/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})'
+    _TEST = {
+        'url': 'https://www.playplus.tv/VOD/7572/db8d274a5163424e967f35a30ddafb8e',
+        'md5': 'd078cb89d7ab6b9df37ce23c647aef72',
+        'info_dict': {
+            'id': 'db8d274a5163424e967f35a30ddafb8e',
+            'ext': 'mp4',
+            'title': 'Capítulo 179 - Final',
+            'description': 'md5:01085d62d8033a1e34121d3c3cabc838',
+            'timestamp': 1529992740,
+            'upload_date': '20180626',
+        },
+        'skip': 'Requires account credential',
+    }
+    _NETRC_MACHINE = 'playplustv'
+    _GEO_COUNTRIES = ['BR']
+    _token = None
+    _profile_id = None
+
+    def _call_api(self, resource, video_id=None, query=None):
+        return self._download_json('https://api.playplus.tv/api/media/v2/get' + resource, video_id, headers={
+            'Authorization': 'Bearer ' + self._token,
+        }, query=query)
+
+    def _real_initialize(self):
+        email, password = self._get_login_info()
+        if email is None:
+            self.raise_login_required()
+
+        req = PUTRequest(
+            'https://api.playplus.tv/api/web/login', json.dumps({
+                'email': email,
+                'password': password,
+            }).encode(), {
+                'Content-Type': 'application/json; charset=utf-8',
+            })
+
+        try:
+            self._token = self._download_json(req, None)['token']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                raise ExtractorError(self._parse_json(
+                    e.cause.read(), None)['errorMessage'], expected=True)
+            raise
+
+        self._profile = self._call_api('Profiles')['list'][0]['_id']
+
+    def _real_extract(self, url):
+        project_id, media_id = re.match(self._VALID_URL, url).groups()
+        media = self._call_api(
+            'Media', media_id, {
+                'profileId': self._profile,
+                'projectId': project_id,
+                'mediaId': media_id,
+            })['obj']
+        title = media['title']
+
+        formats = []
+        for f in media.get('files', []):
+            f_url = f.get('url')
+            if not f_url:
+                continue
+            file_info = f.get('fileInfo') or {}
+            formats.append({
+                'url': f_url,
+                'width': int_or_none(file_info.get('width')),
+                'height': int_or_none(file_info.get('height')),
+            })
+        self._sort_formats(formats)
+
+        thumbnails = []
+        for thumb in media.get('thumbs', []):
+            thumb_url = thumb.get('url')
+            if not thumb_url:
+                continue
+            thumbnails.append({
+                'url': thumb_url,
+                'width': int_or_none(thumb.get('width')),
+                'height': int_or_none(thumb.get('height')),
+            })
+
+        return {
+            'id': media_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': clean_html(media.get('description')) or media.get('shortDescription'),
+            'timestamp': int_or_none(media.get('publishDate'), 1000),
+            'view_count': int_or_none(media.get('numberOfViews')),
+            'comment_count': int_or_none(media.get('numberOfComments')),
+            'tags': media.get('tags'),
+        }

youtube_dl/extractor/pornhd.py

@@ -4,9 +4,11 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     ExtractorError,
     int_or_none,
     js_to_json,
+    urljoin,
 )
 
 
@@ -14,7 +16,7 @@ class PornHdIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
     _TESTS = [{
         'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
-        'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5',
+        'md5': '87f1540746c1d32ec7a2305c12b96b25',
         'info_dict': {
             'id': '9864',
             'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
@@ -23,6 +25,7 @@ class PornHdIE(InfoExtractor):
             'description': 'md5:3748420395e03e31ac96857a8f125b2b',
             'thumbnail': r're:^https?://.*\.jpg',
             'view_count': int,
+            'like_count': int,
             'age_limit': 18,
         }
     }, {
@@ -37,6 +40,7 @@ class PornHdIE(InfoExtractor):
             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
             'thumbnail': r're:^https?://.*\.jpg',
             'view_count': int,
+            'like_count': int,
             'age_limit': 18,
         },
         'skip': 'Not available anymore',
@@ -65,12 +69,14 @@ class PornHdIE(InfoExtractor):
 
         formats = []
         for format_id, video_url in sources.items():
+            video_url = urljoin(url, video_url)
             if not video_url:
                 continue
             height = int_or_none(self._search_regex(
                 r'^(\d+)[pP]', format_id, 'height', default=None))
             formats.append({
                 'url': video_url,
+                'ext': determine_ext(video_url, 'mp4'),
                 'format_id': format_id,
                 'height': height,
             })
@@ -85,6 +91,11 @@ class PornHdIE(InfoExtractor):
             r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
             'thumbnail', fatal=False, group='url')
 
+        like_count = int_or_none(self._search_regex(
+            (r'(\d+)\s*</11[^>]+>(?:&nbsp;|\s)*\blikes',
+             r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
+            webpage, 'like count', fatal=False))
+
         return {
             'id': video_id,
             'display_id': display_id,
@@ -92,6 +103,7 @@ class PornHdIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'view_count': view_count,
+            'like_count': like_count,
             'formats': formats,
             'age_limit': 18,
         }

youtube_dl/extractor/pornhub.py

@@ -10,11 +10,12 @@ from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
     compat_str,
+    compat_urllib_request,
 )
+from .openload import PhantomJSwrapper
 from ..utils import (
     ExtractorError,
     int_or_none,
-    js_to_json,
     orderedSet,
     remove_quotes,
     str_to_int,
@@ -22,7 +23,29 @@ from ..utils import (
 )
 
 
-class PornHubIE(InfoExtractor):
+class PornHubBaseIE(InfoExtractor):
+    def _download_webpage_handle(self, *args, **kwargs):
+        def dl(*args, **kwargs):
+            return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
+
+        webpage, urlh = dl(*args, **kwargs)
+
+        if any(re.search(p, webpage) for p in (
+                r'<body\b[^>]+\bonload=["\']go\(\)',
+                r'document\.cookie\s*=\s*["\']RNKEY=',
+                r'document\.location\.reload\(true\)')):
+            url_or_request = args[0]
+            url = (url_or_request.get_full_url()
+                   if isinstance(url_or_request, compat_urllib_request.Request)
+                   else url_or_request)
+            phantom = PhantomJSwrapper(self, required_version='2.0')
+            phantom.get(url, html=webpage)
+            webpage, urlh = dl(*args, **kwargs)
+
+        return webpage, urlh
+
+
+class PornHubIE(PornHubBaseIE):
     IE_DESC = 'PornHub and Thumbzilla'
     _VALID_URL = r'''(?x)
                     https?://
@@ -279,14 +302,12 @@ class PornHubIE(InfoExtractor):
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
-        page_params = self._parse_json(self._search_regex(
-            r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
-            webpage, 'page parameters', group='data', default='{}'),
-            video_id, transform_source=js_to_json, fatal=False)
-        tags = categories = None
-        if page_params:
-            tags = page_params.get('tags', '').split(',')
-            categories = page_params.get('categories', '').split(',')
+        def extract_list(meta_key):
+            div = self._search_regex(
+                r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
+                % meta_key, webpage, meta_key, default=None)
+            if div:
+                return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)
 
         return {
             'id': video_id,
@@ -301,13 +322,13 @@ class PornHubIE(InfoExtractor):
             'comment_count': comment_count,
             'formats': formats,
             'age_limit': 18,
-            'tags': tags,
-            'categories': categories,
+            'tags': extract_list('tags'),
+            'categories': extract_list('categories'),
             'subtitles': subtitles,
         }
 
 
-class PornHubPlaylistBaseIE(InfoExtractor):
+class PornHubPlaylistBaseIE(PornHubBaseIE):
     def _extract_entries(self, webpage, host):
         # Only process container div with main playlist content skipping
         # drop-down menu that uses similar pattern for videos (see

youtube_dl/extractor/radiocanada.py

@@ -4,16 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_HTTPError
 from ..utils import (
-    xpath_text,
-    find_xpath_attr,
     determine_ext,
+    ExtractorError,
     int_or_none,
     unified_strdate,
-    xpath_element,
-    ExtractorError,
-    determine_protocol,
-    unsmuggle_url,
 )
 
 
@@ -49,107 +45,79 @@ class RadioCanadaIE(InfoExtractor):
                 # m3u8 download
                 'skip_download': True,
             },
+        },
+        {
+            # with protectionType but not actually DRM protected
+            'url': 'radiocanada:toutv:140872',
+            'info_dict': {
+                'id': '140872',
+                'title': 'Épisode 1',
+                'series': 'District 31',
+            },
+            'only_matching': True,
         }
     ]
+    _GEO_COUNTRIES = ['CA']
+    _access_token = None
+    _claims = None
 
-    def _real_extract(self, url):
-        url, smuggled_data = unsmuggle_url(url, {})
-        app_code, video_id = re.match(self._VALID_URL, url).groups()
-
-        metadata = self._download_xml(
-            'http://api.radio-canada.ca/metaMedia/v1/index.ashx',
-            video_id, note='Downloading metadata XML', query={
+    def _call_api(self, path, video_id=None, app_code=None, query=None):
+        if not query:
+            query = {}
+        query.update({
+            'client_key': '773aea60-0e80-41bb-9c7f-e6d7c3ad17fb',
+            'output': 'json',
+        })
+        if video_id:
+            query.update({
                 'appCode': app_code,
                 'idMedia': video_id,
             })
+        if self._access_token:
+            query['access_token'] = self._access_token
+        try:
+            return self._download_json(
+                'https://services.radio-canada.ca/media/' + path, video_id, query=query)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 422):
+                data = self._parse_json(e.cause.read().decode(), None)
+                error = data.get('error_description') or data['errorMessage']['text']
+                raise ExtractorError(error, expected=True)
+            raise
+
+    def _extract_info(self, app_code, video_id):
+        metas = self._call_api('meta/v1/index.ashx', video_id, app_code)['Metas']
 
         def get_meta(name):
-            el = find_xpath_attr(metadata, './/Meta', 'name', name)
-            return el.text if el is not None else None
+            for meta in metas:
+                if meta.get('name') == name:
+                    text = meta.get('text')
+                    if text:
+                        return text
 
+        # protectionType does not necessarily mean the video is DRM protected (see
+        # https://github.com/rg3/youtube-dl/pull/18609).
         if get_meta('protectionType'):
-            raise ExtractorError('This video is DRM protected.', expected=True)
+            self.report_warning('This video is probably DRM protected.')
 
