release 2019.04.07

[ci skip]

.github/ISSUE_TEMPLATE.md

@@ -6,12 +6,12 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.30*. 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 Issues with outdated version will be rejected.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 **2019.01.30**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.04.07*. If it's not, read [this FAQ entry](https://github.com/ytdl-org/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 Issues with outdated version will be rejected.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 **2019.04.07**
 
 ### 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
-- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
+- [ ] At least skimmed through the [README](https://github.com/ytdl-org/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/ytdl-org/youtube-dl#faq) and [BUGS](https://github.com/ytdl-org/youtube-dl#bugs) sections
+- [ ] [Searched](https://github.com/ytdl-org/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
 - [ ] Checked that provided video/audio/playlist URLs (if any) are alive and playable in a browser
 
 ### What is the purpose of your *issue*?
@@ -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 2019.01.30
+[debug] youtube-dl version 2019.04.07
 [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: {}
@@ -51,11 +51,11 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 - Single video: https://youtu.be/BaW_jenozKc
 - Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
 
-Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/rg3/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
+Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 
 ---
 
 ### Description of your *issue*, suggested solution and other information
 
-Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
+Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
 If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

.github/ISSUE_TEMPLATE_tmpl.md

@@ -6,12 +6,12 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *%(version)s*. 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.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *%(version)s*. If it's not, read [this FAQ entry](https://github.com/ytdl-org/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 **%(version)s**
 
 ### 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
-- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
+- [ ] At least skimmed through the [README](https://github.com/ytdl-org/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/ytdl-org/youtube-dl#faq) and [BUGS](https://github.com/ytdl-org/youtube-dl#bugs) sections
+- [ ] [Searched](https://github.com/ytdl-org/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
 - [ ] Checked that provided video/audio/playlist URLs (if any) are alive and playable in a browser
 
 ### What is the purpose of your *issue*?
@@ -51,11 +51,11 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 - Single video: https://youtu.be/BaW_jenozKc
 - Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
 
-Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/rg3/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
+Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 
 ---
 
 ### Description of your *issue*, suggested solution and other information
 
-Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
+Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
 If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

.github/PULL_REQUEST_TEMPLATE.md

@@ -7,8 +7,8 @@
 ---
 
 ### Before submitting a *pull request* make sure you have:
-- [ ] At least skimmed through [adding new extractor tutorial](https://github.com/rg3/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/rg3/youtube-dl#youtube-dl-coding-conventions) sections
-- [ ] [Searched](https://github.com/rg3/youtube-dl/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests
+- [ ] At least skimmed through [adding new extractor tutorial](https://github.com/ytdl-org/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/ytdl-org/youtube-dl#youtube-dl-coding-conventions) sections
+- [ ] [Searched](https://github.com/ytdl-org/youtube-dl/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests
 - [ ] Checked the code with [flake8](https://pypi.python.org/pypi/flake8)
 
 ### In order to be accepted and merged into youtube-dl each piece of code must be in public domain or released under [Unlicense](http://unlicense.org/). Check one of the following options:

.travis.yml

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

CONTRIBUTING.md

@@ -42,11 +42,11 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're
 
 ###  Is the issue already documented?
 
-Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
+Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/ytdl-org/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
 
 ###  Why are existing options not enough?
 
-Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
+Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/ytdl-org/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
 
 ###  Is there enough context in your bug report?
 
@@ -70,7 +70,7 @@ It may sound strange, but some bug reports we receive are completely unrelated t
 
 # DEVELOPER INSTRUCTIONS
 
-Most users do not need to build youtube-dl and can [download the builds](https://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
+Most users do not need to build youtube-dl and can [download the builds](https://ytdl-org.github.io/youtube-dl/download.html) or get them from their distribution.
 
 To run youtube-dl as a developer, you don't need to build anything either. Simply execute
 
@@ -98,7 +98,7 @@ If you want to add support for a new site, first of all **make sure** this site
 
 After you have ensured this site is distributing its content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 
-1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
+1. [Fork this repository](https://github.com/ytdl-org/youtube-dl/fork)
 2. Check out the source code with:
 
         git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git
@@ -150,9 +150,9 @@ After you have ensured this site is distributing its content legally, you can fo
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
-5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
+5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 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.
+7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
 8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart):
 
         $ flake8 youtube_dl/extractor/yourextractor.py
@@ -177,7 +177,7 @@ Extractors are very fragile by nature since they depend on the layout of the sou
 
 ### Mandatory and optional metafields
 
-For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
+For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
 
  - `id` (media identifier)
  - `title` (media title)
@@ -185,7 +185,7 @@ For extraction to work youtube-dl relies on metadata your extractor extracts and
 
 In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken.
 
-[Any field](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
+[Any field](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
 
 #### Example
 
@@ -341,7 +341,7 @@ Incorrect:
 
 ### 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.
+Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
 
 Use `url_or_none` for safe URL processing.
 
@@ -349,7 +349,7 @@ 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.
+Explore [`youtube_dl/utils.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions.
 
 #### More examples
 

ChangeLog

@@ -1,3 +1,189 @@
+version 2019.04.07
+
+Core
++ [downloader/external] Pass rtmp_conn to ffmpeg
+
+Extractors
++ [ruutu] Add support for audio podcasts (#20473, #20545)
++ [xvideos] Extract all thumbnails (#20432)
++ [platzi] Add support for platzi.com (#20562)
+* [dvtv] Fix extraction (#18514, #19174)
++ [vrv] Add basic support for individual movie links (#19229)
++ [bfi:player] Add support for player.bfi.org.uk (#19235)
+* [hbo] Fix extraction and extract subtitles (#14629, #13709)
+* [youtube] Extract srv[1-3] subtitle formats (#20566)
+* [adultswim] Fix extraction (#18025)
+* [teamcoco] Fix extraction and add suport for subdomains (#17099, #20339)
+* [adn] Fix subtitle compatibility with ffmpeg
+* [adn] Fix extraction and add support for positioning styles (#20549)
+* [vk] Use unique video id (#17848)
+* [newstube] Fix extraction
+* [rtl2] Actualize extraction
++ [adobeconnect] Add support for adobeconnect.com (#20283)
++ [gaia] Add support for authentication (#14605)
++ [mediasite] Add support for dashed ids and named catalogs (#20531)
+
+
+version 2019.04.01
+
+Core
+* [utils] Improve int_or_none and float_or_none (#20403)
+* Check for valid --min-sleep-interval when --max-sleep-interval is specified
+  (#20435)
+
+Extractors
++ [weibo] Extend URL regular expression (#20496)
++ [xhamster] Add support for xhamster.one (#20508)
++ [mediasite] Add support for catalogs (#20507)
++ [teamtreehouse] Add support for teamtreehouse.com (#9836)
++ [ina] Add support for audio URLs
+* [ina] Improve extraction
+* [cwtv] Fix episode number extraction (#20461)
+* [npo] Improve DRM detection
++ [pornhub] Add support for DASH formats (#20403)
+* [svtplay] Update API endpoint (#20430)
+
+
+version 2019.03.18
+
+Core
+* [extractor/common] Improve HTML5 entries extraction
++ [utils] Introduce parse_bitrate
+* [update] Hide update URLs behind redirect
+* [extractor/common] Fix url meta field for unfragmented DASH formats (#20346)
+
+Extractors
++ [yandexvideo] Add extractor
+* [openload] Improve embed detection
++ [corus] Add support for bigbrothercanada.ca (#20357)
++ [orf:radio] Extract series (#20012)
++ [cbc:watch] Add support for gem.cbc.ca (#20251, #20359)
+- [anysex] Remove extractor (#19279)
++ [ciscolive] Add support for new URL schema (#20320, #20351)
++ [youtube] Add support for invidiou.sh (#20309)
+- [anitube] Remove extractor (#20334)
+- [ruleporn] Remove extractor (#15344, #20324)
+* [npr] Fix extraction (#10793, #13440)
+* [biqle] Fix extraction (#11471, #15313)
+* [viddler] Modernize
+* [moevideo] Fix extraction
+* [primesharetv] Remove extractor
+* [hypem] Modernize and extract more metadata (#15320)
+* [veoh] Fix extraction
+* [escapist] Modernize
+- [videomega] Remove extractor (#10108)
++ [beeg] Add support for beeg.porn (#20306)
+* [vimeo:review] Improve config url extraction and extract original format
+  (#20305)
+* [fox] Detect geo restriction and authentication errors (#20208)
+
+
+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

README.md

@@ -1,4 +1,4 @@
-[![Build Status](https://travis-ci.org/rg3/youtube-dl.svg?branch=master)](https://travis-ci.org/rg3/youtube-dl)
+[![Build Status](https://travis-ci.org/ytdl-org/youtube-dl.svg?branch=master)](https://travis-ci.org/ytdl-org/youtube-dl)
 
 youtube-dl - download videos from youtube.com or other video platforms
 
@@ -43,7 +43,7 @@ Or with [MacPorts](https://www.macports.org/):
 
     sudo port install youtube-dl
 
-Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
+Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://ytdl-org.github.io/youtube-dl/download.html).
 
 # DESCRIPTION
 **youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
@@ -642,6 +642,7 @@ The simplest case is requesting a specific format, for example with `-f 22` you
 You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download the best quality format of a particular file extension served as a single file, e.g. `-f webm` will download the best quality format with the `webm` extension served as a single file.
 
 You can also use special names to select particular edge case formats:
+
  - `best`: Select the best quality format represented by a single file with video and audio.
  - `worst`: Select the worst quality format represented by a single file with video and audio.
  - `bestvideo`: Select the best quality video-only format (e.g. DASH video). May not be available.
@@ -658,6 +659,7 @@ If you want to download several formats of the same video use a comma as a separ
 You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).
 
 The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals):
+
  - `filesize`: The number of bytes, if known in advance
  - `width`: Width of the video, if known
  - `height`: Height of the video, if known
@@ -668,6 +670,7 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `
  - `fps`: Frame rate
 
 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
@@ -685,7 +688,7 @@ You can merge the video and audio of two formats into a single file using `-f <v
 
 Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`.
 
-Since the end of April 2015 and version 2015.04.26, youtube-dl uses `-f bestvideo+bestaudio/best` as the default format selection (see [#5447](https://github.com/rg3/youtube-dl/issues/5447), [#5456](https://github.com/rg3/youtube-dl/issues/5456)). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
+Since the end of April 2015 and version 2015.04.26, youtube-dl uses `-f bestvideo+bestaudio/best` as the default format selection (see [#5447](https://github.com/ytdl-org/youtube-dl/issues/5447), [#5456](https://github.com/ytdl-org/youtube-dl/issues/5456)). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
 
 If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download the best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
 
@@ -736,7 +739,7 @@ $ youtube-dl --dateafter 20000101 --datebefore 20091231
 
 ### How do I update youtube-dl?
 
-If you've followed [our manual installation instructions](https://rg3.github.io/youtube-dl/download.html), you can simply run `youtube-dl -U` (or, on Linux, `sudo youtube-dl -U`).
+If you've followed [our manual installation instructions](https://ytdl-org.github.io/youtube-dl/download.html), you can simply run `youtube-dl -U` (or, on Linux, `sudo youtube-dl -U`).
 
 If you have used pip, a simple `sudo pip install -U youtube-dl` is sufficient to update.
 
@@ -746,7 +749,7 @@ As a last resort, you can also uninstall the version installed by your package m
 
     sudo apt-get remove -y youtube-dl
 
-Afterwards, simply follow [our manual installation instructions](https://rg3.github.io/youtube-dl/download.html):
+Afterwards, simply follow [our manual installation instructions](https://ytdl-org.github.io/youtube-dl/download.html):
 
 ```
 sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl
@@ -780,7 +783,7 @@ Most people asking this question are not aware that youtube-dl now defaults to d
 
 ### I get HTTP error 402 when trying to download a video. What's this?
 
-Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a web browser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
+Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/ytdl-org/youtube-dl/issues/154), but at the moment, your best course of action is pointing a web browser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
 
 ### Do I need any other programs?
 
@@ -845,7 +848,7 @@ means you're using an outdated version of Python. Please update to Python 2.6 or
 
 ### What is this binary file? Where has the code gone?
 
-Since June 2012 ([#342](https://github.com/rg3/youtube-dl/issues/342)) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.
+Since June 2012 ([#342](https://github.com/ytdl-org/youtube-dl/issues/342)) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.
 
 ### The exe throws an error due to missing `MSVCR100.dll`
 
@@ -904,7 +907,7 @@ When youtube-dl detects an HLS video, it can download it either with the built-i
 
 When youtube-dl knows that one particular downloader works better for a given website, that downloader will be picked. Otherwise, youtube-dl will pick the best downloader for general compatibility, which at the moment happens to be ffmpeg. This choice may change in future versions of youtube-dl, with improvements of the built-in downloader and/or ffmpeg.
 
-In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](https://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
+In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](https://ytdl-org.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
 
 If you put either `--hls-prefer-native` or `--hls-prefer-ffmpeg` into your configuration, a different subset of videos will fail to download correctly. Instead, it is much better to [file an issue](https://yt-dl.org/bug) or a pull request which details why the native or the ffmpeg HLS downloader is a better choice for your use case.
 
@@ -944,7 +947,7 @@ youtube-dl is an open-source project manned by too few volunteers, so we'd rathe
 
 # DEVELOPER INSTRUCTIONS
 
-Most users do not need to build youtube-dl and can [download the builds](https://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
+Most users do not need to build youtube-dl and can [download the builds](https://ytdl-org.github.io/youtube-dl/download.html) or get them from their distribution.
 
 To run youtube-dl as a developer, you don't need to build anything either. Simply execute
 
@@ -972,7 +975,7 @@ If you want to add support for a new site, first of all **make sure** this site
 
 After you have ensured this site is distributing its content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 
-1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
+1. [Fork this repository](https://github.com/ytdl-org/youtube-dl/fork)
 2. Check out the source code with:
 
         git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git
@@ -1024,9 +1027,9 @@ After you have ensured this site is distributing its content legally, you can fo
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
-5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
+5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 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.
+7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
 8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart):
 
         $ flake8 youtube_dl/extractor/yourextractor.py
@@ -1051,7 +1054,7 @@ Extractors are very fragile by nature since they depend on the layout of the sou
 
 ### Mandatory and optional metafields
 
-For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
+For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
 
  - `id` (media identifier)
  - `title` (media title)
@@ -1059,7 +1062,7 @@ For extraction to work youtube-dl relies on metadata your extractor extracts and
 
 In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken.
 
-[Any field](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
+[Any field](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
 
 #### Example
 
@@ -1215,7 +1218,7 @@ Incorrect:
 
 ### 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.
+Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
 
 Use `url_or_none` for safe URL processing.
 
@@ -1223,7 +1226,7 @@ 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.
+Explore [`youtube_dl/utils.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions.
 
 #### More examples
 
@@ -1242,7 +1245,7 @@ view_count = int_or_none(video.get('views'))
 
 # EMBEDDING YOUTUBE-DL
 
-youtube-dl makes the best effort to be a good command-line program, and thus should be callable from any programming language. If you encounter any problems parsing its output, feel free to [create a report](https://github.com/rg3/youtube-dl/issues/new).
+youtube-dl makes the best effort to be a good command-line program, and thus should be callable from any programming language. If you encounter any problems parsing its output, feel free to [create a report](https://github.com/ytdl-org/youtube-dl/issues/new).
 
 From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
 
@@ -1255,7 +1258,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
     ydl.download(['https://www.youtube.com/watch?v=BaW_jenozKc'])
 ```
 
-Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/3e4cedf9e8cd3157df2457df7274d0c842421945/youtube_dl/YoutubeDL.py#L137-L312). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/ytdl-org/youtube-dl/blob/3e4cedf9e8cd3157df2457df7274d0c842421945/youtube_dl/YoutubeDL.py#L137-L312). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
 
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
@@ -1296,7 +1299,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
 
 # BUGS
 
-Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted to or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](https://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
+Bugs and suggestions should be reported at: <https://github.com/ytdl-org/youtube-dl/issues>. Unless you were prompted to or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](https://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
 