-        device_types = ['ipad']
-        if not smuggled_data:
-            device_types.append('flash')
-            device_types.append('android')
-
-        formats = []
-        error = None
-        # TODO: extract f4m formats
-        # f4m formats can be extracted using flashhd device_type but they produce unplayable file
-        for device_type in device_types:
-            validation_url = 'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx'
-            query = {
-                'appCode': app_code,
-                'idMedia': video_id,
-                'connectionType': 'broadband',
-                'multibitrate': 'true',
-                'deviceType': device_type,
-            }
-            if smuggled_data:
-                validation_url = 'https://services.radio-canada.ca/media/validation/v2/'
-                query.update(smuggled_data)
-            else:
-                query.update({
-                    # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction
-                    'paysJ391wsHjbOJwvCs26toz': 'CA',
-                    'bypasslock': 'NZt5K62gRqfc',
-                })
-            v_data = self._download_xml(validation_url, video_id, note='Downloading %s XML' % device_type, query=query, fatal=False)
-            v_url = xpath_text(v_data, 'url')
-            if not v_url:
-                continue
-            if v_url == 'null':
-                error = xpath_text(v_data, 'message')
-                continue
-            ext = determine_ext(v_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    v_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
-            elif ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    v_url, video_id, f4m_id='hds', fatal=False))
-            else:
-                ext = determine_ext(v_url)
-                bitrates = xpath_element(v_data, 'bitrates')
-                for url_e in bitrates.findall('url'):
-                    tbr = int_or_none(url_e.get('bitrate'))
-                    if not tbr:
-                        continue
-                    f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url)
-                    protocol = determine_protocol({'url': f_url})
-                    f = {
-                        'format_id': '%s-%d' % (protocol, tbr),
-                        'url': f_url,
-                        'ext': 'flv' if protocol == 'rtmp' else ext,
-                        'protocol': protocol,
-                        'width': int_or_none(url_e.get('width')),
-                        'height': int_or_none(url_e.get('height')),
-                        'tbr': tbr,
-                    }
-                    mobj = re.match(r'(?P<url>rtmp://[^/]+/[^/]+)/(?P<playpath>[^?]+)(?P<auth>\?.+)', f_url)
-                    if mobj:
-                        f.update({
-                            'url': mobj.group('url') + mobj.group('auth'),
-                            'play_path': mobj.group('playpath'),
-                        })
-                    formats.append(f)
-                    if protocol == 'rtsp':
-                        base_url = self._search_regex(
-                            r'rtsp://([^?]+)', f_url, 'base url', default=None)
-                        if base_url:
-                            base_url = 'http://' + base_url
-                            formats.extend(self._extract_m3u8_formats(
-                                base_url + '/playlist.m3u8', video_id, 'mp4',
-                                'm3u8_native', m3u8_id='hls', fatal=False))
-                            formats.extend(self._extract_f4m_formats(
-                                base_url + '/manifest.f4m', video_id,
-                                f4m_id='hds', fatal=False))
-        if not formats and error:
+        query = {
+            'connectionType': 'hd',
+            'deviceType': 'ipad',
+            'multibitrate': 'true',
+        }
+        if self._claims:
+            query['claims'] = self._claims
+        v_data = self._call_api('validation/v2/', video_id, app_code, query)
+        v_url = v_data.get('url')
+        if not v_url:
+            error = v_data['message']
+            if error == "Le contenu sélectionné n'est pas disponible dans votre pays":
+                raise self.raise_geo_restricted(error, self._GEO_COUNTRIES)
+            if error == 'Le contenu sélectionné est disponible seulement en premium':
+                self.raise_login_required(error)
             raise ExtractorError(
                 '%s said: %s' % (self.IE_NAME, error), expected=True)
+        formats = self._extract_m3u8_formats(v_url, video_id, 'mp4')
         self._sort_formats(formats)
 
         subtitles = {}
@@ -174,11 +142,14 @@ class RadioCanadaIE(InfoExtractor):
             'formats': formats,
         }
 
+    def _real_extract(self, url):
+        return self._extract_info(*re.match(self._VALID_URL, url).groups())
+
 
 class RadioCanadaAudioVideoIE(InfoExtractor):
     'radiocanada:audiovideo'
-    _VALID_URL = r'https?://ici\.radio-canada\.ca/audio-video/media-(?P<id>[0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://ici\.radio-canada\.ca/([^/]+/)*media-(?P<id>[0-9]+)'
+    _TESTS = [{
         'url': 'http://ici.radio-canada.ca/audio-video/media-7527184/barack-obama-au-vietnam',
         'info_dict': {
             'id': '7527184',
@@ -191,7 +162,10 @@ class RadioCanadaAudioVideoIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'https://ici.radio-canada.ca/info/videos/media-7527184/barack-obama-au-vietnam',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         return self.url_result('radiocanada:medianet:%s' % self._match_id(url))

youtube_dl/extractor/rai.py

@@ -74,11 +74,11 @@ class RaiBaseIE(InfoExtractor):
             if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'):
                 continue
 
-            if ext == 'm3u8':
+            if ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon':
                 formats.extend(self._extract_m3u8_formats(
                     media_url, video_id, 'mp4', 'm3u8_native',
                     m3u8_id='hls', fatal=False))
-            elif ext == 'f4m':
+            elif ext == 'f4m' or platform == 'flash':
                 manifest_url = update_url_query(
                     media_url.replace('manifest#live_hds.f4m', 'manifest.f4m'),
                     {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'})
@@ -288,7 +288,7 @@ class RaiPlayPlaylistIE(InfoExtractor):
 
 
 class RaiIE(RaiBaseIE):
-    _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
+    _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
     _TESTS = [{
         # var uniquename = "ContentItem-..."
         # data-id="ContentItem-..."
@@ -375,6 +375,9 @@ class RaiIE(RaiBaseIE):
         # Direct MMS URL
         'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
         'only_matching': True,
+    }, {
+        'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html',
+        'only_matching': True,
     }]
 
     def _extract_from_content_id(self, content_id, url):

youtube_dl/extractor/rmcdecouverte.py

@@ -1,38 +1,46 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from .brightcove import BrightcoveLegacyIE
 from ..compat import (
     compat_parse_qs,
     compat_urlparse,
 )
+from ..utils import smuggle_url
 
 
 class RMCDecouverteIE(InfoExtractor):
-    _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/mediaplayer-replay.*?\bid=(?P<id>\d+)'
+    _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/(?:(?:[^/]+/)*program_(?P<id>\d+)|(?P<live_id>mediaplayer-direct))'
 
-    _TEST = {
-        'url': 'http://rmcdecouverte.bfmtv.com/mediaplayer-replay/?id=13502&title=AQUAMEN:LES%20ROIS%20DES%20AQUARIUMS%20:UN%20DELICIEUX%20PROJET',
+    _TESTS = [{
+        'url': 'https://rmcdecouverte.bfmtv.com/wheeler-dealers-occasions-a-saisir/program_2566/',
         'info_dict': {
-            'id': '5419055995001',
+            'id': '5983675500001',
             'ext': 'mp4',
-            'title': 'UN DELICIEUX PROJET',
-            'description': 'md5:63610df7c8b1fc1698acd4d0d90ba8b5',
+            'title': 'CORVETTE',
+            'description': 'md5:c1e8295521e45ffebf635d6a7658f506',
             'uploader_id': '1969646226001',
-            'upload_date': '20170502',
-            'timestamp': 1493745308,
+            'upload_date': '20181226',
+            'timestamp': 1545861635,
         },
         'params': {
             'skip_download': True,
         },
         'skip': 'only available for a week',
-    }
+    }, {
+        # live, geo restricted, bypassable
+        'url': 'https://rmcdecouverte.bfmtv.com/mediaplayer-direct/',
+        'only_matching': True,
+    }]
     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1969646226001/default_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id') or mobj.group('live_id')
+        webpage = self._download_webpage(url, display_id)
         brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
         if brightcove_legacy_url:
             brightcove_id = compat_parse_qs(compat_urlparse.urlparse(
@@ -41,5 +49,7 @@ class RMCDecouverteIE(InfoExtractor):
             brightcove_id = self._search_regex(
                 r'data-video-id=["\'](\d+)', webpage, 'brightcove id')
         return self.url_result(
-            self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew',
-            brightcove_id)
+            smuggle_url(
+                self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+                {'geo_countries': ['FR']}),
+            'BrightcoveNew', brightcove_id)

youtube_dl/extractor/rutube.py

@@ -21,7 +21,17 @@ from ..utils import (
 
 
 class RutubeBaseIE(InfoExtractor):
-    def _extract_video(self, video, video_id=None, require_title=True):
+    def _download_api_info(self, video_id, query=None):
+        if not query:
+            query = {}
+        query['format'] = 'json'
+        return self._download_json(
+            'http://rutube.ru/api/video/%s/' % video_id,
+            video_id, 'Downloading video JSON',
+            'Unable to download video JSON', query=query)
+
+    @staticmethod
+    def _extract_info(video, video_id=None, require_title=True):
         title = video['title'] if require_title else video.get('title')
 
         age_limit = video.get('is_adult')
@@ -32,7 +42,7 @@ class RutubeBaseIE(InfoExtractor):
         category = try_get(video, lambda x: x['category']['name'])
 
         return {
-            'id': video.get('id') or video_id,
+            'id': video.get('id') or video_id if video_id else video['id'],
             'title': title,
             'description': video.get('description'),
             'thumbnail': video.get('thumbnail_url'),
@@ -47,6 +57,42 @@ class RutubeBaseIE(InfoExtractor):
             'is_live': bool_or_none(video.get('is_livestream')),
         }
 
+    def _download_and_extract_info(self, video_id, query=None):
+        return self._extract_info(
+            self._download_api_info(video_id, query=query), video_id)
+
+    def _download_api_options(self, video_id, query=None):
+        if not query:
+            query = {}
+        query['format'] = 'json'
+        return self._download_json(
+            'http://rutube.ru/api/play/options/%s/' % video_id,
+            video_id, 'Downloading options JSON',
+            'Unable to download options JSON',
+            headers=self.geo_verification_headers(), query=query)
+
+    def _extract_formats(self, options, video_id):
+        formats = []
+        for format_id, format_url in options['video_balancer'].items():
+            ext = determine_ext(format_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
+            elif ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    format_url, video_id, f4m_id=format_id, fatal=False))
+            else:
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                })
+        self._sort_formats(formats)
+        return formats
+
+    def _download_and_extract_formats(self, video_id, query=None):
+        return self._extract_formats(
+            self._download_api_options(video_id, query=query), video_id)
+
 
 class RutubeIE(RutubeBaseIE):
     IE_NAME = 'rutube'
@@ -55,13 +101,13 @@ class RutubeIE(RutubeBaseIE):
 
     _TESTS = [{
         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
-        'md5': '79938ade01294ef7e27574890d0d3769',
+        'md5': '1d24f180fac7a02f3900712e5a5764d6',
         'info_dict': {
             'id': '3eac3b4561676c17df9132a9a1e62e3e',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Раненный кенгуру забежал в аптеку',
             'description': 'http://www.ntdtv.ru ',
-            'duration': 80,
+            'duration': 81,
             'uploader': 'NTDRussian',
             'uploader_id': '29790',
             'timestamp': 1381943602,
@@ -94,39 +140,12 @@ class RutubeIE(RutubeBaseIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
-        video = self._download_json(
-            'http://rutube.ru/api/video/%s/?format=json' % video_id,
-            video_id, 'Downloading video JSON')
-
-        info = self._extract_video(video, video_id)
-
-        options = self._download_json(
-            'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
-            video_id, 'Downloading options JSON',
-            headers=self.geo_verification_headers())
-
-        formats = []
-        for format_id, format_url in options['video_balancer'].items():
-            ext = determine_ext(format_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
-            elif ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    format_url, video_id, f4m_id=format_id, fatal=False))
-            else:
-                formats.append({
-                    'url': format_url,
-                    'format_id': format_id,
-                })
-        self._sort_formats(formats)
-
-        info['formats'] = formats
+        info = self._download_and_extract_info(video_id)
+        info['formats'] = self._download_and_extract_formats(video_id)
         return info
 
 
-class RutubeEmbedIE(InfoExtractor):
+class RutubeEmbedIE(RutubeBaseIE):
     IE_NAME = 'rutube:embed'
     IE_DESC = 'Rutube embedded videos'
     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
@@ -135,7 +154,7 @@ class RutubeEmbedIE(InfoExtractor):
         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
         'info_dict': {
             'id': 'a10e53b86e8f349080f718582ce4c661',
-            'ext': 'flv',
+            'ext': 'mp4',
             'timestamp': 1387830582,
             'upload_date': '20131223',
             'uploader_id': '297833',
@@ -149,16 +168,26 @@ class RutubeEmbedIE(InfoExtractor):
     }, {
         'url': 'http://rutube.ru/play/embed/8083783',
         'only_matching': True,
+    }, {
+        # private video
+        'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         embed_id = self._match_id(url)
-        webpage = self._download_webpage(url, embed_id)
-
-        canonical_url = self._html_search_regex(
-            r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
-            'Canonical URL')
-        return self.url_result(canonical_url, RutubeIE.ie_key())
+        # Query may contain private videos token and should be passed to API
+        # requests (see #19163)
+        query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        options = self._download_api_options(embed_id, query)
+        video_id = options['effective_video']
+        formats = self._extract_formats(options, video_id)
+        info = self._download_and_extract_info(video_id, query)
+        info.update({
+            'extractor_key': 'Rutube',
+            'formats': formats,
+        })
+        return info
 
 
 class RutubePlaylistBaseIE(RutubeBaseIE):
@@ -181,7 +210,7 @@ class RutubePlaylistBaseIE(RutubeBaseIE):
                 video_url = url_or_none(result.get('video_url'))
                 if not video_url:
                     continue
-                entry = self._extract_video(result, require_title=False)
+                entry = self._extract_info(result, require_title=False)
                 entry.update({
                     '_type': 'url',
                     'url': video_url,

youtube_dl/extractor/savefrom.py

@@ -30,8 +30,5 @@ class SaveFromIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = os.path.splitext(url.split('/')[-1])[0]
-        return {
-            '_type': 'url',
-            'id': video_id,
-            'url': mobj.group('url'),
-        }
+
+        return self.url_result(mobj.group('url'), video_id=video_id)

youtube_dl/extractor/scrippsnetworks.py

@@ -19,7 +19,7 @@ class ScrippsNetworksWatchIE(AWSIE):
     _VALID_URL = r'''(?x)
                     https?://
                         watch\.
-                        (?P<site>hgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv|geniuskitchen)\.com/
+                        (?P<site>geniuskitchen)\.com/
                         (?:
                             player\.[A-Z0-9]+\.html\#|
                             show/(?:[^/]+/){2}|
@@ -28,38 +28,23 @@ class ScrippsNetworksWatchIE(AWSIE):
                         (?P<id>\d+)
                     '''
     _TESTS = [{
-        'url': 'http://watch.hgtv.com/show/HGTVE/Best-Ever-Treehouses/2241515/Best-Ever-Treehouses/',
-        'md5': '26545fd676d939954c6808274bdb905a',
+        'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/',
         'info_dict': {
-            'id': '4173834',
+            'id': '4194875',
             'ext': 'mp4',
-            'title': 'Best Ever Treehouses',
-            'description': "We're searching for the most over the top treehouses.",
+            'title': 'Ample Hills Ice Cream Bike',
+            'description': 'Courtney Rada churns up a signature GK Now ice cream with The Scoopmaster.',
             'uploader': 'ANV',
-            'upload_date': '20170922',
-            'timestamp': 1506056400,
+            'upload_date': '20171011',
+            'timestamp': 1507698000,
         },
         'params': {
             'skip_download': True,
         },
         'add_ie': [AnvatoIE.ie_key()],
-    }, {
-        'url': 'http://watch.diynetwork.com/show/DSAL/Salvage-Dawgs/2656646/Covington-Church/',
-        'only_matching': True,
-    }, {
-        'url': 'http://watch.diynetwork.com/player.HNT.html#2656646',
-        'only_matching': True,
-    }, {
-        'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/',
-        'only_matching': True,
     }]
 
     _SNI_TABLE = {
-        'hgtv': 'hgtv',
-        'diynetwork': 'diy',
-        'foodnetwork': 'food',
-        'cookingchanneltv': 'cook',
-        'travelchannel': 'trav',
         'geniuskitchen': 'genius',
     }
 

youtube_dl/extractor/servus.py

@@ -1,31 +1,44 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 
 
 class ServusIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:at|de)/p/[^/]+/(?P<id>AA-\w+|\d+-\d+)'
+    _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)/(?P<id>[aA]{2}-\w+|\d+-\d+)'
     _TESTS = [{
         'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
-        'md5': '046dee641cda1c4cabe13baef3be2c1c',
+        'md5': '3e1dd16775aa8d5cbef23628cfffc1f4',
         'info_dict': {
             'id': 'AA-1T6VBU5PW1W12',
             'ext': 'mp4',
-            'title': 'Die Grünen aus Volkssicht',
-            'description': 'md5:052b5da1cb2cd7d562ef1f19be5a5cba',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'title': 'Die Grünen aus Sicht des Volkes',
+            'description': 'md5:1247204d85783afe3682644398ff2ec4',
+            'thumbnail': r're:^https?://.*\.jpg',
         }
     }, {
         'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.servus.com/tv/videos/aa-1t6vbu5pw1w12/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.servus.com/tv/videos/1380889096408-1235196658/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id = self._match_id(url).upper()
         webpage = self._download_webpage(url, video_id)
 
-        title = self._og_search_title(webpage)
+        title = self._search_regex(
+            (r'videoLabel\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
+             r'<h\d+[^>]+\bclass=["\']heading--(?:one|two)["\'][^>]*>(?P<title>[^<]+)'),
+            webpage, 'title', default=None,
+            group='title') or self._og_search_title(webpage)
+        title = re.sub(r'\s*-\s*Servus TV\s*$', '', title)
         description = self._og_search_description(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
 

youtube_dl/extractor/sixplay.py

@@ -61,7 +61,8 @@ class SixPlayIE(InfoExtractor):
         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
         formats = []
         subtitles = {}
-        for asset in clip_data['assets']:
+        assets = clip_data.get('assets') or []
+        for asset in assets:
             asset_url = asset.get('full_physical_path')
             protocol = asset.get('protocol')
             if not asset_url or protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264' or asset_url in urls:

youtube_dl/extractor/skylinewebcams.py

@@ -26,7 +26,7 @@ class SkylineWebcamsIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         stream_url = self._search_regex(
-            r'url\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage,
+            r'(?:url|source)\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage,
             'stream url', group='url')
 
         title = self._og_search_title(webpage)

youtube_dl/extractor/soundcloud.py

@@ -16,8 +16,10 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     int_or_none,
-    unified_strdate,
+    try_get,
+    unified_timestamp,
     update_url_query,
+    url_or_none,
 )
 