 **Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
 ```
@@ -1342,11 +1345,11 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're
 
 ###  Is the issue already documented?
 
-Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
+Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/ytdl-org/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
 
 ###  Why are existing options not enough?
 
-Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
+Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/ytdl-org/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
 
 ###  Is there enough context in your bug report?
 

devscripts/buildserver.py

@@ -322,7 +322,7 @@ class GITBuilder(GITInfoBuilder):
 
 
 class YoutubeDLBuilder(object):
-    authorizedUsers = ['fraca7', 'phihag', 'rg3', 'FiloSottile']
+    authorizedUsers = ['fraca7', 'phihag', 'rg3', 'FiloSottile', 'ytdl-org']
 
     def __init__(self, **kwargs):
         if self.repoName != 'youtube-dl':

devscripts/create-github-release.py

@@ -27,8 +27,8 @@ from youtube_dl.utils import (
 
 
 class GitHubReleaser(object):
-    _API_URL = 'https://api.github.com/repos/rg3/youtube-dl/releases'
-    _UPLOADS_URL = 'https://uploads.github.com/repos/rg3/youtube-dl/releases/%s/assets?name=%s'
+    _API_URL = 'https://api.github.com/repos/ytdl-org/youtube-dl/releases'
+    _UPLOADS_URL = 'https://uploads.github.com/repos/ytdl-org/youtube-dl/releases/%s/assets?name=%s'
     _NETRC_MACHINE = 'github.com'
 
     def __init__(self, debuglevel=0):

devscripts/gh-pages/update-feed.py

@@ -10,7 +10,7 @@ import textwrap
 atom_template = textwrap.dedent("""\
     <?xml version="1.0" encoding="utf-8"?>
     <feed xmlns="http://www.w3.org/2005/Atom">
-        <link rel="self" href="http://rg3.github.io/youtube-dl/update/releases.atom" />
+        <link rel="self" href="http://ytdl-org.github.io/youtube-dl/update/releases.atom" />
         <title>youtube-dl releases</title>
         <id>https://yt-dl.org/feed/youtube-dl-updates-feed</id>
         <updated>@TIMESTAMP@</updated>
@@ -21,7 +21,7 @@ entry_template = textwrap.dedent("""
     <entry>
         <id>https://yt-dl.org/feed/youtube-dl-updates-feed/youtube-dl-@VERSION@</id>
         <title>New version @VERSION@</title>
-        <link href="http://rg3.github.io/youtube-dl" />
+        <link href="http://ytdl-org.github.io/youtube-dl" />
         <content type="xhtml">
             <div xmlns="http://www.w3.org/1999/xhtml">
                 Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>

devscripts/release.sh

@@ -96,7 +96,7 @@ git push origin "$version"
 REV=$(git rev-parse HEAD)
 make youtube-dl youtube-dl.tar.gz
 read -p "VM running? (y/n) " -n 1
-wget "http://$buildserver/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
+wget "http://$buildserver/build/ytdl-org/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
 mkdir -p "build/$version"
 mv youtube-dl youtube-dl.exe "build/$version"
 mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz"

devscripts/show-downloads-statistics.py

@@ -24,7 +24,7 @@ total_bytes = 0
 
 for page in itertools.count(1):
     releases = json.loads(compat_urllib_request.urlopen(
-        'https://api.github.com/repos/rg3/youtube-dl/releases?page=%s' % page
+        'https://api.github.com/repos/ytdl-org/youtube-dl/releases?page=%s' % page
     ).read().decode('utf-8'))
 
     if not releases:

docs/supportedsites.md

@@ -28,6 +28,7 @@
  - **acast:channel**
  - **AddAnime**
  - **ADN**: Anime Digital Network
+ - **AdobeConnect**
  - **AdobeTV**
  - **AdobeTVChannel**
  - **AdobeTVShow**
@@ -44,9 +45,7 @@
  - **AmericasTestKitchen**
  - **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
  - **AnimeOnDemand**
- - **anitube.se**
  - **Anvato**
- - **AnySex**
  - **APA**
  - **Aparat**
  - **AppleConnect**
@@ -103,6 +102,7 @@
  - **Bellator**
  - **BellMedia**
  - **Bet**
+ - **bfi:player**
  - **Bigflix**
  - **Bild**: Bild.de
  - **BiliBili**
@@ -347,7 +347,6 @@
  - **Groupon**
  - **Hark**
  - **hbo**
- - **hbo:episode**
  - **HearThisAt**
  - **Heise**
  - **HellPorno**
@@ -458,6 +457,7 @@
  - **LineTV**
  - **linkedin:learning**
  - **linkedin:learning:course**
+ - **LinuxAcademy**
  - **LiTV**
  - **LiveLeak**
  - **LiveLeakEmbed**
@@ -476,6 +476,7 @@
  - **mailru:music**: Музыка@Mail.Ru
  - **mailru:music:search**: Музыка@Mail.Ru
  - **MakerTV**
+ - **MallTV**
  - **mangomolo:live**
  - **mangomolo:video**
  - **ManyVids**
@@ -488,6 +489,8 @@
  - **Medialaan**
  - **Mediaset**
  - **Mediasite**
+ - **MediasiteCatalog**
+ - **MediasiteNamedCatalog**
  - **Medici**
  - **megaphone.fm**: megaphone.fm embedded players
  - **Meipai**: 美拍
@@ -670,6 +673,8 @@
  - **Piksel**
  - **Pinkbike**
  - **Pladform**
+ - **Platzi**
+ - **PlatziCourse**
  - **play.fm**
  - **PlayPlusTV**
  - **PlaysTV**
@@ -696,7 +701,6 @@
  - **PornoXO**
  - **PornTube**
  - **PressTV**
- - **PrimeShareTV**
  - **PromptFile**
  - **prosiebensat1**: ProSiebenSat.1 Digital
  - **puhutv**
@@ -716,7 +720,7 @@
  - **radio.de**
  - **radiobremen**
  - **radiocanada**
- - **RadioCanadaAudioVideo**
+ - **radiocanada:audiovideo**
  - **radiofrance**
  - **RadioJavan**
  - **Rai**
@@ -763,7 +767,6 @@
  - **RTVS**
  - **Rudo**
  - **RUHD**
- - **RulePorn**
  - **rutube**: Rutube videos
  - **rutube:channel**: Rutube channels
  - **rutube:embed**: Rutube embedded videos
@@ -827,6 +830,7 @@
  - **southpark.nl**
  - **southparkstudios.dk**
  - **SpankBang**
+ - **SpankBangPlaylist**
  - **Spankwire**
  - **Spiegel**
  - **Spiegel:Article**: Articles on spiegel.de
@@ -870,6 +874,7 @@
  - **teachertube:user:collection**: teachertube.com user and collection videos
  - **TeachingChannel**
  - **Teamcoco**
+ - **TeamTreeHouse**
  - **TechTalks**
  - **techtv.mit.edu**
  - **ted**
@@ -913,6 +918,7 @@
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
+ - **TruNews**
  - **TruTV**
  - **Tube8**
  - **TubiTv**
@@ -1006,7 +1012,6 @@
  - **video.mit.edu**
  - **VideoDetective**
  - **videofy.me**
- - **VideoMega**
  - **videomore**
  - **videomore:season**
  - **videomore:video**
@@ -1057,7 +1062,6 @@
  - **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
@@ -1124,6 +1128,7 @@
  - **yandexmusic:album**: Яндекс.Музыка - Альбом
  - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
  - **yandexmusic:track**: Яндекс.Музыка - Трек
+ - **YandexVideo**
  - **YapFiles**
  - **YesJapan**
  - **yinyuetai:video**: 音悦Tai

setup.py

@@ -104,7 +104,7 @@ setup(
     version=__version__,
     description=DESCRIPTION,
     long_description=LONG_DESCRIPTION,
-    url='https://github.com/rg3/youtube-dl',
+    url='https://github.com/ytdl-org/youtube-dl',
     author='Ricardo Garcia',
     author_email='ytdl@yt-dl.org',
     maintainer='Sergey M.',

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)
@@ -105,6 +107,184 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertRaises(ExtractorError, self.ie._download_json, uri, None)
         self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
 
+    def test_parse_html5_media_entries(self):
+        # from https://www.r18.com/
+        # with kpbs in label
+        expect_dict(
+            self,
+            self.ie._parse_html5_media_entries(
+                'https://www.r18.com/',
+                r'''
+                <video id="samplevideo_amateur" class="js-samplevideo video-js vjs-default-skin vjs-big-play-centered" controls preload="auto" width="400" height="225" poster="//pics.r18.com/digital/amateur/mgmr105/mgmr105jp.jpg">
+                    <source id="video_source" src="https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_sm_w.mp4" type="video/mp4"  res="240" label="300kbps">
+                    <source id="video_source" src="https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_dm_w.mp4" type="video/mp4"  res="480" label="1000kbps">
+                    <source id="video_source" src="https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_dmb_w.mp4" type="video/mp4"  res="740" label="1500kbps">
+                    <p>Your browser does not support the video tag.</p>
+                </video>
+                ''', None)[0],
+            {
+                'formats': [{
+                    'url': 'https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_sm_w.mp4',
+                    'ext': 'mp4',
+                    'format_id': '300kbps',
+                    'height': 240,
+                    'tbr': 300,
+                }, {
+                    'url': 'https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_dm_w.mp4',
+                    'ext': 'mp4',
+                    'format_id': '1000kbps',
+                    'height': 480,
+                    'tbr': 1000,
+                }, {
+                    'url': 'https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_dmb_w.mp4',
+                    'ext': 'mp4',
+                    'format_id': '1500kbps',
+                    'height': 740,
+                    'tbr': 1500,
+                }],
+                'thumbnail': '//pics.r18.com/digital/amateur/mgmr105/mgmr105jp.jpg'
+            })
+
+        # from https://www.csfd.cz/
+        # with width and height
+        expect_dict(
+            self,
+            self.ie._parse_html5_media_entries(
+                'https://www.csfd.cz/',
+                r'''
+                <video width="770" height="328" preload="none" controls  poster="https://img.csfd.cz/files/images/film/video/preview/163/344/163344118_748d20.png?h360" >
+                    <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327358_eac647.mp4" type="video/mp4" width="640" height="360">
+                    <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327360_3d2646.mp4" type="video/mp4" width="1280" height="720">
+                    <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327356_91f258.mp4" type="video/mp4" width="1920" height="1080">
+                    <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327359_962b4a.webm" type="video/webm" width="640" height="360">
+                    <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327361_6feee0.webm" type="video/webm" width="1280" height="720">
+                    <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327357_8ab472.webm" type="video/webm" width="1920" height="1080">
+                    <track src="https://video.csfd.cz/files/subtitles/163/344/163344115_4c388b.srt" type="text/x-srt" kind="subtitles" srclang="cs" label="cs">
+                </video>
+                ''', None)[0],
+            {
+                'formats': [{
+                    'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327358_eac647.mp4',
+                    'ext': 'mp4',
+                    'width': 640,
+                    'height': 360,
+                }, {
+                    'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327360_3d2646.mp4',
+                    'ext': 'mp4',
+                    'width': 1280,
+                    'height': 720,
+                }, {
+                    'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327356_91f258.mp4',
+                    'ext': 'mp4',
+                    'width': 1920,
+                    'height': 1080,
+                }, {
+                    'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327359_962b4a.webm',
+                    'ext': 'webm',
+                    'width': 640,
+                    'height': 360,
+                }, {
+                    'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327361_6feee0.webm',
+                    'ext': 'webm',
+                    'width': 1280,
+                    'height': 720,
+                }, {
+                    'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327357_8ab472.webm',
+                    'ext': 'webm',
+                    'width': 1920,
+                    'height': 1080,
+                }],
+                'subtitles': {
+                    'cs': [{'url': 'https://video.csfd.cz/files/subtitles/163/344/163344115_4c388b.srt'}]
+                },
+                'thumbnail': 'https://img.csfd.cz/files/images/film/video/preview/163/344/163344118_748d20.png?h360'
+            })
+
+        # from https://tamasha.com/v/Kkdjw
+        # with height in label
+        expect_dict(
+            self,
+            self.ie._parse_html5_media_entries(
+                'https://tamasha.com/v/Kkdjw',
+                r'''
+                <video crossorigin="anonymous">
+                        <source src="https://s-v2.tamasha.com/statics/videos_file/19/8f/Kkdjw_198feff8577d0057536e905cce1fb61438dd64e0_n_240.mp4" type="video/mp4" label="AUTO" res="0"/>
+                                <source src="https://s-v2.tamasha.com/statics/videos_file/19/8f/Kkdjw_198feff8577d0057536e905cce1fb61438dd64e0_n_240.mp4" type="video/mp4"
+                                        label="240p" res="240"/>
+                                <source src="https://s-v2.tamasha.com/statics/videos_file/20/00/Kkdjw_200041c66f657fc967db464d156eafbc1ed9fe6f_n_144.mp4" type="video/mp4"
+                                        label="144p" res="144"/>
+                </video>
+                ''', None)[0],
+            {
+                'formats': [{
+                    'url': 'https://s-v2.tamasha.com/statics/videos_file/19/8f/Kkdjw_198feff8577d0057536e905cce1fb61438dd64e0_n_240.mp4',
+                }, {
+                    'url': 'https://s-v2.tamasha.com/statics/videos_file/19/8f/Kkdjw_198feff8577d0057536e905cce1fb61438dd64e0_n_240.mp4',
+                    'ext': 'mp4',
+                    'format_id': '240p',
+                    'height': 240,
+                }, {
+                    'url': 'https://s-v2.tamasha.com/statics/videos_file/20/00/Kkdjw_200041c66f657fc967db464d156eafbc1ed9fe6f_n_144.mp4',
+                    'ext': 'mp4',
+                    'format_id': '144p',
+                    'height': 144,
+                }]
+            })
+
+        # from https://www.directvnow.com
+        # with data-src
+        expect_dict(
+            self,
+            self.ie._parse_html5_media_entries(
+                'https://www.directvnow.com',
+                r'''
+                <video id="vid1" class="header--video-masked active" muted playsinline>
+                    <source data-src="https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4" type="video/mp4" />
+                </video>
+                ''', None)[0],
+            {
+                'formats': [{
+                    'ext': 'mp4',
+                    'url': 'https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4',
+                }]
+            })
+
+        # from https://www.directvnow.com
+        # with data-src
+        expect_dict(
+            self,
+            self.ie._parse_html5_media_entries(
+                'https://www.directvnow.com',
+                r'''
+                <video id="vid1" class="header--video-masked active" muted playsinline>
+                    <source data-src="https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4" type="video/mp4" />
+                </video>
+                ''', None)[0],
+            {
+                'formats': [{
+                    'url': 'https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4',
+                    'ext': 'mp4',
+                }]
+            })
+
+        # from https://www.klarna.com/uk/
+        # with data-video-src
+        expect_dict(
+            self,
+            self.ie._parse_html5_media_entries(
+                'https://www.directvnow.com',
+                r'''
+                <video loop autoplay muted class="responsive-video block-kl__video video-on-medium">
+                    <source src="" data-video-desktop data-video-src="https://www.klarna.com/uk/wp-content/uploads/sites/11/2019/01/KL062_Smooth3_0_DogWalking_5s_920x080_.mp4" type="video/mp4" />