 
@@ -34,7 +36,7 @@ class SoundcloudIE(InfoExtractor):
                     (?:(?:(?:www\.|m\.)?soundcloud\.com/
                             (?!stations/track)
                             (?P<uploader>[\w\d-]+)/
-                            (?!(?:tracks|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
+                            (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
                             (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
@@ -50,12 +52,17 @@ class SoundcloudIE(InfoExtractor):
             'info_dict': {
                 'id': '62986583',
                 'ext': 'mp3',
-                'upload_date': '20121011',
+                'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
                 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d',
                 'uploader': 'E.T. ExTerrestrial Music',
-                'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
+                'timestamp': 1349920598,
+                'upload_date': '20121011',
                 'duration': 143,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             }
         },
         # not streamable song
@@ -67,9 +74,14 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Goldrushed',
                 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
                 'uploader': 'The Royal Concept',
+                'timestamp': 1337635207,
                 'upload_date': '20120521',
-                'duration': 227,
+                'duration': 30,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
             'params': {
                 # rtmp
@@ -84,11 +96,16 @@ class SoundcloudIE(InfoExtractor):
                 'id': '123998367',
                 'ext': 'mp3',
                 'title': 'Youtube - Dl Test Video \'\' Ä↭',
-                'uploader': 'jaimeMF',
                 'description': 'test chars:  \"\'/\\ä↭',
+                'uploader': 'jaimeMF',
+                'timestamp': 1386604920,
                 'upload_date': '20131209',
                 'duration': 9,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
         },
         # private link (alt format)
@@ -99,11 +116,16 @@ class SoundcloudIE(InfoExtractor):
                 'id': '123998367',
                 'ext': 'mp3',
                 'title': 'Youtube - Dl Test Video \'\' Ä↭',
-                'uploader': 'jaimeMF',
                 'description': 'test chars:  \"\'/\\ä↭',
+                'uploader': 'jaimeMF',
+                'timestamp': 1386604920,
                 'upload_date': '20131209',
                 'duration': 9,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
         },
         # downloadable song
@@ -116,9 +138,14 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Bus Brakes',
                 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66',
                 'uploader': 'oddsamples',
+                'timestamp': 1389232924,
                 'upload_date': '20140109',
                 'duration': 17,
                 'license': 'cc-by-sa',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
         },
         # private link, downloadable format
@@ -131,9 +158,14 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
                 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366',
                 'uploader': 'Ori Uplift Music',
+                'timestamp': 1504206263,
                 'upload_date': '20170831',
                 'duration': 7449,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
         },
         # no album art, use avatar pic for thumbnail
@@ -146,10 +178,15 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Sideways (Prod. Mad Real)',
                 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
                 'uploader': 'garyvee',
+                'timestamp': 1488152409,
                 'upload_date': '20170226',
                 'duration': 207,
                 'thumbnail': r're:https?://.*\.jpg',
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
             'params': {
                 'skip_download': True,
@@ -157,7 +194,7 @@ class SoundcloudIE(InfoExtractor):
         },
     ]
 
-    _CLIENT_ID = 'LvWovRaJZlWCHql0bISuum8Bd2KX79mb'
+    _CLIENT_ID = 'NmW1FlPaiL94ueEu7oziOWjYEzZzQDcK'
 
     @staticmethod
     def _extract_urls(webpage):
@@ -175,22 +212,33 @@ class SoundcloudIE(InfoExtractor):
 
     def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None):
         track_id = compat_str(info['id'])
+        title = info['title']
         name = full_title or track_id
         if quiet:
             self.report_extraction(name)
         thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url')
         if isinstance(thumbnail, compat_str):
             thumbnail = thumbnail.replace('-large', '-t500x500')
+        username = try_get(info, lambda x: x['user']['username'], compat_str)
+
+        def extract_count(key):
+            return int_or_none(info.get('%s_count' % key))
+
         result = {
             'id': track_id,
-            'uploader': info.get('user', {}).get('username'),
-            'upload_date': unified_strdate(info.get('created_at')),
-            'title': info['title'],
+            'uploader': username,
+            'timestamp': unified_timestamp(info.get('created_at')),
+            'title': title,
             'description': info.get('description'),
             'thumbnail': thumbnail,
             'duration': int_or_none(info.get('duration'), 1000),
             'webpage_url': info.get('permalink_url'),
             'license': info.get('license'),
+            'view_count': extract_count('playback'),
+            'like_count': extract_count('favoritings'),
+            'comment_count': extract_count('comment'),
+            'repost_count': extract_count('reposts'),
+            'genre': info.get('genre'),
         }
         formats = []
         query = {'client_id': self._CLIENT_ID}
@@ -368,7 +416,6 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
 
 
 class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
-    _API_BASE = 'https://api.soundcloud.com'
     _API_V2_BASE = 'https://api-v2.soundcloud.com'
 
     def _extract_playlist(self, base_url, playlist_id, playlist_title):
@@ -389,21 +436,30 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
                 next_href, playlist_id, 'Downloading track page %s' % (i + 1))
 
             collection = response['collection']
-            if not collection:
-                break
 
-            def resolve_permalink_url(candidates):
+            if not isinstance(collection, list):
+                collection = []
+
+            # Empty collection may be returned, in this case we proceed
+            # straight to next_href
+
+            def resolve_entry(candidates):
                 for cand in candidates:
-                    if isinstance(cand, dict):
-                        permalink_url = cand.get('permalink_url')
-                        entry_id = self._extract_id(cand)
-                        if permalink_url and permalink_url.startswith('http'):
-                            return permalink_url, entry_id
+                    if not isinstance(cand, dict):
+                        continue
+                    permalink_url = url_or_none(cand.get('permalink_url'))
+                    if not permalink_url:
+                        continue
+                    return self.url_result(
+                        permalink_url,
+                        ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None,
+                        video_id=self._extract_id(cand),
+                        video_title=cand.get('title'))
 
             for e in collection:
-                permalink_url, entry_id = resolve_permalink_url((e, e.get('track'), e.get('playlist')))
-                if permalink_url:
-                    entries.append(self.url_result(permalink_url, video_id=entry_id))
+                entry = resolve_entry((e, e.get('track'), e.get('playlist')))
+                if entry:
+                    entries.append(entry)
 
             next_href = response.get('next_href')
             if not next_href:
@@ -429,46 +485,53 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
                             (?:(?:www|m)\.)?soundcloud\.com/
                             (?P<user>[^/]+)
                             (?:/
-                                (?P<rsrc>tracks|sets|reposts|likes|spotlight)
+                                (?P<rsrc>tracks|albums|sets|reposts|likes|spotlight)
                             )?
                             /?(?:[?#].*)?$
                     '''
     IE_NAME = 'soundcloud:user'
     _TESTS = [{
-        'url': 'https://soundcloud.com/the-akashic-chronicler',
+        'url': 'https://soundcloud.com/soft-cell-official',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (All)',
+            'id': '207965082',
+            'title': 'Soft Cell (All)',
         },
-        'playlist_mincount': 74,
+        'playlist_mincount': 28,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/tracks',
+        'url': 'https://soundcloud.com/soft-cell-official/tracks',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (Tracks)',
+            'id': '207965082',
+            'title': 'Soft Cell (Tracks)',
         },
-        'playlist_mincount': 37,
+        'playlist_mincount': 27,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/sets',
+        'url': 'https://soundcloud.com/soft-cell-official/albums',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (Playlists)',
+            'id': '207965082',
+            'title': 'Soft Cell (Albums)',
+        },
+        'playlist_mincount': 1,
+    }, {
+        'url': 'https://soundcloud.com/jcv246/sets',
+        'info_dict': {
+            'id': '12982173',
+            'title': 'Jordi / cv (Playlists)',
         },
         'playlist_mincount': 2,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/reposts',
+        'url': 'https://soundcloud.com/jcv246/reposts',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (Reposts)',
+            'id': '12982173',
+            'title': 'Jordi / cv (Reposts)',
         },
-        'playlist_mincount': 7,
+        'playlist_mincount': 6,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/likes',
+        'url': 'https://soundcloud.com/clalberg/likes',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (Likes)',
+            'id': '11817582',
+            'title': 'clalberg (Likes)',
         },
-        'playlist_mincount': 321,
+        'playlist_mincount': 5,
     }, {
         'url': 'https://soundcloud.com/grynpyret/spotlight',
         'info_dict': {
@@ -479,10 +542,11 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
     }]
 
     _BASE_URL_MAP = {
-        'all': '%s/profile/soundcloud:users:%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_BASE,
+        'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+        'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+        'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
         'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'reposts': '%s/profile/soundcloud:users:%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+        'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
         'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
         'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
     }
@@ -490,6 +554,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
     _TITLE_MAP = {
         'all': 'All',
         'tracks': 'Tracks',
+        'albums': 'Albums',
         'sets': 'Playlists',
         'reposts': 'Reposts',
         'likes': 'Likes',

youtube_dl/extractor/spankbang.py

@@ -5,14 +5,17 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    orderedSet,
     parse_duration,
     parse_resolution,
     str_to_int,
+    url_or_none,
+    urlencode_postdata,
 )
 
 
 class SpankBangIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
+    _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
     _TESTS = [{
         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
         'md5': '1cc433e1d6aa14bc376535b8679302f7',
@@ -41,29 +44,71 @@ class SpankBangIE(InfoExtractor):
         # 4k
         'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
         'only_matching': True,
+    }, {
+        'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
+        'only_matching': True,
+    }, {
+        'url': 'https://m.spankbang.com/3vvn/play',
+        'only_matching': True,
+    }, {
+        'url': 'https://spankbang.com/2y3td/embed/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id, headers={
-            'Cookie': 'country=US'
-        })
+        webpage = self._download_webpage(
+            url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
+            video_id, headers={'Cookie': 'country=US'})
 