+                </video>
+                ''', None)[0],
+            {
+                'formats': [{
+                    'url': 'https://www.klarna.com/uk/wp-content/uploads/sites/11/2019/01/KL062_Smooth3_0_DogWalking_5s_920x080_.mp4',
+                    'ext': 'mp4',
+                }],
+            })
+
     def test_extract_jwplayer_data_realworld(self):
         # from http://www.suffolk.edu/sjc/
         expect_dict(
@@ -199,7 +379,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
     def test_parse_m3u8_formats(self):
         _TEST_CASES = [
             (
-                # https://github.com/rg3/youtube-dl/issues/11507
+                # https://github.com/ytdl-org/youtube-dl/issues/11507
                 # http://pluzz.francetv.fr/videos/le_ministere.html
                 'pluzz_francetv_11507',
                 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
@@ -261,7 +441,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 }]
             ),
             (
-                # https://github.com/rg3/youtube-dl/issues/11995
+                # https://github.com/ytdl-org/youtube-dl/issues/11995
                 # http://teamcoco.com/video/clueless-gamer-super-bowl-for-honor
                 'teamcoco_11995',
                 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
@@ -335,7 +515,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 }]
             ),
             (
-                # https://github.com/rg3/youtube-dl/issues/12211
+                # https://github.com/ytdl-org/youtube-dl/issues/12211
                 # http://video.toggle.sg/en/series/whoopie-s-world/ep3/478601
                 'toggle_mobile_12211',
                 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
@@ -499,7 +679,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 }]
             ),
             (
-                # https://github.com/rg3/youtube-dl/issues/18923
+                # https://github.com/ytdl-org/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',
@@ -568,11 +748,12 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
     def test_parse_mpd_formats(self):
         _TEST_CASES = [
             (
-                # https://github.com/rg3/youtube-dl/issues/13919
+                # https://github.com/ytdl-org/youtube-dl/issues/13919
                 # Also tests duplicate representation ids, see
-                # https://github.com/rg3/youtube-dl/issues/15111
+                # https://github.com/ytdl-org/youtube-dl/issues/15111
                 'float_duration',
-                'http://unknown/manifest.mpd',
+                'http://unknown/manifest.mpd',  # mpd_url
+                None,  # mpd_base_url
                 [{
                     'manifest_url': 'http://unknown/manifest.mpd',
                     'ext': 'm4a',
@@ -650,9 +831,10 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 1080,
                 }]
             ), (
-                # https://github.com/rg3/youtube-dl/pull/14844
+                # https://github.com/ytdl-org/youtube-dl/pull/14844
                 'urls_only',
-                'http://unknown/manifest.mpd',
+                'http://unknown/manifest.mpd',  # mpd_url
+                None,  # mpd_base_url
                 [{
                     'manifest_url': 'http://unknown/manifest.mpd',
                     'ext': 'mp4',
@@ -731,22 +913,68 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'width': 1920,
                     'height': 1080,
                 }]
+            ), (
+                # https://github.com/ytdl-org/youtube-dl/issues/20346
+                # Media considered unfragmented even though it contains
+                # Initialization tag
+                'unfragmented',
+                'https://v.redd.it/hw1x7rcg7zl21/DASHPlaylist.mpd',  # mpd_url
+                'https://v.redd.it/hw1x7rcg7zl21',  # mpd_base_url
+                [{
+                    'url': 'https://v.redd.it/hw1x7rcg7zl21/audio',
+                    'manifest_url': 'https://v.redd.it/hw1x7rcg7zl21/DASHPlaylist.mpd',
+                    'ext': 'm4a',
+                    'format_id': 'AUDIO-1',
+                    'format_note': 'DASH audio',
+                    'container': 'm4a_dash',
+                    'acodec': 'mp4a.40.2',
+                    'vcodec': 'none',
+                    'tbr': 129.87,
+                    'asr': 48000,
+
+                }, {
+                    'url': 'https://v.redd.it/hw1x7rcg7zl21/DASH_240',
+                    'manifest_url': 'https://v.redd.it/hw1x7rcg7zl21/DASHPlaylist.mpd',
+                    'ext': 'mp4',
+                    'format_id': 'VIDEO-2',
+                    'format_note': 'DASH video',
+                    'container': 'mp4_dash',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.4d401e',
+                    'tbr': 608.0,
+                    'width': 240,
+                    'height': 240,
+                    'fps': 30,
+                }, {
+                    'url': 'https://v.redd.it/hw1x7rcg7zl21/DASH_360',
+                    'manifest_url': 'https://v.redd.it/hw1x7rcg7zl21/DASHPlaylist.mpd',
+                    'ext': 'mp4',
+                    'format_id': 'VIDEO-1',
+                    'format_note': 'DASH video',
+                    'container': 'mp4_dash',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.4d401e',
+                    'tbr': 804.261,
+                    'width': 360,
+                    'height': 360,
+                    'fps': 30,
+                }]
             )
         ]
 
-        for mpd_file, mpd_url, expected_formats in _TEST_CASES:
+        for mpd_file, mpd_url, mpd_base_url, expected_formats in _TEST_CASES:
             with io.open('./test/testdata/mpd/%s.mpd' % mpd_file,
                          mode='r', encoding='utf-8') as f:
                 formats = self.ie._parse_mpd_formats(
                     compat_etree_fromstring(f.read().encode('utf-8')),
-                    mpd_url=mpd_url)
+                    mpd_base_url=mpd_base_url, mpd_url=mpd_url)
                 self.ie._sort_formats(formats)
                 expect_value(self, formats, expected_formats, None)
 
     def test_parse_f4m_formats(self):
         _TEST_CASES = [
             (
-                # https://github.com/rg3/youtube-dl/issues/14660
+                # https://github.com/ytdl-org/youtube-dl/issues/14660
                 'custom_base_url',
                 'http://api.new.livestream.com/accounts/6115179/events/6764928/videos/144884262.f4m',
                 [{

test/test_YoutubeDL.py

@@ -411,7 +411,7 @@ class TestFormatSelection(unittest.TestCase):
         # For extractors with incomplete formats (all formats are audio-only or
         # video-only) best and worst should fallback to corresponding best/worst
         # video-only or audio-only formats (as per
-        # https://github.com/rg3/youtube-dl/pull/5556)
+        # https://github.com/ytdl-org/youtube-dl/pull/5556)
         formats = [
             {'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
             {'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
@@ -442,7 +442,7 @@ class TestFormatSelection(unittest.TestCase):
         self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
 
     def test_format_selection_issue_10083(self):
-        # See https://github.com/rg3/youtube-dl/issues/10083
+        # See https://github.com/ytdl-org/youtube-dl/issues/10083
         formats = [
             {'format_id': 'regular', 'height': 360, 'url': TEST_URL},
             {'format_id': 'video', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
@@ -853,7 +853,7 @@ class TestYoutubeDL(unittest.TestCase):
         self.assertEqual(result, [2, 3, 4])
 
     def test_urlopen_no_file_protocol(self):
-        # see https://github.com/rg3/youtube-dl/issues/8227
+        # see https://github.com/ytdl-org/youtube-dl/issues/8227
         ydl = YDL()
         self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd')
 

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_all_urls.py

@@ -110,7 +110,7 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
         self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
 
-    # https://github.com/rg3/youtube-dl/issues/1930
+    # https://github.com/ytdl-org/youtube-dl/issues/1930
     def test_soundcloud_not_matching_sets(self):
         self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
 
@@ -119,12 +119,12 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
 
     def test_pbs(self):
-        # https://github.com/rg3/youtube-dl/issues/2350
+        # https://github.com/ytdl-org/youtube-dl/issues/2350
         self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
         self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
 
     def test_yahoo_https(self):
-        # https://github.com/rg3/youtube-dl/issues/2701
+        # https://github.com/ytdl-org/youtube-dl/issues/2701
         self.assertMatch(
             'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
             ['Yahoo'])

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

@@ -33,11 +33,13 @@ from youtube_dl.utils import (
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
+    float_or_none,
     get_element_by_class,
     get_element_by_attribute,
     get_elements_by_class,
     get_elements_by_attribute,
     InAdvancePagedList,
+    int_or_none,
     intlist_to_bytes,
     is_html,
     js_to_json,
@@ -55,6 +57,7 @@ from youtube_dl.utils import (
     parse_count,
     parse_iso8601,
     parse_resolution,
+    parse_bitrate,
     pkcs1pad,
     read_batch_urls,
     sanitize_filename,
@@ -467,6 +470,21 @@ class TestUtil(unittest.TestCase):
             shell_quote(args),
             """ffmpeg -i 'ñ€ß'"'"'.mp4'""" if compat_os_name != 'nt' else '''ffmpeg -i "ñ€ß'.mp4"''')
 
+    def test_float_or_none(self):
+        self.assertEqual(float_or_none('42.42'), 42.42)
+        self.assertEqual(float_or_none('42'), 42.0)
+        self.assertEqual(float_or_none(''), None)
+        self.assertEqual(float_or_none(None), None)
+        self.assertEqual(float_or_none([]), None)
+        self.assertEqual(float_or_none(set()), None)
+
+    def test_int_or_none(self):
+        self.assertEqual(int_or_none('42'), 42)
+        self.assertEqual(int_or_none(''), None)
+        self.assertEqual(int_or_none(None), None)
+        self.assertEqual(int_or_none([]), None)
+        self.assertEqual(int_or_none(set()), None)
+
     def test_str_to_int(self):
         self.assertEqual(str_to_int('123,456'), 123456)
         self.assertEqual(str_to_int('123.456'), 123456)
@@ -1030,6 +1048,13 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_resolution('4k'), {'height': 2160})
         self.assertEqual(parse_resolution('8K'), {'height': 4320})
 
+    def test_parse_bitrate(self):
+        self.assertEqual(parse_bitrate(None), None)
+        self.assertEqual(parse_bitrate(''), None)
+        self.assertEqual(parse_bitrate('300kbps'), 300)
+        self.assertEqual(parse_bitrate('1500kbps'), 1500)
+        self.assertEqual(parse_bitrate('300 kbps'), 300)
+
     def test_version_tuple(self):
         self.assertEqual(version_tuple('1'), (1,))
         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))

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/mpd/unfragmented.mpd

@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<MPD mediaPresentationDuration="PT54.915S" minBufferTime="PT1.500S" profiles="urn:mpeg:dash:profile:isoff-on-demand:2011" type="static" xmlns="urn:mpeg:dash:schema:mpd:2011">
+    <Period duration="PT54.915S">
+        <AdaptationSet segmentAlignment="true" subsegmentAlignment="true" subsegmentStartsWithSAP="1">
+            <Representation bandwidth="804261" codecs="avc1.4d401e" frameRate="30" height="360" id="VIDEO-1" mimeType="video/mp4" startWithSAP="1" width="360">
+                <BaseURL>DASH_360</BaseURL>
+                <SegmentBase indexRange="915-1114" indexRangeExact="true">
+                    <Initialization range="0-914"/>
+                </SegmentBase>
+            </Representation>
+            <Representation bandwidth="608000" codecs="avc1.4d401e" frameRate="30" height="240" id="VIDEO-2" mimeType="video/mp4" startWithSAP="1" width="240">
+                <BaseURL>DASH_240</BaseURL>
+                <SegmentBase indexRange="913-1112" indexRangeExact="true">
+                    <Initialization range="0-912"/>
+                </SegmentBase>
+            </Representation>
+        </AdaptationSet>
+        <AdaptationSet>
+            <Representation audioSamplingRate="48000" bandwidth="129870" codecs="mp4a.40.2" id="AUDIO-1" mimeType="audio/mp4" startWithSAP="1">
+                <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
+                <BaseURL>audio</BaseURL>
+                <SegmentBase indexRange="832-1007" indexRangeExact="true">
+                    <Initialization range="0-831"/>
+                </SegmentBase>
+            </Representation>
+        </AdaptationSet>
+    </Period>
+</MPD>

youtube-dl.plugin.zsh

@@ -7,7 +7,7 @@
 # https://github.com/zsh-users/antigen
 
 # Install youtube-dl:
-# antigen bundle rg3/youtube-dl
+# antigen bundle ytdl-org/youtube-dl
 # Bundles installed by antigen are available for use immediately.
 
 # Update youtube-dl (and all other antigen bundles):

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,
@@ -308,6 +309,8 @@ class YoutubeDL(object):
     The following options are used by the post processors:
     prefer_ffmpeg:     If False, use avconv instead of ffmpeg if both are available,
                        otherwise prefer ffmpeg.
+    ffmpeg_location:   Location of the ffmpeg/avconv binary; either the path
+                       to the binary or its containing directory.
     postprocessor_args: A list of additional command-line arguments for the
                         postprocessor.
 
@@ -888,7 +891,7 @@ class YoutubeDL(object):
             # url_transparent. In such cases outer metadata (from ie_result)
             # should be propagated to inner one (info). For this to happen
             # _type of info should be overridden with url_transparent. This
-            # fixes issue from https://github.com/rg3/youtube-dl/pull/11163.
+            # fixes issue from https://github.com/ytdl-org/youtube-dl/pull/11163.
             if new_result.get('_type') == 'url':
                 new_result['_type'] = 'url_transparent'
 
@@ -1605,7 +1608,7 @@ class YoutubeDL(object):
         # by extractor are incomplete or not (i.e. whether extractor provides only
         # video-only or audio-only formats) for proper formats selection for
         # extractors with such incomplete formats (see
-        # https://github.com/rg3/youtube-dl/pull/5556).
+        # https://github.com/ytdl-org/youtube-dl/pull/5556).
         # Since formats may be filtered during format selection and may not match
         # the original formats the results may be incorrect. Thus original formats
         # or pre-calculated metrics should be passed to format selection routines
@@ -1613,7 +1616,7 @@ class YoutubeDL(object):
         # We will pass a context object containing all necessary additional data
         # instead of just formats.
         # This fixes incorrect format selection issue (see
-        # https://github.com/rg3/youtube-dl/issues/10083).
+        # https://github.com/ytdl-org/youtube-dl/issues/10083).
         incomplete_formats = (
             # All formats are video-only or
             all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats) or
@@ -1809,7 +1812,7 @@ class YoutubeDL(object):
                     if sub_info.get('data') is not None:
                         try:
                             # Use newline='' to prevent conversion of newline characters
-                            # See https://github.com/rg3/youtube-dl/issues/10268
+                            # See https://github.com/ytdl-org/youtube-dl/issues/10268
                             with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
                                 subfile.write(sub_info['data'])
                         except (OSError, IOError):
@@ -2060,15 +2063,24 @@ 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')
@@ -2076,7 +2088,7 @@ 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:
@@ -2219,7 +2231,7 @@ class YoutubeDL(object):
             return
 
         if type('') is not compat_str:
-            # Python 2.6 on SLES11 SP1 (https://github.com/rg3/youtube-dl/issues/3326)
+            # Python 2.6 on SLES11 SP1 (https://github.com/ytdl-org/youtube-dl/issues/3326)
             self.report_warning(
                 'Your Python is broken! Update to a newer and supported version')
 
@@ -2313,7 +2325,7 @@ class YoutubeDL(object):
                 proxies = {'http': opts_proxy, 'https': opts_proxy}
         else:
             proxies = compat_urllib_request.getproxies()
-            # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805)
+            # Set HTTPS proxy to HTTP one if given (https://github.com/ytdl-org/youtube-dl/issues/805)
             if 'http' in proxies and 'https' not in proxies:
                 proxies['https'] = proxies['http']
         proxy_handler = PerRequestProxyHandler(proxies)
@@ -2326,7 +2338,7 @@ class YoutubeDL(object):
         # When passing our own FileHandler instance, build_opener won't add the
         # default FileHandler and allows us to disable the file protocol, which
         # can be used for malicious purposes (see
-        # https://github.com/rg3/youtube-dl/issues/8227)
+        # https://github.com/ytdl-org/youtube-dl/issues/8227)
         file_handler = compat_urllib_request.FileHandler()
 
         def file_open(*args, **kwargs):
@@ -2338,7 +2350,7 @@ class YoutubeDL(object):
 
         # Delete the default user-agent header, which would otherwise apply in
         # cases where our custom HTTP handler doesn't come into play
-        # (See https://github.com/rg3/youtube-dl/issues/1309 for details)
+        # (See https://github.com/ytdl-org/youtube-dl/issues/1309 for details)
         opener.addheaders = []
         self._opener = opener
 

youtube_dl/__init__.py

@@ -48,7 +48,7 @@ from .YoutubeDL import YoutubeDL
 def _real_main(argv=None):
     # Compatibility fixes for Windows
     if sys.platform == 'win32':
-        # https://github.com/rg3/youtube-dl/issues/820
+        # https://github.com/ytdl-org/youtube-dl/issues/820
         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
 
     workaround_optparse_bug9161()
@@ -166,6 +166,8 @@ def _real_main(argv=None):
     if opts.max_sleep_interval is not None:
         if opts.max_sleep_interval < 0:
             parser.error('max sleep interval must be positive or 0')
+        if opts.sleep_interval is None:
+            parser.error('min sleep interval must be specified, use --min-sleep-interval')
         if opts.max_sleep_interval < opts.sleep_interval:
             parser.error('max sleep interval must be greater than or equal to min sleep interval')
     else:

youtube_dl/compat.py

@@ -2364,7 +2364,7 @@ except ImportError:  # Python 2
 
     # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
     # implementations from cpython 3.4.3's stdlib. Python 2's version
-    # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244)
+    # is apparently broken (see https://github.com/ytdl-org/youtube-dl/pull/6244)
 
     def compat_urllib_parse_unquote_to_bytes(string):
         """unquote_to_bytes('abc%20def') -> b'abc def'."""
@@ -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()))
@@ -2819,7 +2828,7 @@ else:
     compat_socket_create_connection = socket.create_connection
 
 
-# Fix https://github.com/rg3/youtube-dl/issues/4223
+# Fix https://github.com/ytdl-org/youtube-dl/issues/4223
 # See http://bugs.python.org/issue9161 for what is broken
 def workaround_optparse_bug9161():
     op = optparse.OptionParser()
@@ -2944,7 +2953,7 @@ if platform.python_implementation() == 'PyPy' and sys.pypy_version_info < (5, 4,
     # PyPy2 prior to version 5.4.0 expects byte strings as Windows function
     # names, see the original PyPy issue [1] and the youtube-dl one [2].
     # 1. https://bitbucket.org/pypy/pypy/issues/2360/windows-ctypescdll-typeerror-function-name
-    # 2. https://github.com/rg3/youtube-dl/pull/4392
+    # 2. https://github.com/ytdl-org/youtube-dl/pull/4392
     def compat_ctypes_WINFUNCTYPE(*args, **kwargs):
         real = ctypes.WINFUNCTYPE(*args, **kwargs)
 
@@ -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')
@@ -229,7 +239,7 @@ class FFmpegFD(ExternalFD):
             # setting -seekable prevents ffmpeg from guessing if the server
             # supports seeking(by adding the header `Range: bytes=0-`), which
             # can cause problems in some cases
-            # https://github.com/rg3/youtube-dl/issues/11800#issuecomment-275037127
+            # https://github.com/ytdl-org/youtube-dl/issues/11800#issuecomment-275037127
             # http://trac.ffmpeg.org/ticket/6125#comment:10
             args += ['-seekable', '1' if seekable else '0']
 
@@ -279,6 +289,7 @@ class FFmpegFD(ExternalFD):
             tc_url = info_dict.get('tc_url')
             flash_version = info_dict.get('flash_version')
             live = info_dict.get('rtmp_live', False)
+            conn = info_dict.get('rtmp_conn')
             if player_url is not None:
                 args += ['-rtmp_swfverify', player_url]
             if page_url is not None:
@@ -293,6 +304,11 @@ class FFmpegFD(ExternalFD):
                 args += ['-rtmp_flashver', flash_version]
             if live:
                 args += ['-rtmp_live', 'live']
+            if isinstance(conn, list):
+                for entry in conn:
+                    args += ['-rtmp_conn', entry]
+            elif isinstance(conn, compat_str):
+                args += ['-rtmp_conn', conn]
 
         args += ['-i', url, '-c', 'copy']
 
@@ -324,7 +340,7 @@ class FFmpegFD(ExternalFD):
             # mp4 file couldn't be played, but if we ask ffmpeg to quit it
             # produces a file that is playable (this is mostly useful for live
             # streams). Note that Windows is not affected and produces playable
-            # files (see https://github.com/rg3/youtube-dl/issues/8300).
+            # files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
             if sys.platform != 'win32':
                 proc.communicate(b'q')
             raise

youtube_dl/downloader/f4m.py

@@ -324,8 +324,8 @@ class F4mFD(FragmentFD):
         urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
         man_url = urlh.geturl()
         # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
-        # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244
-        # and https://github.com/rg3/youtube-dl/issues/7823)
+        # (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244
+        # and https://github.com/ytdl-org/youtube-dl/issues/7823)
         manifest = fix_xml_ampersands(urlh.read().decode('utf-8', 'ignore')).strip()
 
         doc = compat_etree_fromstring(manifest)
@@ -409,7 +409,7 @@ class F4mFD(FragmentFD):
                             # In tests, segments may be truncated, and thus
                             # FlvReader may not be able to parse the whole
                             # chunk. If so, write the segment as is
-                            # See https://github.com/rg3/youtube-dl/issues/9214
+                            # See https://github.com/ytdl-org/youtube-dl/issues/9214
                             dest_stream.write(down_data)
                             break
                         raise

youtube_dl/downloader/hls.py

@@ -152,8 +152,8 @@ class HlsFD(FragmentFD):
                         except compat_urllib_error.HTTPError as err:
                             # Unavailable (possibly temporary) fragments may be served.
                             # First we try to retry then either skip or abort.
-                            # See https://github.com/rg3/youtube-dl/issues/10165,
-                            # https://github.com/rg3/youtube-dl/issues/10448).
+                            # See https://github.com/ytdl-org/youtube-dl/issues/10165,
+                            # https://github.com/ytdl-org/youtube-dl/issues/10448).
                             count += 1
                             if count <= fragment_retries:
                                 self.report_retry_fragment(err, frag_index, count, fragment_retries)

youtube_dl/downloader/http.py

@@ -111,7 +111,7 @@ class HttpFD(FileDownloader):
                 # to match the value of requested Range HTTP header. This is due to a webservers
                 # that don't support resuming and serve a whole file with no Content-Range
                 # set in response despite of requested Range (see
-                # https://github.com/rg3/youtube-dl/issues/6057#issuecomment-126129799)
+                # https://github.com/ytdl-org/youtube-dl/issues/6057#issuecomment-126129799)
                 if has_range:
                     content_range = ctx.data.headers.get('Content-Range')
                     if content_range:

youtube_dl/extractor/adn.py

@@ -21,7 +21,6 @@ from ..utils import (
     intlist_to_bytes,
     long_to_bytes,
     pkcs1pad,
-    srt_subtitles_timecode,
     strip_or_none,
     urljoin,
 )
@@ -42,6 +41,18 @@ class ADNIE(InfoExtractor):
     }
     _BASE_URL = 'http://animedigitalnetwork.fr'
     _RSA_KEY = (0xc35ae1e4356b65a73b551493da94b8cb443491c0aa092a357a5aee57ffc14dda85326f42d716e539a34542a0d3f363adf16c5ec222d713d5997194030ee2e4f0d1fb328c01a81cf6868c090d50de8e169c6b13d1675b9eeed1cbc51e1fffca9b38af07f37abd790924cd3bee59d0257cfda4fe5f3f0534877e21ce5821447d1b, 65537)
+    _POS_ALIGN_MAP = {
+        'start': 1,
+        'end': 3,
+    }
+    _LINE_ALIGN_MAP = {
+        'middle': 8,
+        'end': 4,
+    }
+
+    @staticmethod
+    def _ass_subtitles_timecode(seconds):
+        return '%01d:%02d:%02d.%02d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 100)
 
     def _get_subtitles(self, sub_path, video_id):
         if not sub_path:
@@ -49,14 +60,14 @@ class ADNIE(InfoExtractor):
 
         enc_subtitles = self._download_webpage(
             urljoin(self._BASE_URL, sub_path),
-            video_id, fatal=False)
+            video_id, 'Downloading subtitles data', fatal=False)
         if not enc_subtitles:
             return None
 
         # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
         dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
             bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
-            bytes_to_intlist(binascii.unhexlify(self._K + '9032ad7083106400')),
+            bytes_to_intlist(binascii.unhexlify(self._K + '083db5aebd9353b4')),
             bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
         ))
         subtitles_json = self._parse_json(
@@ -67,23 +78,27 @@ class ADNIE(InfoExtractor):
 
         subtitles = {}
         for sub_lang, sub in subtitles_json.items():
-            srt = ''
-            for num, current in enumerate(sub):
-                start, end, text = (
+            ssa = '''[Script Info]
+ScriptType:V4.00
+[V4 Styles]
+Format: Name,Fontname,Fontsize,PrimaryColour,SecondaryColour,TertiaryColour,BackColour,Bold,Italic,BorderStyle,Outline,Shadow,Alignment,MarginL,MarginR,MarginV,AlphaLevel,Encoding
+Style: Default,Arial,18,16777215,16777215,16777215,0,-1,0,1,1,0,2,20,20,20,0,0
+[Events]
+Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
+            for current in sub:
+                start, end, text, line_align, position_align = (
                     float_or_none(current.get('startTime')),
                     float_or_none(current.get('endTime')),
-                    current.get('text'))
+                    current.get('text'), current.get('lineAlign'),
+                    current.get('positionAlign'))
                 if start is None or end is None or text is None:
                     continue
-                srt += os.linesep.join(
-                    (
-                        '%d' % num,
-                        '%s --> %s' % (
-                            srt_subtitles_timecode(start),
-                            srt_subtitles_timecode(end)),
-                        text,
-                        os.linesep,
-                    ))
+                alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0)
+                ssa += os.linesep + 'Dialogue: Marked=0,%s,%s,Default,,0,0,0,,%s%s' % (
+                    self._ass_subtitles_timecode(start),
+                    self._ass_subtitles_timecode(end),
+                    '{\\a%d}' % alignment if alignment != 2 else '',
+                    text.replace('\n', '\\N').replace('<i>', '{\\i1}').replace('</i>', '{\\i0}'))
 
             if sub_lang == 'vostf':
                 sub_lang = 'fr'
@@ -91,8 +106,8 @@ class ADNIE(InfoExtractor):
                 'ext': 'json',
                 'data': json.dumps(sub),
             }, {
-                'ext': 'srt',
-                'data': srt,
+                'ext': 'ssa',
+                'data': ssa,
             }])
         return subtitles
 
@@ -100,7 +115,15 @@ class ADNIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         player_config = self._parse_json(self._search_regex(
-            r'playerConfig\s*=\s*({.+});', webpage, 'player config'), video_id)
+            r'playerConfig\s*=\s*({.+});', webpage,
+            'player config', default='{}'), video_id, fatal=False)
+        if not player_config:
+            config_url = urljoin(self._BASE_URL, self._search_regex(
+                r'(?:id="player"|class="[^"]*adn-player-container[^"]*")[^>]+data-url="([^"]+)"',
+                webpage, 'config url'))
+            player_config = self._download_json(
+                config_url, video_id,
+                'Downloading player config JSON metadata')['player']
 
         video_info = {}
         video_info_str = self._search_regex(
@@ -129,12 +152,15 @@ class ADNIE(InfoExtractor):
             encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
             authorization = base64.b64encode(encrypted_message).decode()
             links_data = self._download_json(
-                urljoin(self._BASE_URL, links_url), video_id, headers={
+                urljoin(self._BASE_URL, links_url), video_id,
+                'Downloading links JSON metadata', headers={
                     'Authorization': 'Bearer ' + authorization,
                 })
             links = links_data.get('links') or {}
             metas = metas or links_data.get('meta') or {}
-            sub_path = (sub_path or links_data.get('subtitles')) + '&token=' + token
+            sub_path = sub_path or links_data.get('subtitles') or \
+                'index.php?option=com_vodapi&task=subtitles.getJSON&format=json&id=' + video_id
+            sub_path += '&token=' + token
             error = links_data.get('error')
         title = metas.get('title') or video_info['title']
 
@@ -142,9 +168,11 @@ class ADNIE(InfoExtractor):
         for format_id, qualities in links.items():
             if not isinstance(qualities, dict):
                 continue
-            for load_balancer_url in qualities.values():
+            for quality, load_balancer_url in qualities.items():
                 load_balancer_data = self._download_json(
-                    load_balancer_url, video_id, fatal=False) or {}
+                    load_balancer_url, video_id,
+                    'Downloading %s %s JSON metadata' % (format_id, quality),
+                    fatal=False) or {}
                 m3u8_url = load_balancer_data.get('location')