         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
             raise ExtractorError(
                 'Video %s is not available' % video_id, expected=True)
 
         formats = []
-        for mobj in re.finditer(
-                r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
-                webpage):
-            format_id, format_url = mobj.group('id', 'url')
+
+        def extract_format(format_id, format_url):
+            f_url = url_or_none(format_url)
+            if not f_url:
+                return
             f = parse_resolution(format_id)
             f.update({
-                'url': format_url,
+                'url': f_url,
                 'format_id': format_id,
             })
             formats.append(f)
+
+        STREAM_URL_PREFIX = 'stream_url_'
+
+        for mobj in re.finditer(
+                r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
+                % STREAM_URL_PREFIX, webpage):
+            extract_format(mobj.group('id', 'url'))
+
+        if not formats:
+            stream_key = self._search_regex(
+                r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+                webpage, 'stream key', group='value')
+
+            sb_csrf_session = self._get_cookies(
+                'https://spankbang.com')['sb_csrf_session'].value
+
+            stream = self._download_json(
+                'https://spankbang.com/api/videos/stream', video_id,
+                'Downloading stream JSON', data=urlencode_postdata({
+                    'id': stream_key,
+                    'data': 0,
+                    'sb_csrf_session': sb_csrf_session,
+                }), headers={
+                    'Referer': url,
+                    'X-CSRFToken': sb_csrf_session,
+                })
+
+            for format_id, format_url in stream.items():
+                if format_id.startswith(STREAM_URL_PREFIX):
+                    extract_format(
+                        format_id[len(STREAM_URL_PREFIX):], format_url)
+
         self._sort_formats(formats)
 
         title = self._html_search_regex(
@@ -94,3 +139,33 @@ class SpankBangIE(InfoExtractor):
             'formats': formats,
             'age_limit': age_limit,
         }
+
+
+class SpankBangPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
+    _TEST = {
+        'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
+        'info_dict': {
+            'id': 'ug0k',
+            'title': 'Big Ass Titties',
+        },
+        'playlist_mincount': 50,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
+
+        entries = [self.url_result(
+            'https://spankbang.com/%s/video' % video_id,
+            ie=SpankBangIE.ie_key(), video_id=video_id)
+            for video_id in orderedSet(re.findall(
+                r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
+
+        title = self._html_search_regex(
+            r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
+            fatal=False)
+
+        return self.playlist_result(entries, playlist_id, title)

youtube_dl/extractor/spike.py

@@ -46,8 +46,12 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
     _GEO_COUNTRIES = ['US']
 
     def _extract_mgid(self, webpage):
-        cs = self._parse_json(self._search_regex(
+        root_data = self._parse_json(self._search_regex(
             r'window\.__DATA__\s*=\s*({.+})',
-            webpage, 'data'), None)['children']
-        c = next(c for c in cs if c.get('type') == 'VideoPlayer')
+            webpage, 'data'), None)
+
+        def find_sub_data(data, data_type):
+            return next(c for c in data['children'] if c.get('type') == data_type)
+
+        c = find_sub_data(find_sub_data(root_data, 'MainContainer'), 'VideoPlayer')
         return c['props']['media']['video']['config']['uri']

youtube_dl/extractor/streamango.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class StreamangoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?streamango\.com/(?:f|embed)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net)/(?:f|embed)/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4',
         'md5': 'e992787515a182f55e38fc97588d802a',
@@ -38,6 +38,9 @@ class StreamangoIE(InfoExtractor):
     }, {
         'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4',
         'only_matching': True,
+    }, {
+        'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/teachable.py

@@ -27,6 +27,7 @@ class TeachableBaseIE(InfoExtractor):
         'market.saleshacker.com': 'saleshacker',
         'learnability.org': 'learnability',
         'edurila.com': 'edurila',
+        'courses.workitdaily.com': 'workitdaily',
     }
 
     _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys()))

youtube_dl/extractor/ted.py

@@ -203,10 +203,8 @@ class TEDIE(InfoExtractor):
                 ext_url = None
                 if service.lower() == 'youtube':
                     ext_url = external.get('code')
-                return {
-                    '_type': 'url',
-                    'url': ext_url or external['uri'],
-                }
+
+                return self.url_result(ext_url or external['uri'])
 
         resources_ = player_talk.get('resources') or talk_info.get('resources')
 
@@ -267,6 +265,8 @@ class TEDIE(InfoExtractor):
                     'format_id': m3u8_format['format_id'].replace('hls', 'http'),
                     'protocol': 'http',
                 })
+                if f.get('acodec') == 'none':
+                    del f['acodec']
                 formats.append(f)
 
         audio_download = talk_info.get('audioDownload')

youtube_dl/extractor/testurl.py

@@ -61,8 +61,4 @@ class TestURLIE(InfoExtractor):
 
         self.to_screen('Test URL: %s' % tc['url'])
 
-        return {
-            '_type': 'url',
-            'url': tc['url'],
-            'id': video_id,
-        }
+        return self.url_result(tc['url'], video_id=video_id)

youtube_dl/extractor/tnaflix.py

@@ -96,7 +96,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
 
         cfg_xml = self._download_xml(
             cfg_url, display_id, 'Downloading metadata',
-            transform_source=fix_xml_ampersands)
+            transform_source=fix_xml_ampersands, headers={'Referer': url})
 
         formats = []
 

youtube_dl/extractor/toutv.py

@@ -1,24 +1,21 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
+import json
 
-from .common import InfoExtractor
+from .radiocanada import RadioCanadaIE
+from ..compat import compat_HTTPError
 from ..utils import (
+    ExtractorError,
     int_or_none,
-    js_to_json,
-    urlencode_postdata,
-    extract_attributes,
-    smuggle_url,
+    merge_dicts,
 )
 
 
-class TouTvIE(InfoExtractor):
+class TouTvIE(RadioCanadaIE):
     _NETRC_MACHINE = 'toutv'
     IE_NAME = 'tou.tv'
     _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)'
-    _access_token = None
-    _claims = None
 
     _TESTS = [{
         'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
@@ -41,57 +38,31 @@ class TouTvIE(InfoExtractor):
         'url': 'https://ici.tou.tv/l-age-adulte/S01C501',
         'only_matching': True,
     }]
+    _CLIENT_KEY = '4dd36440-09d5-4468-8923-b6d91174ad36'
 
     def _real_initialize(self):
         email, password = self._get_login_info()
         if email is None:
             return
-        state = 'http://ici.tou.tv/'
-        webpage = self._download_webpage(state, None, 'Downloading homepage')
-        toutvlogin = self._parse_json(self._search_regex(
-            r'(?s)toutvlogin\s*=\s*({.+?});', webpage, 'toutvlogin'), None, js_to_json)
-        authorize_url = toutvlogin['host'] + '/auth/oauth/v2/authorize'
-        login_webpage = self._download_webpage(
-            authorize_url, None, 'Downloading login page', query={
-                'client_id': toutvlogin['clientId'],
-                'redirect_uri': 'https://ici.tou.tv/login/loginCallback',
-                'response_type': 'token',
-                'scope': 'media-drmt openid profile email id.write media-validation.read.privileged',
-                'state': state,
-            })
-
-        def extract_form_url_and_data(wp, default_form_url, form_spec_re=''):
-            form, form_elem = re.search(
-                r'(?s)((<form[^>]+?%s[^>]*?>).+?</form>)' % form_spec_re, wp).groups()
-            form_data = self._hidden_inputs(form)
-            form_url = extract_attributes(form_elem).get('action') or default_form_url
-            return form_url, form_data
-
-        post_url, form_data = extract_form_url_and_data(
-            login_webpage,
-            'https://services.radio-canada.ca/auth/oauth/v2/authorize/login',
-            r'(?:id|name)="Form-login"')
-        form_data.update({
-            'login-email': email,
-            'login-password': password,
-        })
-        consent_webpage = self._download_webpage(
-            post_url, None, 'Logging in', data=urlencode_postdata(form_data))
-        post_url, form_data = extract_form_url_and_data(
-            consent_webpage,
-            'https://services.radio-canada.ca/auth/oauth/v2/authorize/consent')
-        _, urlh = self._download_webpage_handle(
-            post_url, None, 'Following Redirection',
-            data=urlencode_postdata(form_data))
-        self._access_token = self._search_regex(
-            r'access_token=([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
-            urlh.geturl(), 'access token')
-        self._claims = self._download_json(
-            'https://services.radio-canada.ca/media/validation/v2/getClaims',
-            None, 'Extracting Claims', query={
-                'token': self._access_token,
-                'access_token': self._access_token,
-            })['claims']
+        try:
+            self._access_token = self._download_json(
+                'https://services.radio-canada.ca/toutv/profiling/accounts/login',
+                None, 'Logging in', data=json.dumps({
+                    'ClientId': self._CLIENT_KEY,
+                    'ClientSecret': '34026772-244b-49b6-8b06-317b30ac9a20',
+                    'Email': email,
+                    'Password': password,
+                    'Scope': 'id.write media-validation.read',
+                }).encode(), headers={
+                    'Authorization': 'client-key ' + self._CLIENT_KEY,
+                    'Content-Type': 'application/json;charset=utf-8',
+                })['access_token']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                error = self._parse_json(e.cause.read().decode(), None)['Message']
+                raise ExtractorError(error, expected=True)
+            raise
+        self._claims = self._call_api('validation/v2/getClaims')['claims']
 
     def _real_extract(self, url):
         path = self._match_id(url)
@@ -102,19 +73,10 @@ class TouTvIE(InfoExtractor):
             self.report_warning('This video is probably DRM protected.', path)
         video_id = metadata['IdMedia']
         details = metadata['Details']
-        title = details['OriginalTitle']
-        video_url = 'radiocanada:%s:%s' % (metadata.get('AppCode', 'toutv'), video_id)
-        if self._access_token and self._claims:
-            video_url = smuggle_url(video_url, {
-                'access_token': self._access_token,
-                'claims': self._claims,
-            })
 