                 if not m3u8_url:
                     continue

youtube_dl/extractor/adobeconnect.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urlparse,
+)
+
+
+class AdobeConnectIE(InfoExtractor):
+    _VALID_URL = r'https?://\w+\.adobeconnect\.com/(?P<id>[\w-]+)'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
+        qs = compat_parse_qs(self._search_regex(r"swfUrl\s*=\s*'([^']+)'", webpage, 'swf url').split('?')[1])
+        is_live = qs.get('isLive', ['false'])[0] == 'true'
+        formats = []
+        for con_string in qs['conStrings'][0].split(','):
+            formats.append({
+                'format_id': con_string.split('://')[0],
+                'app': compat_urlparse.quote('?' + con_string.split('?')[1] + 'flvplayerapp/' + qs['appInstance'][0]),
+                'ext': 'flv',
+                'play_path': 'mp4:' + qs['streamName'][0],
+                'rtmp_conn': 'S:' + qs['ticket'][0],
+                'rtmp_live': is_live,
+                'url': con_string,
+            })
+
+        return {
+            'id': video_id,
+            'title': self._live_title(title) if is_live else title,
+            'formats': formats,
+            'is_live': is_live,
+        }

youtube_dl/extractor/adultswim.py

@@ -1,13 +1,19 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .turner import TurnerBaseIE
 from ..utils import (
+    determine_ext,
+    float_or_none,
     int_or_none,
+    mimetype2ext,
+    parse_age_limit,
+    parse_iso8601,
     strip_or_none,
-    url_or_none,
+    try_get,
 )
 
 
@@ -21,8 +27,8 @@ class AdultSwimIE(TurnerBaseIE):
             'ext': 'mp4',
             'title': 'Rick and Morty - Pilot',
             'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
-            'timestamp': 1493267400,
-            'upload_date': '20170427',
+            'timestamp': 1543294800,
+            'upload_date': '20181127',
         },
         'params': {
             # m3u8 download
@@ -43,6 +49,7 @@ class AdultSwimIE(TurnerBaseIE):
             # m3u8 download
             'skip_download': True,
         },
+        'skip': '404 Not Found',
     }, {
         'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
         'info_dict': {
@@ -61,9 +68,9 @@ class AdultSwimIE(TurnerBaseIE):
     }, {
         'url': 'http://www.adultswim.com/videos/attack-on-titan',
         'info_dict': {
-            'id': 'b7A69dzfRzuaXIECdxW8XQ',
+            'id': 'attack-on-titan',
             'title': 'Attack on Titan',
-            'description': 'md5:6c8e003ea0777b47013e894767f5e114',
+            'description': 'md5:41caa9416906d90711e31dc00cb7db7e',
         },
         'playlist_mincount': 12,
     }, {
@@ -78,83 +85,118 @@ class AdultSwimIE(TurnerBaseIE):
             # m3u8 download
             'skip_download': True,
         },
+        'skip': '404 Not Found',
     }]
 
     def _real_extract(self, url):
         show_path, episode_path = re.match(self._VALID_URL, url).groups()
         display_id = episode_path or show_path
-        webpage = self._download_webpage(url, display_id)
-        initial_data = self._parse_json(self._search_regex(
-            r'AS_INITIAL_DATA(?:__)?\s*=\s*({.+?});',
-            webpage, 'initial data'), display_id)
-
-        is_stream = show_path == 'streams'
-        if is_stream:
-            if not episode_path:
-                episode_path = 'live-stream'
-
-            video_data = next(stream for stream_path, stream in initial_data['streams'].items() if stream_path == episode_path)
-            video_id = video_data.get('stream')
-
-            if not video_id:
-                entries = []
-                for episode in video_data.get('archiveEpisodes', []):
-                    episode_url = url_or_none(episode.get('url'))
-                    if not episode_url:
-                        continue
-                    entries.append(self.url_result(
-                        episode_url, 'AdultSwim', episode.get('id')))
-                return self.playlist_result(
-                    entries, video_data.get('id'), video_data.get('title'),
-                    strip_or_none(video_data.get('description')))
+        query = '''query {
+  getShowBySlug(slug:"%s") {
+    %%s
+  }
+}''' % show_path
+        if episode_path:
+            query = query % '''title
+    getVideoBySlug(slug:"%s") {
+      _id
+      auth
+      description
+      duration
+      episodeNumber
+      launchDate
+      mediaID
+      seasonNumber
+      poster
+      title
+      tvRating
+    }''' % episode_path
+            ['getVideoBySlug']
         else:
-            show_data = initial_data['show']
+            query = query % '''metaDescription
+    title
+    videos(first:1000,sort:["episode_number"]) {
+      edges {
+        node {
+           _id
+           slug
+        }
+      }
+    }'''
+        show_data = self._download_json(
+            'https://www.adultswim.com/api/search', display_id,
+            data=json.dumps({'query': query}).encode(),
+            headers={'Content-Type': 'application/json'})['data']['getShowBySlug']
+        if episode_path:
+            video_data = show_data['getVideoBySlug']
+            video_id = video_data['_id']
+            episode_title = title = video_data['title']
+            series = show_data.get('title')
+            if series:
+                title = '%s - %s' % (series, title)
+            info = {
+                'id': video_id,
+                'title': title,
+                'description': strip_or_none(video_data.get('description')),
+                'duration': float_or_none(video_data.get('duration')),
+                'formats': [],
+                'subtitles': {},
+                'age_limit': parse_age_limit(video_data.get('tvRating')),
+                'thumbnail': video_data.get('poster'),
+                'timestamp': parse_iso8601(video_data.get('launchDate')),
+                'series': series,
+                'season_number': int_or_none(video_data.get('seasonNumber')),
+                'episode': episode_title,
+                'episode_number': int_or_none(video_data.get('episodeNumber')),
+            }
 
-            if not episode_path:
-                entries = []
-                for video in show_data.get('videos', []):
-                    slug = video.get('slug')
-                    if not slug:
+            auth = video_data.get('auth')
+            media_id = video_data.get('mediaID')
+            if media_id:
+                info.update(self._extract_ngtv_info(media_id, {
+                    # CDN_TOKEN_APP_ID from:
+                    # https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js
+                    'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE',
+                }, {
+                    'url': url,
+                    'site_name': 'AdultSwim',
+                    'auth_required': auth,
+                }))
+
+            if not auth:
+                extract_data = self._download_json(
+                    'https://www.adultswim.com/api/shows/v1/videos/' + video_id,
+                    video_id, query={'fields': 'stream'}, fatal=False) or {}
+                assets = try_get(extract_data, lambda x: x['data']['video']['stream']['assets'], list) or []
+                for asset in assets:
+                    asset_url = asset.get('url')
+                    if not asset_url:
                         continue
-                    entries.append(self.url_result(
-                        'http://adultswim.com/videos/%s/%s' % (show_path, slug),
-                        'AdultSwim', video.get('id')))
-                return self.playlist_result(
-                    entries, show_data.get('id'), show_data.get('title'),
-                    strip_or_none(show_data.get('metadata', {}).get('description')))
+                    ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type')))
+                    if ext == 'm3u8':
+                        info['formats'].extend(self._extract_m3u8_formats(
+                            asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                    elif ext == 'f4m':
+                        continue
+                        # info['formats'].extend(self._extract_f4m_formats(
+                        #     asset_url, video_id, f4m_id='hds', fatal=False))
+                    elif ext in ('scc', 'ttml', 'vtt'):
+                        info['subtitles'].setdefault('en', []).append({
+                            'url': asset_url,
+                        })
+            self._sort_formats(info['formats'])
 
-            video_data = show_data['sluggedVideo']
-            video_id = video_data['id']
-
-        info = self._extract_cvp_info(
-            'http://www.adultswim.com/videos/api/v0/assets?platform=desktop&id=' + video_id,
-            video_id, {
-                'secure': {
-                    'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
-                    'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
-                },
-            }, {
-                'url': url,
-                'site_name': 'AdultSwim',
-                'auth_required': video_data.get('auth'),
-            })
-
-        info.update({
-            'id': video_id,
-            'display_id': display_id,
-            'description': info.get('description') or strip_or_none(video_data.get('description')),
-        })
-        if not is_stream:
-            info.update({
-                'duration': info.get('duration') or int_or_none(video_data.get('duration')),
-                'timestamp': info.get('timestamp') or int_or_none(video_data.get('launch_date')),
-                'season_number': info.get('season_number') or int_or_none(video_data.get('season_number')),
-                'episode': info['title'],
-                'episode_number': info.get('episode_number') or int_or_none(video_data.get('episode_number')),
-            })
-
-            info['series'] = video_data.get('collection_title') or info.get('series')
-            if info['series'] and info['series'] != info['title']:
-                info['title'] = '%s - %s' % (info['series'], info['title'])
-
-        return info
+            return info
+        else:
+            entries = []
+            for edge in show_data.get('videos', {}).get('edges', []):
+                video = edge.get('node') or {}
+                slug = video.get('slug')
+                if not slug:
+                    continue
+                entries.append(self.url_result(
+                    'http://adultswim.com/videos/%s/%s' % (show_path, slug),
+                    'AdultSwim', video.get('_id')))
+            return self.playlist_result(
+                entries, show_path, show_data.get('title'),
+                strip_or_none(show_data.get('metaDescription')))

youtube_dl/extractor/anitube.py

@@ -1,30 +0,0 @@
-from __future__ import unicode_literals
-
-from .nuevo import NuevoBaseIE
-
-
-class AnitubeIE(NuevoBaseIE):
-    IE_NAME = 'anitube.se'
-    _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
-
-    _TEST = {
-        'url': 'http://www.anitube.se/video/36621',
-        'md5': '59d0eeae28ea0bc8c05e7af429998d43',
-        'info_dict': {
-            'id': '36621',
-            'ext': 'mp4',
-            'title': 'Recorder to Randoseru 01',
-            'duration': 180.19,
-        },
-        'skip': 'Blocked in the US',
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        key = self._search_regex(
-            r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
-
-        return self._extract_nuevo(
-            'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, video_id)

youtube_dl/extractor/anysex.py

@@ -1,61 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    parse_duration,
-    int_or_none,
-)
-
-
-class AnySexIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://anysex.com/156592/',
-        'md5': '023e9fbb7f7987f5529a394c34ad3d3d',
-        'info_dict': {
-            'id': '156592',
-            'ext': 'mp4',
-            'title': 'Busty and sexy blondie in her bikini strips for you',
-            'description': 'md5:de9e418178e2931c10b62966474e1383',
-            'categories': ['Erotic'],
-            'duration': 270,
-            'age_limit': 18,
-        }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        webpage = self._download_webpage(url, video_id)
-
-        video_url = self._html_search_regex(r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
-
-        title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
-        description = self._html_search_regex(
-            r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False)
-        thumbnail = self._html_search_regex(
-            r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
-
-        categories = re.findall(
-            r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
-
-        duration = parse_duration(self._search_regex(
-            r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False))
-        view_count = int_or_none(self._html_search_regex(
-            r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'categories': categories,
-            'duration': duration,
-            'view_count': view_count,
-            'age_limit': 18,
-        }

youtube_dl/extractor/arkena.py

@@ -103,7 +103,7 @@ class ArkenaIE(InfoExtractor):
                         f_url, video_id, mpd_id=kind, fatal=False))
                 elif kind == 'silverlight':
                     # TODO: process when ism is supported (see
-                    # https://github.com/rg3/youtube-dl/issues/8118)
+                    # https://github.com/ytdl-org/youtube-dl/issues/8118)
                     continue
                 else:
                     tbr = float_or_none(f.get('Bitrate'), 1000)

youtube_dl/extractor/bambuser.py

@@ -23,7 +23,7 @@ class BambuserIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://bambuser.com/v/4050584',
-        # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388
+        # MD5 seems to be flaky, see https://travis-ci.org/ytdl-org/youtube-dl/jobs/14051016#L388
         # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
         'info_dict': {
             'id': '4050584',
@@ -38,7 +38,7 @@ class BambuserIE(InfoExtractor):
         },
         'params': {
             # It doesn't respect the 'Range' header, it would download the whole video
-            # caused the travis builds to fail: https://travis-ci.org/rg3/youtube-dl/jobs/14493845#L59
+            # caused the travis builds to fail: https://travis-ci.org/ytdl-org/youtube-dl/jobs/14493845#L59
             'skip_download': True,
         },
     }

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,
 )
@@ -206,7 +208,7 @@ class BBCCoUkIE(InfoExtractor):
             },
             'skip': 'Now it\'s really geo-restricted',
         }, {
-            # compact player (https://github.com/rg3/youtube-dl/issues/8147)
+            # compact player (https://github.com/ytdl-org/youtube-dl/issues/8147)
             'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
             'info_dict': {
                 'id': 'p028bfkj',
@@ -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] = [
                 {

youtube_dl/extractor/beeg.py

@@ -9,8 +9,8 @@ from ..utils import (
 
 
 class BeegIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
+    _TESTS = [{
         'url': 'http://beeg.com/5416503',
         'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
         'info_dict': {
@@ -24,7 +24,13 @@ class BeegIE(InfoExtractor):
             'tags': list,
             'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'https://beeg.porn/video/5416503',
+        'only_matching': True,
+    }, {
+        'url': 'https://beeg.porn/5416503',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/bfi.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import extract_attributes