-        return {
-            '_type': 'url_transparent',
-            'url': video_url,
+        return merge_dicts({
             'id': video_id,
-            'title': title,
+            'title': details.get('OriginalTitle'),
             'thumbnail': details.get('ImageUrl'),
             'duration': int_or_none(details.get('LengthInSeconds')),
-        }
+        }, self._extract_info(metadata.get('AppCode', 'toutv'), video_id))

youtube_dl/extractor/trunews.py

@@ -0,0 +1,75 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    dict_get,
+    float_or_none,
+    int_or_none,
+    unified_timestamp,
+    update_url_query,
+    url_or_none,
+)
+
+
+class TruNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?trunews\.com/stream/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://www.trunews.com/stream/will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech',
+        'md5': 'a19c024c3906ff954fac9b96ce66bb08',
+        'info_dict': {
+            'id': '5c5a21e65d3c196e1c0020cc',
+            'display_id': 'will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech',
+            'ext': 'mp4',
+            'title': "Will Democrats Stage a Circus During President Trump's State of the Union Speech?",
+            'description': 'md5:c583b72147cc92cf21f56a31aff7a670',
+            'duration': 3685,
+            'timestamp': 1549411440,
+            'upload_date': '20190206',
+        },
+        'add_ie': ['Zype'],
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        video = self._download_json(
+            'https://api.zype.com/videos', display_id, query={
+                'app_key': 'PUVKp9WgGUb3-JUw6EqafLx8tFVP6VKZTWbUOR-HOm__g4fNDt1bCsm_LgYf_k9H',
+                'per_page': 1,
+                'active': 'true',
+                'friendly_title': display_id,
+            })['response'][0]
+
+        zype_id = video['_id']
+
+        thumbnails = []
+        thumbnails_list = video.get('thumbnails')
+        if isinstance(thumbnails_list, list):
+            for thumbnail in thumbnails_list:
+                if not isinstance(thumbnail, dict):
+                    continue
+                thumbnail_url = url_or_none(thumbnail.get('url'))
+                if not thumbnail_url:
+                    continue
+                thumbnails.append({
+                    'url': thumbnail_url,
+                    'width': int_or_none(thumbnail.get('width')),
+                    'height': int_or_none(thumbnail.get('height')),
+                })
+
+        return {
+            '_type': 'url_transparent',
+            'url': update_url_query(
+                'https://player.zype.com/embed/%s.js' % zype_id,
+                {'api_key': 'X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt'}),
+            'ie_key': 'Zype',
+            'id': zype_id,
+            'display_id': display_id,
+            'title': video.get('title'),
+            'description': dict_get(video, ('description', 'ott_description', 'short_description')),
+            'duration': int_or_none(video.get('duration')),
+            'timestamp': unified_timestamp(video.get('published_at')),
+            'average_rating': float_or_none(video.get('rating')),
+            'view_count': int_or_none(video.get('request_count')),
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/trutv.py

@@ -4,44 +4,72 @@ from __future__ import unicode_literals
 import re
 
 from .turner import TurnerBaseIE
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class TruTVIE(TurnerBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?trutv\.com(?:(?P<path>/shows/[^/]+/videos/[^/?#]+?)\.html|/full-episodes/[^/]+/(?P<id>\d+))'
+    _VALID_URL = r'https?://(?:www\.)?trutv\.com/(?:shows|full-episodes)/(?P<series_slug>[0-9A-Za-z-]+)/(?:videos/(?P<clip_slug>[0-9A-Za-z-]+)|(?P<id>\d+))'
     _TEST = {
-        'url': 'http://www.trutv.com/shows/10-things/videos/you-wont-believe-these-sports-bets.html',
-        'md5': '2cdc844f317579fed1a7251b087ff417',
+        'url': 'https://www.trutv.com/shows/the-carbonaro-effect/videos/sunlight-activated-flower.html',
         'info_dict': {
-            'id': '/shows/10-things/videos/you-wont-believe-these-sports-bets',
+            'id': 'f16c03beec1e84cd7d1a51f11d8fcc29124cc7f1',
             'ext': 'mp4',
-            'title': 'You Won\'t Believe These Sports Bets',
-            'description': 'Jamie Lee sits down with a bookie to discuss the bizarre world of illegal sports betting.',
-            'upload_date': '20130305',
-        }
+            'title': 'Sunlight-Activated Flower',
+            'description': "A customer is stunned when he sees Michael's sunlight-activated flower.",
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
-        path, video_id = re.match(self._VALID_URL, url).groups()
-        auth_required = False
-        if path:
-            data_src = 'http://www.trutv.com/video/cvp/v2/xml/content.xml?id=%s.xml' % path
+        series_slug, clip_slug, video_id = re.match(self._VALID_URL, url).groups()
+
+        if video_id:
+            path = 'episode'
+            display_id = video_id
         else:
-            webpage = self._download_webpage(url, video_id)
-            video_id = self._search_regex(
-                r"TTV\.TVE\.episodeId\s*=\s*'([^']+)';",
-                webpage, 'video id', default=video_id)
-            auth_required = self._search_regex(
-                r'TTV\.TVE\.authRequired\s*=\s*(true|false);',
-                webpage, 'auth required', default='false') == 'true'
-            data_src = 'http://www.trutv.com/tveverywhere/services/cvpXML.do?titleId=' + video_id
-        return self._extract_cvp_info(
-            data_src, path, {
-                'secure': {
-                    'media_src': 'http://androidhls-secure.cdn.turner.com/trutv/big',
-                    'tokenizer_src': 'http://www.trutv.com/tveverywhere/processors/services/token_ipadAdobe.do',
-                },
-            }, {
+            path = 'series/clip'
+            display_id = clip_slug
+
+        data = self._download_json(
+            'https://api.trutv.com/v2/web/%s/%s/%s' % (path, series_slug, display_id),
+            display_id)
+        video_data = data['episode'] if video_id else data['info']
+        media_id = video_data['mediaId']
+        title = video_data['title'].strip()
+
+        info = self._extract_ngtv_info(
+            media_id, {}, {
                 'url': url,
                 'site_name': 'truTV',
-                'auth_required': auth_required,
+                'auth_required': video_data.get('isAuthRequired'),
             })
+
+        thumbnails = []
+        for image in video_data.get('images', []):
+            image_url = image.get('srcUrl')
+            if not image_url:
+                continue
+            thumbnails.append({
+                'url': image_url,
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),
+            })
+
+        info.update({
+            'id': media_id,
+            'display_id': display_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'thumbnails': thumbnails,
+            'timestamp': parse_iso8601(video_data.get('publicationDate')),
+            'series': video_data.get('showTitle'),
+            'season_number': int_or_none(video_data.get('seasonNum')),
+            'episode_number': int_or_none(video_data.get('episodeNum')),
+        })
+        return info

youtube_dl/extractor/tvnow.py

@@ -10,8 +10,9 @@ from ..utils import (
     int_or_none,
     parse_iso8601,
     parse_duration,
-    try_get,
+    str_or_none,
     update_url_query,
+    urljoin,
 )
 
 
@@ -24,8 +25,7 @@ class TVNowBaseIE(InfoExtractor):
 
     def _call_api(self, path, video_id, query):
         return self._download_json(
-            'https://api.tvnow.de/v3/' + path,
-            video_id, query=query)
+            'https://api.tvnow.de/v3/' + path, video_id, query=query)
 
     def _extract_video(self, info, display_id):
         video_id = compat_str(info['id'])
@@ -108,6 +108,11 @@ class TVNowIE(TVNowBaseIE):
                         (?!(?:list|jahr)(?:/|$))(?P<id>[^/?\#&]+)
                     '''
 
+    @classmethod
+    def suitable(cls, url):
+        return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) or TVNowShowIE.suitable(url)
+                else super(TVNowIE, cls).suitable(url))
+
     _TESTS = [{
         'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/der-neue-porsche-911-gt-3/player',
         'info_dict': {
@@ -116,7 +121,6 @@ class TVNowIE(TVNowBaseIE):
             'ext': 'mp4',
             'title': 'Der neue Porsche 911 GT 3',
             'description': 'md5:6143220c661f9b0aae73b245e5d898bb',
-            'thumbnail': r're:^https?://.*\.jpg$',
             'timestamp': 1495994400,
             'upload_date': '20170528',
             'duration': 5283,
@@ -161,136 +165,314 @@ class TVNowIE(TVNowBaseIE):
         info = self._call_api(
             'movies/' + display_id, display_id, query={
                 'fields': ','.join(self._VIDEO_FIELDS),
-                'station': mobj.group(1),
             })
 
         return self._extract_video(info, display_id)
 
 
-class TVNowListBaseIE(TVNowBaseIE):
-    _SHOW_VALID_URL = r'''(?x)
-                    (?P<base_url>
-                        https?://
-                            (?:www\.)?tvnow\.(?:de|at|ch)/[^/]+/
-                            (?P<show_id>[^/]+)
-                    )
+class TVNowNewIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    (?P<base_url>https?://
+                        (?:www\.)?tvnow\.(?:de|at|ch)/
+                        (?:shows|serien))/
+                        (?P<show>[^/]+)-\d+/
+                        [^/]+/
+                        episode-\d+-(?P<episode>[^/?$&]+)-(?P<id>\d+)
                     '''
 
-    def _extract_list_info(self, display_id, show_id):
-        fields = list(self._SHOW_FIELDS)
-        fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS)
-        fields.extend(
-            'formatTabs.formatTabPages.container.movies.%s' % field
-            for field in self._VIDEO_FIELDS)
-        return self._call_api(
-            'formats/seo', display_id, query={
-                'fields': ','.join(fields),
-                'name': show_id + '.php'
-            })
-
-
-class TVNowListIE(TVNowListBaseIE):
-    _VALID_URL = r'%s/(?:list|jahr)/(?P<id>[^?\#&]+)' % TVNowListBaseIE._SHOW_VALID_URL
-
-    _SHOW_FIELDS = ('title', )
-    _SEASON_FIELDS = ('id', 'headline', 'seoheadline', )
-    _VIDEO_FIELDS = ('id', 'headline', 'seoUrl', )
-
     _TESTS = [{
-        'url': 'https://www.tvnow.de/rtl/30-minuten-deutschland/list/aktuell',
-        'info_dict': {
-            'id': '28296',
-            'title': '30 Minuten Deutschland - Aktuell',
-        },
-        'playlist_mincount': 1,
-    }, {
-        'url': 'https://www.tvnow.de/vox/ab-ins-beet/list/staffel-14',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/2018/3',
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082',
         'only_matching': True,
     }]
 
-    @classmethod
-    def suitable(cls, url):
-        return (False if TVNowIE.suitable(url)
-                else super(TVNowListIE, cls).suitable(url))
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        base_url = re.sub(r'(?:shows|serien)', '_', mobj.group('base_url'))
+        show, episode = mobj.group('show', 'episode')
+        return self.url_result(
+            # Rewrite new URLs to the old format and use extraction via old API
+            # at api.tvnow.de as a loophole for bypassing premium content checks
+            '%s/%s/%s' % (base_url, show, episode),
+            ie=TVNowIE.ie_key(), video_id=mobj.group('id'))
+
+
+class TVNowNewBaseIE(InfoExtractor):
+    def _call_api(self, path, video_id, query={}):
+        result = self._download_json(
+            'https://apigw.tvnow.de/module/' + path, video_id, query=query)
+        error = result.get('error')
+        if error:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, error), expected=True)
+        return result
+
+
+"""
+TODO: new apigw.tvnow.de based version of TVNowIE. Replace old TVNowIE with it
+when api.tvnow.de is shut down. This version can't bypass premium checks though.
+class TVNowIE(TVNowNewBaseIE):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?tvnow\.(?:de|at|ch)/
+                        (?:shows|serien)/[^/]+/
+                        (?:[^/]+/)+
+                        (?P<display_id>[^/?$&]+)-(?P<id>\d+)
+                    '''
+
+    _TESTS = [{
+        # episode with annual navigation
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082',
+        'info_dict': {
+            'id': '331082',
+            'display_id': 'grip-das-motormagazin/der-neue-porsche-911-gt-3',
+            'ext': 'mp4',
+            'title': 'Der neue Porsche 911 GT 3',
+            'description': 'md5:6143220c661f9b0aae73b245e5d898bb',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'timestamp': 1495994400,
+            'upload_date': '20170528',
+            'duration': 5283,
+            'series': 'GRIP - Das Motormagazin',
+            'season_number': 14,
+            'episode_number': 405,
+            'episode': 'Der neue Porsche 911 GT 3',
+        },
+    }, {
+        # rtl2, episode with season navigation
+        'url': 'https://www.tvnow.de/shows/armes-deutschland-11471/staffel-3/episode-14-bernd-steht-seit-der-trennung-von-seiner-frau-allein-da-526124',
+        'only_matching': True,
+    }, {
+        # rtlnitro
+        'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13/episode-5-auf-eigene-faust-pilot-366822',
+        'only_matching': True,
+    }, {
+        # superrtl
+        'url': 'https://www.tvnow.de/shows/die-lustigsten-schlamassel-der-welt-1221/staffel-2/episode-14-u-a-ketchup-effekt-364120',
+        'only_matching': True,
+    }, {
+        # ntv
+        'url': 'https://www.tvnow.de/shows/startup-news-10674/staffel-2/episode-39-goetter-in-weiss-387630',
+        'only_matching': True,
+    }, {
+        # vox
+        'url': 'https://www.tvnow.de/shows/auto-mobil-174/2017-11/episode-46-neues-vom-automobilmarkt-2017-11-19-17-00-00-380072',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082',
+        'only_matching': True,
+    }]
+
+    def _extract_video(self, info, url, display_id):
+        config = info['config']
+        source = config['source']
+
+        video_id = compat_str(info.get('id') or source['videoId'])
+        title = source['title'].strip()
+
+        paths = []
+        for manifest_url in (info.get('manifest') or {}).values():
+            if not manifest_url:
+                continue
+            manifest_url = update_url_query(manifest_url, {'filter': ''})
+            path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path')
+            if path in paths:
+                continue
+            paths.append(path)
+
+            def url_repl(proto, suffix):
+                return re.sub(
+                    r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub(
+                        r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)',
+                        '.ism/' + suffix, manifest_url))
+
+            formats = self._extract_mpd_formats(
+                url_repl('dash', '.mpd'), video_id,
+                mpd_id='dash', fatal=False)
+            formats.extend(self._extract_ism_formats(
+                url_repl('hss', 'Manifest'),
+                video_id, ism_id='mss', fatal=False))
+            formats.extend(self._extract_m3u8_formats(
+                url_repl('hls', '.m3u8'), video_id, 'mp4',
+                'm3u8_native', m3u8_id='hls', fatal=False))
+            if formats:
+                break
+        else:
+            if try_get(info, lambda x: x['rights']['isDrm']):
+                raise ExtractorError(
+                    'Video %s is DRM protected' % video_id, expected=True)
+            if try_get(config, lambda x: x['boards']['geoBlocking']['block']):
+                raise self.raise_geo_restricted()
+            if not info.get('free', True):
+                raise ExtractorError(
+                    'Video %s is not available for free' % video_id, expected=True)
+        self._sort_formats(formats)
+
+        description = source.get('description')
+        thumbnail = url_or_none(source.get('poster'))
+        timestamp = unified_timestamp(source.get('previewStart'))
+        duration = parse_duration(source.get('length'))
+
+        series = source.get('format')
+        season_number = int_or_none(self._search_regex(
+            r'staffel-(\d+)', url, 'season number', default=None))
+        episode_number = int_or_none(self._search_regex(
+            r'episode-(\d+)', url, 'episode number', default=None))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'series': series,
+            'season_number': season_number,
+            'episode_number': episode_number,
+            'episode': title,
+            'formats': formats,
+        }
 
     def _real_extract(self, url):
-        base_url, show_id, season_id = re.match(self._VALID_URL, url).groups()
+        display_id, video_id = re.match(self._VALID_URL, url).groups()
+        info = self._call_api('player/' + video_id, video_id)
+        return self._extract_video(info, video_id, display_id)
+"""
 
-        list_info = self._extract_list_info(season_id, show_id)
 
-        season = next(
-            season for season in list_info['formatTabs']['items']
-            if season.get('seoheadline') == season_id)
+class TVNowListBaseIE(TVNowNewBaseIE):
+    _SHOW_VALID_URL = r'''(?x)
+                    (?P<base_url>
+                        https?://
+                            (?:www\.)?tvnow\.(?:de|at|ch)/(?:shows|serien)/
+                            [^/?#&]+-(?P<show_id>\d+)
+                    )
+                    '''
 
-        title = list_info.get('title')
-        headline = season.get('headline')
-        if title and headline:
-            title = '%s - %s' % (title, headline)
-        else:
-            title = headline or title
+    @classmethod
+    def suitable(cls, url):
+        return (False if TVNowNewIE.suitable(url)
+                else super(TVNowListBaseIE, cls).suitable(url))
+
+    def _extract_items(self, url, show_id, list_id, query):
+        items = self._call_api(
+            'teaserrow/format/episode/' + show_id, list_id,
+            query=query)['items']
 
         entries = []
-        for container in season['formatTabPages']['items']:
-            items = try_get(
-                container, lambda x: x['container']['movies']['items'],
-                list) or []
-            for info in items:
-                seo_url = info.get('seoUrl')
-                if not seo_url:
-                    continue
-                video_id = info.get('id')
-                entries.append(self.url_result(
-                    '%s/%s/player' % (base_url, seo_url), TVNowIE.ie_key(),
-                    compat_str(video_id) if video_id else None))
+        for item in items:
+            if not isinstance(item, dict):
+                continue
+            item_url = urljoin(url, item.get('url'))
+            if not item_url:
+                continue
+            video_id = str_or_none(item.get('id') or item.get('videoId'))
+            item_title = item.get('subheadline') or item.get('text')
+            entries.append(self.url_result(
+                item_url, ie=TVNowNewIE.ie_key(), video_id=video_id,
+                video_title=item_title))
 
-        return self.playlist_result(
-            entries, compat_str(season.get('id') or season_id), title)
+        return self.playlist_result(entries, '%s/%s' % (show_id, list_id))
+
+
+class TVNowSeasonIE(TVNowListBaseIE):
+    _VALID_URL = r'%s/staffel-(?P<id>\d+)' % TVNowListBaseIE._SHOW_VALID_URL
+    _TESTS = [{
+        'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13',
+        'info_dict': {
+            'id': '1815/13',
+        },
+        'playlist_mincount': 22,
+    }]
+
+    def _real_extract(self, url):
+        _, show_id, season_id = re.match(self._VALID_URL, url).groups()
+        return self._extract_items(
+            url, show_id, season_id, {'season': season_id})
+
+
+class TVNowAnnualIE(TVNowListBaseIE):
+    _VALID_URL = r'%s/(?P<year>\d{4})-(?P<month>\d{2})' % TVNowListBaseIE._SHOW_VALID_URL
+    _TESTS = [{
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05',
+        'info_dict': {
+            'id': '1669/2017-05',
+        },
+        'playlist_mincount': 2,
+    }]
+
+    def _real_extract(self, url):
+        _, show_id, year, month = re.match(self._VALID_URL, url).groups()
+        return self._extract_items(
+            url, show_id, '%s-%s' % (year, month), {
+                'year': int(year),
+                'month': int(month),
+            })
 
 
 class TVNowShowIE(TVNowListBaseIE):
     _VALID_URL = TVNowListBaseIE._SHOW_VALID_URL
-
-    _SHOW_FIELDS = ('id', 'title', )
-    _SEASON_FIELDS = ('id', 'headline', 'seoheadline', )
-    _VIDEO_FIELDS = ()
-
     _TESTS = [{
-        'url': 'https://www.tvnow.at/vox/ab-ins-beet',
+        # annual navigationType
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669',
         'info_dict': {
-            'id': 'ab-ins-beet',
-            'title': 'Ab ins Beet!',
+            'id': '1669',
         },
-        'playlist_mincount': 7,
+        'playlist_mincount': 73,
     }, {
-        'url': 'https://www.tvnow.at/vox/ab-ins-beet/list',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/',
-        'only_matching': True,
+        # season navigationType
+        'url': 'https://www.tvnow.de/shows/armes-deutschland-11471',
+        'info_dict': {
+            'id': '11471',
+        },
+        'playlist_mincount': 3,
     }]
 