+
+
+class BFIPlayerIE(InfoExtractor):
+    IE_NAME = 'bfi:player'
+    _VALID_URL = r'https?://player\.bfi\.org\.uk/[^/]+/film/watch-(?P<id>[\w-]+)-online'
+    _TEST = {
+        'url': 'https://player.bfi.org.uk/free/film/watch-computer-doctor-1974-online',
+        'md5': 'e8783ebd8e061ec4bc6e9501ed547de8',
+        'info_dict': {
+            'id': 'htNnhlZjE60C9VySkQEIBtU-cNV1Xx63',
+            'ext': 'mp4',
+            'title': 'Computer Doctor',
+            'description': 'md5:fb6c240d40c4dbe40428bdd62f78203b',
+        },
+        'skip': 'BFI Player films cannot be played outside of the UK',
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        entries = []
+        for player_el in re.findall(r'(?s)<[^>]+class="player"[^>]*>', webpage):
+            player_attr = extract_attributes(player_el)
+            ooyala_id = player_attr.get('data-video-id')
+            if not ooyala_id:
+                continue
+            entries.append(self.url_result(
+                'ooyala:' + ooyala_id, 'Ooyala',
+                ooyala_id, player_attr.get('data-label')))
+        return self.playlist_result(entries)

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/biqle.py

@@ -2,39 +2,96 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .vk import VKIE
+from ..utils import (
+    HEADRequest,
+    int_or_none,
+)
 
 
 class BIQLEIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
     _TESTS = [{
-        'url': 'http://www.biqle.ru/watch/847655_160197695',
-        'md5': 'ad5f746a874ccded7b8f211aeea96637',
+        # Youtube embed
+        'url': 'https://biqle.ru/watch/-115995369_456239081',
+        'md5': '97af5a06ee4c29bbf9c001bdb1cf5c06',
         'info_dict': {
-            'id': '160197695',
+            'id': '8v4f-avW-VI',
             'ext': 'mp4',
-            'title': 'Foo Fighters - The Pretender (Live at Wembley Stadium)',
-            'uploader': 'Andrey Rogozin',
-            'upload_date': '20110605',
-        }
+            'title': "PASSE-PARTOUT - L'ete c'est fait pour jouer",
+            'description': 'Passe-Partout',
+            'uploader_id': 'mrsimpsonstef3',
+            'uploader': 'Phanolito',
+            'upload_date': '20120822',
+        },
     }, {
-        'url': 'https://biqle.org/watch/-44781847_168547604',
+        'url': 'http://biqle.org/watch/-44781847_168547604',
         'md5': '7f24e72af1db0edf7c1aaba513174f97',
         'info_dict': {
-            'id': '168547604',
+            'id': '-44781847_168547604',
             'ext': 'mp4',
             'title': 'Ребенок в шоке от автоматической мойки',
+            'timestamp': 1396633454,
             'uploader': 'Dmitry Kotov',
+            'upload_date': '20140404',
+            'uploader_id': '47850140',
         },
-        'skip': ' This video was marked as adult.  Embedding adult videos on external sites is prohibited.',
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         embed_url = self._proto_relative_url(self._search_regex(
-            r'<iframe.+?src="((?:http:)?//daxab\.com/[^"]+)".*?></iframe>', webpage, 'embed url'))
+            r'<iframe.+?src="((?:https?:)?//daxab\.com/[^"]+)".*?></iframe>',
+            webpage, 'embed url'))
+        if VKIE.suitable(embed_url):
+            return self.url_result(embed_url, VKIE.ie_key(), video_id)
+
+        self._request_webpage(
+            HEADRequest(embed_url), video_id, headers={'Referer': url})
+        video_id, sig, _, access_token = self._get_cookies(embed_url)['video_ext'].value.split('%3A')
+        item = self._download_json(
+            'https://api.vk.com/method/video.get', video_id,
+            headers={'User-Agent': 'okhttp/3.4.1'}, query={
+                'access_token': access_token,
+                'sig': sig,
+                'v': 5.44,
+                'videos': video_id,
+            })['response']['items'][0]
+        title = item['title']
+
+        formats = []
+        for f_id, f_url in item.get('files', {}).items():
+            if f_id == 'external':
+                return self.url_result(f_url)
+            ext, height = f_id.split('_')
+            formats.append({
+                'format_id': height + 'p',
+                'url': f_url,
+                'height': int_or_none(height),
+                'ext': ext,
+            })
+        self._sort_formats(formats)
+
+        thumbnails = []
+        for k, v in item.items():
+            if k.startswith('photo_') and v:
+                width = k.replace('photo_', '')
+                thumbnails.append({
+                    'id': width,
+                    'url': v,
+                    'width': int_or_none(width),
+                })
 
         return {
-            '_type': 'url_transparent',
-            'url': embed_url,
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'comment_count': int_or_none(item.get('comments')),
+            'description': item.get('description'),
+            'duration': int_or_none(item.get('duration')),
+            'thumbnails': thumbnails,
+            'timestamp': int_or_none(item.get('date')),
+            'uploader': item.get('owner_id'),
+            'view_count': int_or_none(item.get('views')),
         }

youtube_dl/extractor/brightcove.py

@@ -126,7 +126,7 @@ class BrightcoveLegacyIE(InfoExtractor):
             'playlist_mincount': 7,
         },
         {
-            # playlist with 'playlistTab' (https://github.com/rg3/youtube-dl/issues/9965)
+            # playlist with 'playlistTab' (https://github.com/ytdl-org/youtube-dl/issues/9965)
             'url': 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=AQ%7E%7E,AAABXlLMdok%7E,NJ4EoMlZ4rZdx9eU1rkMVd8EaYPBBUlg',
             'info_dict': {
                 'id': '1522758701001',
@@ -155,10 +155,10 @@ class BrightcoveLegacyIE(InfoExtractor):
         <object class="BrightcoveExperience">{params}</object>
         """
 
-        # Fix up some stupid HTML, see https://github.com/rg3/youtube-dl/issues/1553
+        # Fix up some stupid HTML, see https://github.com/ytdl-org/youtube-dl/issues/1553
         object_str = re.sub(r'(<param(?:\s+[a-zA-Z0-9_]+="[^"]*")*)>',
                             lambda m: m.group(1) + '/>', object_str)
-        # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
+        # Fix up some stupid XML, see https://github.com/ytdl-org/youtube-dl/issues/1608
         object_str = object_str.replace('<--', '<!--')
         # remove namespace to simplify extraction
         object_str = re.sub(r'(<object[^>]*)(xmlns=".*?")', r'\1', object_str)

youtube_dl/extractor/cbc.py

@@ -360,7 +360,7 @@ class CBCWatchVideoIE(CBCWatchBaseIE):
 
 class CBCWatchIE(CBCWatchBaseIE):
     IE_NAME = 'cbc.ca:watch'
-    _VALID_URL = r'https?://watch\.cbc\.ca/(?:[^/]+/)+(?P<id>[0-9a-f-]+)'
+    _VALID_URL = r'https?://(?:gem|watch)\.cbc\.ca/(?:[^/]+/)+(?P<id>[0-9a-f-]+)'
     _TESTS = [{
         # geo-restricted to Canada, bypassable
         'url': 'http://watch.cbc.ca/doc-zone/season-6/customer-disservice/38e815a-009e3ab12e4',
@@ -386,6 +386,9 @@ class CBCWatchIE(CBCWatchBaseIE):
             'description': 'Arthur, the sweetest 8-year-old aardvark, and his pals solve all kinds of problems with humour, kindness and teamwork.',
         },
         'playlist_mincount': 30,
+    }, {
+        'url': 'https://gem.cbc.ca/media/this-hour-has-22-minutes/season-26/episode-20/38e815a-0108c6c6a42',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/ceskatelevize.py

@@ -155,7 +155,7 @@ class CeskaTelevizeIE(InfoExtractor):
                         stream_formats = self._extract_mpd_formats(
                             stream_url, playlist_id,
                             mpd_id='dash-%s' % format_id, fatal=False)
-                    # See https://github.com/rg3/youtube-dl/issues/12119#issuecomment-280037031
+                    # See https://github.com/ytdl-org/youtube-dl/issues/12119#issuecomment-280037031
                     if format_id == 'audioDescription':
                         for f in stream_formats:
                             f['source_preference'] = -10

youtube_dl/extractor/ciscolive.py

@@ -65,8 +65,8 @@ class CiscoLiveBaseIE(InfoExtractor):
 
 
 class CiscoLiveSessionIE(CiscoLiveBaseIE):
-    _VALID_URL = r'https?://ciscolive\.cisco\.com/on-demand-library/\??[^#]*#/session/(?P<id>[^/?&]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?ciscolive(?:\.cisco)?\.com/[^#]*#/session/(?P<id>[^/?&]+)'
+    _TESTS = [{
         'url': 'https://ciscolive.cisco.com/on-demand-library/?#/session/1423353499155001FoSs',
         'md5': 'c98acf395ed9c9f766941c70f5352e22',
         'info_dict': {
@@ -79,7 +79,13 @@ class CiscoLiveSessionIE(CiscoLiveBaseIE):
             'uploader_id': '5647924234001',
             'location': '16B Mezz.',
         },
-    }
+    }, {
+        'url': 'https://www.ciscolive.com/global/on-demand-library.html?search.event=ciscoliveemea2019#/session/15361595531500013WOU',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ciscolive.com/global/on-demand-library.html?#/session/1490051371645001kNaS',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         rf_id = self._match_id(url)
@@ -88,7 +94,7 @@ class CiscoLiveSessionIE(CiscoLiveBaseIE):
 
 
 class CiscoLiveSearchIE(CiscoLiveBaseIE):
-    _VALID_URL = r'https?://ciscolive\.cisco\.com/on-demand-library/'
+    _VALID_URL = r'https?://(?:www\.)?ciscolive(?:\.cisco)?\.com/(?:global/)?on-demand-library(?:\.html|/)'
     _TESTS = [{
         'url': 'https://ciscolive.cisco.com/on-demand-library/?search.event=ciscoliveus2018&search.technicallevel=scpsSkillLevel_aintroductory&search.focus=scpsSessionFocus_designAndDeployment#/',
         'info_dict': {
@@ -98,6 +104,9 @@ class CiscoLiveSearchIE(CiscoLiveBaseIE):
     }, {
         'url': 'https://ciscolive.cisco.com/on-demand-library/?search.technology=scpsTechnology_applicationDevelopment&search.technology=scpsTechnology_ipv6&search.focus=scpsSessionFocus_troubleshootingTroubleshooting#/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.ciscolive.com/global/on-demand-library.html?search.technicallevel=scpsSkillLevel_aintroductory&search.event=ciscoliveemea2019&search.technology=scpsTechnology_dataCenter&search.focus=scpsSessionFocus_bestPractices#/',
+        'only_matching': True,
     }]
 
     @classmethod

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,
@@ -43,6 +44,7 @@ from ..utils import (
     compiled_regex_type,
     determine_ext,
     determine_protocol,
+    dict_get,
     error_to_compat_str,
     ExtractorError,
     extract_attributes,
@@ -55,13 +57,16 @@ from ..utils import (
     JSON_LD_RE,
     mimetype2ext,
     orderedSet,
+    parse_bitrate,
     parse_codecs,
     parse_duration,
     parse_iso8601,
     parse_m3u8_attributes,
+    parse_resolution,
     RegexNotFoundError,
     sanitized_Request,
     sanitize_filename,
+    str_or_none,
     unescapeHTML,
     unified_strdate,
     unified_timestamp,
@@ -102,10 +107,26 @@ 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
+                                     - HTTP URL to plain file media (in case of
+                                       unfragmented media)
+                                     - URL of the MPD manifest or base URL
+                                       representing the media if MPD manifest
+                                       is parsed froma string (in case of
+                                       fragmented media)
+                                   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 +809,7 @@ 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 +830,7 @@ 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 +1079,7 @@ 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 [
@@ -1440,7 +1461,7 @@ class InfoExtractor(object):
             manifest_url, video_id, 'Downloading f4m manifest',
             'Unable to download f4m manifest',
             # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
-            # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244)
+            # (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244)
             transform_source=transform_source,
             fatal=fatal)
 
@@ -1454,6 +1475,9 @@ 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:
@@ -1468,7 +1492,7 @@ class InfoExtractor(object):
             manifest_version = '2.0'
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
         # Remove unsupported DRM protected media from final formats
-        # rendition (see https://github.com/rg3/youtube-dl/issues/8573).
+        # rendition (see https://github.com/ytdl-org/youtube-dl/issues/8573).
         media_nodes = remove_encrypted_media(media_nodes)
         if not media_nodes:
             return formats
@@ -1598,8 +1622,8 @@ 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
+        # 2. https://github.com/ytdl-org/youtube-dl/issues/12211
+        # 3. https://github.com/ytdl-org/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
@@ -2120,7 +2144,6 @@ 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,
                             'manifest_url': mpd_url,
                             'ext': mimetype2ext(mime_type),
                             'width': int_or_none(representation_attrib.get('width')),
@@ -2141,7 +2164,7 @@ class InfoExtractor(object):
                             # First of, % characters outside $...$ templates
                             # must be escaped by doubling for proper processing
                             # by % operator string formatting used further (see
-                            # https://github.com/rg3/youtube-dl/issues/16867).
+                            # https://github.com/ytdl-org/youtube-dl/issues/16867).
                             t = ''
                             in_template = False
                             for c in tmpl:
@@ -2160,7 +2183,7 @@ class InfoExtractor(object):
 
                         # @initialization is a regular template like @media one
                         # so it should be handled just the same way (see
-                        # https://github.com/rg3/youtube-dl/issues/11605)
+                        # https://github.com/ytdl-org/youtube-dl/issues/11605)
                         if 'initialization' in representation_ms_info:
                             initialization_template = prepare_template(
                                 'initialization',
@@ -2246,7 +2269,7 @@ class InfoExtractor(object):
                         elif 'segment_urls' in representation_ms_info:
                             # Segment URLs with no SegmentTimeline
                             # Example: https://www.seznam.cz/zpravy/clanek/cesko-zasahne-vitr-o-sile-vichrice-muze-byt-i-zivotu-nebezpecny-39091
-                            # https://github.com/rg3/youtube-dl/pull/14844
+                            # https://github.com/ytdl-org/youtube-dl/pull/14844
                             fragments = []
                             segment_duration = float_or_none(
                                 representation_ms_info['segment_duration'],
@@ -2259,10 +2282,14 @@ class InfoExtractor(object):
                                     fragment['duration'] = segment_duration
                                 fragments.append(fragment)
                             representation_ms_info['fragments'] = fragments
-                        # NB: MPD manifest may contain direct URLs to unfragmented media.
-                        # No fragments key is present in this case.
+                        # If there is a fragments key available then we correctly recognized fragmented media.
+                        # Otherwise we will assume unfragmented media with direct access. Technically, such
+                        # assumption is not necessarily correct since we may simply have no support for