     @classmethod
     def suitable(cls, url):
-        return (False if TVNowIE.suitable(url) or TVNowListIE.suitable(url)
+        return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url)
                 else super(TVNowShowIE, cls).suitable(url))
 
     def _real_extract(self, url):
         base_url, show_id = re.match(self._VALID_URL, url).groups()
 
-        list_info = self._extract_list_info(show_id, show_id)
+        result = self._call_api(
+            'teaserrow/format/navigation/' + show_id, show_id)
+
+        items = result['items']
 
         entries = []
-        for season_info in list_info['formatTabs']['items']:
-            season_url = season_info.get('seoheadline')
-            if not season_url:
-                continue
-            season_id = season_info.get('id')
-            entries.append(self.url_result(
-                '%s/list/%s' % (base_url, season_url), TVNowListIE.ie_key(),
-                compat_str(season_id) if season_id else None,
-                season_info.get('headline')))
+        navigation = result.get('navigationType')
+        if navigation == 'annual':
+            for item in items:
+                if not isinstance(item, dict):
+                    continue
+                year = int_or_none(item.get('year'))
+                if year is None:
+                    continue
+                months = item.get('months')
+                if not isinstance(months, list):
+                    continue
+                for month_dict in months:
+                    if not isinstance(month_dict, dict) or not month_dict:
+                        continue
+                    month_number = int_or_none(list(month_dict.keys())[0])
+                    if month_number is None:
+                        continue
+                    entries.append(self.url_result(
+                        '%s/%04d-%02d' % (base_url, year, month_number),
+                        ie=TVNowAnnualIE.ie_key()))
+        elif navigation == 'season':
+            for item in items:
+                if not isinstance(item, dict):
+                    continue
+                season_number = int_or_none(item.get('season'))
+                if season_number is None:
+                    continue
+                entries.append(self.url_result(
+                    '%s/staffel-%d' % (base_url, season_number),
+                    ie=TVNowSeasonIE.ie_key()))
+        else:
+            raise ExtractorError('Unknown navigationType')
 
-        return self.playlist_result(entries, show_id, list_info.get('title'))
+        return self.playlist_result(entries, show_id)

youtube_dl/extractor/tvp.py

@@ -1,14 +1,16 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     clean_html,
-    get_element_by_attribute,
+    determine_ext,
     ExtractorError,
+    get_element_by_attribute,
+    orderedSet,
 )
 
 
@@ -19,12 +21,12 @@ class TVPIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'https://vod.tvp.pl/video/czas-honoru,i-seria-odc-13,194536',
-        'md5': '8aa518c15e5cc32dfe8db400dc921fbb',
+        'md5': 'a21eb0aa862f25414430f15fdfb9e76c',
         'info_dict': {
             'id': '194536',
             'ext': 'mp4',
-            'title': 'Czas honoru, I seria – odc. 13',
-            'description': 'md5:381afa5bca72655fe94b05cfe82bf53d',
+            'title': 'Czas honoru, odc. 13 – Władek',
+            'description': 'md5:437f48b93558370b031740546b696e24',
         },
     }, {
         'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
@@ -45,6 +47,7 @@ class TVPIE(InfoExtractor):
             'title': 'Wiadomości, 28.09.2017, 19:30',
             'description': 'Wydanie główne codziennego serwisu informacyjnego.'
         },
+        'skip': 'HTTP Error 404: Not Found',
     }, {
         'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
         'only_matching': True,
@@ -75,8 +78,10 @@ class TVPIE(InfoExtractor):
         return {
             '_type': 'url_transparent',
             'url': 'tvp:' + video_id,
-            'description': self._og_search_description(webpage, default=None),
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(
+                webpage, default=None) or self._html_search_meta(
+                'description', webpage, default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'ie_key': 'TVPEmbed',
         }
 
@@ -87,6 +92,15 @@ class TVPEmbedIE(InfoExtractor):
     _VALID_URL = r'(?:tvp:|https?://[^/]+\.tvp\.(?:pl|info)/sess/tvplayer\.php\?.*?object_id=)(?P<id>\d+)'
 
     _TESTS = [{
+        'url': 'tvp:194536',
+        'md5': 'a21eb0aa862f25414430f15fdfb9e76c',
+        'info_dict': {
+            'id': '194536',
+            'ext': 'mp4',
+            'title': 'Czas honoru, odc. 13 – Władek',
+        },
+    }, {
+        # not available
         'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268',
         'md5': '8c9cd59d16edabf39331f93bf8a766c7',
         'info_dict': {
@@ -94,6 +108,7 @@ class TVPEmbedIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Panorama, 07.12.2015, 15:40',
         },
+        'skip': 'Transmisja została zakończona lub materiał niedostępny',
     }, {
         'url': 'tvp:22670268',
         'only_matching': True,
@@ -105,10 +120,13 @@ class TVPEmbedIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id)
 
-        error_massage = get_element_by_attribute('class', 'msg error', webpage)
-        if error_massage:
+        error = self._html_search_regex(
+            r'(?s)<p[^>]+\bclass=["\']notAvailable__text["\'][^>]*>(.+?)</p>',
+            webpage, 'error', default=None) or clean_html(
+            get_element_by_attribute('class', 'msg error', webpage))
+        if error:
             raise ExtractorError('%s said: %s' % (
-                self.IE_NAME, clean_html(error_massage)), expected=True)
+                self.IE_NAME, clean_html(error)), expected=True)
 
         title = self._search_regex(
             r'name\s*:\s*([\'"])Title\1\s*,\s*value\s*:\s*\1(?P<title>.+?)\1',
@@ -180,48 +198,55 @@ class TVPEmbedIE(InfoExtractor):
         }
 
 
-class TVPSeriesIE(InfoExtractor):
+class TVPWebsiteIE(InfoExtractor):
     IE_NAME = 'tvp:series'
-    _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$'
+    _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)'
 
     _TESTS = [{
-        'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem',
+        # series
+        'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312/video',
         'info_dict': {
-            'title': 'Ogniem i mieczem',
-            'id': '4278026',
+            'id': '38678312',
         },
-        'playlist_count': 4,
+        'playlist_count': 115,
     }, {
-        'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat',
+        # film
+        'url': 'https://vod.tvp.pl/website/gloria,35139666',
         'info_dict': {
-            'title': 'Boso przez świat',
-            'id': '9329207',
+            'id': '36637049',
+            'ext': 'mp4',
+            'title': 'Gloria, Gloria',
         },
-        'playlist_count': 86,
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['TVPEmbed'],
+    }, {
+        'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312',
+        'only_matching': True,
     }]
 
+    def _entries(self, display_id, playlist_id):
+        url = 'https://vod.tvp.pl/website/%s,%s/video' % (display_id, playlist_id)
+        for page_num in itertools.count(1):
+            page = self._download_webpage(
+                url, display_id, 'Downloading page %d' % page_num,
+                query={'page': page_num})
+
+            video_ids = orderedSet(re.findall(
+                r'<a[^>]+\bhref=["\']/video/%s,[^,]+,(\d+)' % display_id,
+                page))
+
+            if not video_ids:
+                break
+
+            for video_id in video_ids:
+                yield self.url_result(
+                    'tvp:%s' % video_id, ie=TVPEmbedIE.ie_key(),
+                    video_id=video_id)
+
     def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id, tries=5)
-
-        title = self._html_search_regex(
-            r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series')
-        playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id')
-        playlist = self._download_webpage(
-            'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend'
-            'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5,
-            note='Downloading playlist')
-
-        videos_paths = re.findall(
-            '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist)
-        entries = [
-            self.url_result('http://vod.tvp.pl%s' % v_path, ie=TVPIE.ie_key())
-            for v_path in videos_paths]
-
-        return {
-            '_type': 'playlist',
-            'id': playlist_id,
-            'display_id': display_id,
-            'title': title,
-            'entries': entries,
-        }
+        mobj = re.match(self._VALID_URL, url)
+        display_id, playlist_id = mobj.group('display_id', 'id')
+        return self.playlist_result(
+            self._entries(display_id, playlist_id), playlist_id)

youtube_dl/extractor/tvplay.py

@@ -493,10 +493,9 @@ class TVPlayHomeIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._search_regex(
-            r'data-asset-id\s*=\s*["\'](\d{5,7})\b', webpage, 'video id',
-            default=None)
+            r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id')
 
-        if video_id:
+        if len(video_id) < 8:
             return self.url_result(
                 'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
 
@@ -537,8 +536,9 @@ class TVPlayHomeIE(InfoExtractor):
             r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
             default=None))
         episode = self._search_regex(
-            r'(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'episode',
-            default=None, group='value')
+            (r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+             r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+            'episode', default=None, group='value')
         episode_number = int_or_none(self._search_regex(
             r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
             default=None))

youtube_dl/extractor/twitch.py

@@ -136,7 +136,12 @@ class TwitchBaseIE(InfoExtractor):
             source = next(f for f in formats if f['format_id'] == 'Source')
             source['preference'] = 10
         except StopIteration:
-            pass  # No Source stream present
+            for f in formats:
+                if '/chunked/' in f['url']:
+                    f.update({
+                        'source_preference': 10,
+                        'format_note': 'Source',
+                    })
         self._sort_formats(formats)