+                        # some forms of fragmented media renditions yet, but for now we'll use this fallback.
                         if 'fragments' in representation_ms_info:
                             f.update({
+                                # NB: mpd_url may be empty when MPD manifest is parsed from a string
+                                'url': mpd_url or base_url,
                                 'fragment_base_url': base_url,
                                 'fragments': [],
                                 'protocol': 'http_dash_segments',
@@ -2273,11 +2300,15 @@ class InfoExtractor(object):
                                     f['url'] = initialization_url
                                 f['fragments'].append({location_key(initialization_url): initialization_url})
                             f['fragments'].extend(representation_ms_info['fragments'])
+                        else:
+                            # Assuming direct URL to unfragmented media.
+                            f['url'] = base_url
+
                         # According to [1, 5.3.5.2, Table 7, page 35] @id of Representation
                         # is not necessarily unique within a Period thus formats with
                         # the same `format_id` are quite possible. There are numerous examples
-                        # of such manifests (see https://github.com/rg3/youtube-dl/issues/15111,
-                        # https://github.com/rg3/youtube-dl/issues/13919)
+                        # of such manifests (see https://github.com/ytdl-org/youtube-dl/issues/15111,
+                        # https://github.com/ytdl-org/youtube-dl/issues/13919)
                         full_info = formats_dict.get(representation_id, {}).copy()
                         full_info.update(f)
                         formats.append(full_info)
@@ -2438,7 +2469,7 @@ class InfoExtractor(object):
         media_tags.extend(re.findall(
             # We only allow video|audio followed by a whitespace or '>'.
             # Allowing more characters may end up in significant slow down (see
-            # https://github.com/rg3/youtube-dl/issues/11979, example URL:
+            # https://github.com/ytdl-org/youtube-dl/issues/11979, example URL:
             # http://www.porntrex.com/maps/videositemap.xml).
             r'(?s)(<(?P<tag>(?:amp-)?(?:video|audio))(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
         for media_tag, media_type, media_content in media_tags:
@@ -2454,18 +2485,43 @@ class InfoExtractor(object):
             media_info['thumbnail'] = absolute_url(media_attributes.get('poster'))
             if media_content:
                 for source_tag in re.findall(r'<source[^>]+>', media_content):
-                    source_attributes = extract_attributes(source_tag)
-                    src = source_attributes.get('src')
+                    s_attr = extract_attributes(source_tag)
+                    # data-video-src and data-src are non standard but seen
+                    # several times in the wild
+                    src = dict_get(s_attr, ('src', 'data-video-src', 'data-src'))
                     if not src:
                         continue
-                    f = parse_content_type(source_attributes.get('type'))
+                    f = parse_content_type(s_attr.get('type'))
                     is_plain_url, formats = _media_formats(src, media_type, f)
                     if is_plain_url:
-                        # res attribute is not standard but seen several times
-                        # in the wild
+                        # width, height, res, label and title attributes are
+                        # all not standard but seen several times in the wild
+                        labels = [
+                            s_attr.get(lbl)
+                            for lbl in ('label', 'title')
+                            if str_or_none(s_attr.get(lbl))
+                        ]
+                        width = int_or_none(s_attr.get('width'))
+                        height = (int_or_none(s_attr.get('height')) or
+                                  int_or_none(s_attr.get('res')))
+                        if not width or not height:
+                            for lbl in labels:
+                                resolution = parse_resolution(lbl)
+                                if not resolution:
+                                    continue
+                                width = width or resolution.get('width')
+                                height = height or resolution.get('height')
+                        for lbl in labels:
+                            tbr = parse_bitrate(lbl)
+                            if tbr:
+                                break
+                        else:
+                            tbr = None
                         f.update({
-                            'height': int_or_none(source_attributes.get('res')),
-                            'format_id': source_attributes.get('label'),
+                            'width': width,
+                            'height': height,
+                            'tbr': tbr,
+                            'format_id': s_attr.get('label') or s_attr.get('title'),
                         })
                         f.update(formats[0])
                         media_info['formats'].append(f)

youtube_dl/extractor/commonmistakes.py

@@ -36,7 +36,7 @@ class UnicodeBOMIE(InfoExtractor):
         _VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$'
 
         # Disable test for python 3.2 since BOM is broken in re in this version
-        # (see https://github.com/rg3/youtube-dl/issues/9751)
+        # (see https://github.com/ytdl-org/youtube-dl/issues/9751)
         _TESTS = [] if (3, 0) < sys.version_info <= (3, 3) else [{
             'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc',
             'only_matching': True,

youtube_dl/extractor/corus.py

@@ -13,9 +13,9 @@ class CorusIE(ThePlatformFeedIE):
                         (?:www\.)?
                         (?P<domain>
                             (?:globaltv|etcanada)\.com|
-                            (?:hgtv|foodnetwork|slice|history|showcase)\.ca
+                            (?:hgtv|foodnetwork|slice|history|showcase|bigbrothercanada)\.ca
                         )
-                        /(?:video/|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=))
+                        /(?:video/(?:[^/]+/)?|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=))
                         (?P<id>\d+)
                     '''
     _TESTS = [{
@@ -42,6 +42,12 @@ class CorusIE(ThePlatformFeedIE):
     }, {
         'url': 'http://www.showcase.ca/eyewitness/video/eyewitness++106/video.html?v=955070531919&p=1&s=da#video',
         'only_matching': True,
+    }, {
+        'url': 'http://www.bigbrothercanada.ca/video/1457812035894/',
+        'only_matching': True
+    }, {
+        'url': 'https://www.bigbrothercanada.ca/video/big-brother-canada-704/1457812035894/',
+        'only_matching': True
     }]
 
     _TP_FEEDS = {
@@ -73,6 +79,10 @@ class CorusIE(ThePlatformFeedIE):
             'feed_id': '9H6qyshBZU3E',
             'account_id': 2414426607,
         },
+        'bigbrothercanada': {
+            'feed_id': 'ChQqrem0lNUp',
+            'account_id': 2269680845,
+        },
     }
 
     def _real_extract(self, url):

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
@@ -74,13 +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

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()
@@ -119,7 +107,7 @@ class CrunchyrollBaseIE(InfoExtractor):
         request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
                    else sanitized_Request(url_or_request))
         # Accept-Language must be set explicitly to accept any language to avoid issues
-        # similar to https://github.com/rg3/youtube-dl/issues/6797.
+        # similar to https://github.com/ytdl-org/youtube-dl/issues/6797.
         # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
         # should be imposed or not (from what I can see it just takes the first language
         # ignoring the priority and requires it to correspond the IP). By the way this causes
@@ -136,7 +124,7 @@ class CrunchyrollBaseIE(InfoExtractor):
         # > This content may be inappropriate for some people.
         # > Are you sure you want to continue?
         # since it's not disabled by default in crunchyroll account's settings.
-        # See https://github.com/rg3/youtube-dl/issues/7202.
+        # See https://github.com/ytdl-org/youtube-dl/issues/7202.
         qs['skip_wall'] = ['1']
         return compat_urlparse.urlunparse(
             parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
@@ -402,7 +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')
@@ -519,7 +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)
@@ -530,7 +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')
@@ -605,7 +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/cwtv.py

@@ -79,7 +79,7 @@ class CWTVIE(InfoExtractor):
         season = str_or_none(video_data.get('season'))
         episode = str_or_none(video_data.get('episode'))
         if episode and season:
-            episode = episode.lstrip(season)
+            episode = episode[len(season):]
 
         return {
             '_type': 'url_transparent',

youtube_dl/extractor/dailymotion.py

@@ -166,11 +166,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             webpage, 'comment count', default=None))
 
         player_v5 = self._search_regex(
-            [r'buildPlayer\(({.+?})\);\n',  # See https://github.com/rg3/youtube-dl/issues/7826
+            [r'buildPlayer\(({.+?})\);\n',  # See https://github.com/ytdl-org/youtube-dl/issues/7826
              r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
              r'buildPlayer\(({.+?})\);',
              r'var\s+config\s*=\s*({.+?});',
-             # New layout regex (see https://github.com/rg3/youtube-dl/issues/13580)
+             # New layout regex (see https://github.com/ytdl-org/youtube-dl/issues/13580)
              r'__PLAYER_CONFIG__\s*=\s*({.+?});'],
             webpage, 'player v5', default=None)
         if player_v5:

youtube_dl/extractor/dreisat.py

@@ -114,7 +114,7 @@ class DreiSatIE(InfoExtractor):
                     video_url, video_id, fatal=False))
             elif ext == 'm3u8':
                 # the certificates are misconfigured (see
-                # https://github.com/rg3/youtube-dl/issues/8665)
+                # https://github.com/ytdl-org/youtube-dl/issues/8665)
                 if video_url.startswith('https://'):
                     continue
                 formats.extend(self._extract_m3u8_formats(

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

@@ -171,10 +171,13 @@ class DRTVIE(InfoExtractor):
                         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',

youtube_dl/extractor/dvtv.py

@@ -10,16 +10,16 @@ from ..utils import (
     int_or_none,
     js_to_json,
     mimetype2ext,
+    try_get,
     unescapeHTML,
+    parse_iso8601,
 )
 
 
 class DVTVIE(InfoExtractor):
     IE_NAME = 'dvtv'
     IE_DESC = 'http://video.aktualne.cz/'
-
     _VALID_URL = r'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
-
     _TESTS = [{
         'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
         'md5': '67cb83e4a955d36e1b5d31993134a0c2',
@@ -28,11 +28,13 @@ class DVTVIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně',
             'duration': 1484,
+            'upload_date': '20141217',
+            'timestamp': 1418792400,
         }
     }, {
         'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/',
         'info_dict': {
-            'title': r're:^DVTV 16\. 12\. 2014: útok Talibanu, boj o kliniku, uprchlíci',
+            'title': r'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci',
             'id': '973eb3bc854e11e498be002590604f2e',
         },
         'playlist': [{
@@ -84,6 +86,8 @@ class DVTVIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Zeman si jen léčí mindráky, Sobotku nenávidí a Babiš se mu teď hodí, tvrdí Kmenta',
             'duration': 1103,
+            'upload_date': '20170511',
+            'timestamp': 1494514200,
         },
         'params': {
             'skip_download': True,
@@ -91,43 +95,59 @@ class DVTVIE(InfoExtractor):
     }, {
         'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/',
         'only_matching': True,
+    }, {
+        # Test live stream video (liveStarter) parsing
+        'url': 'https://video.aktualne.cz/dvtv/zive-mistryne-sveta-eva-samkova-po-navratu-ze-sampionatu/r~182654c2288811e990fd0cc47ab5f122/',
+        'md5': '2e552e483f2414851ca50467054f9d5d',
+        'info_dict': {
+            'id': '8d116360288011e98c840cc47ab5f122',
+            'ext': 'mp4',
+            'title': 'Živě: Mistryně světa Eva Samková po návratu ze šampionátu',
+            'upload_date': '20190204',
+            'timestamp': 1549289591,
+        },
+        'params': {
+            # Video content is no longer available
+            'skip_download': True,
+        },
     }]
 
-    def _parse_video_metadata(self, js, video_id, live_js=None):
+    def _parse_video_metadata(self, js, video_id, timestamp):
         data = self._parse_json(js, video_id, transform_source=js_to_json)
-        if live_js:
-            data.update(self._parse_json(
-                live_js, video_id, transform_source=js_to_json))
-
         title = unescapeHTML(data['title'])
 
+        live_starter = try_get(data, lambda x: x['plugins']['liveStarter'], dict)
+        if live_starter:
+            data.update(live_starter)
+
         formats = []
-        for video in data['sources']:
-            video_url = video.get('file')
-            if not video_url:
-                continue
-            video_type = video.get('type')
-            ext = determine_ext(video_url, mimetype2ext(video_type))
-            if video_type == 'application/vnd.apple.mpegurl' or ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False))
-            elif video_type == 'application/dash+xml' or ext == 'mpd':
-                formats.extend(self._extract_mpd_formats(
-                    video_url, video_id, mpd_id='dash', fatal=False))
-            else:
-                label = video.get('label')
-                height = self._search_regex(
-                    r'^(\d+)[pP]', label or '', 'height', default=None)
-                format_id = ['http']
-                for f in (ext, label):
-                    if f:
-                        format_id.append(f)
-                formats.append({
-                    'url': video_url,
-                    'format_id': '-'.join(format_id),
-                    'height': int_or_none(height),
-                })
+        for tracks in data.get('tracks', {}).values():
+            for video in tracks:
+                video_url = video.get('src')
+                if not video_url:
+                    continue
+                video_type = video.get('type')
+                ext = determine_ext(video_url, mimetype2ext(video_type))
+                if video_type == 'application/vnd.apple.mpegurl' or ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id='hls', fatal=False))
+                elif video_type == 'application/dash+xml' or ext == 'mpd':
+                    formats.extend(self._extract_mpd_formats(
+                        video_url, video_id, mpd_id='dash', fatal=False))
+                else:
+                    label = video.get('label')
+                    height = self._search_regex(
+                        r'^(\d+)[pP]', label or '', 'height', default=None)
+                    format_id = ['http']
+                    for f in (ext, label):
+                        if f:
+                            format_id.append(f)
+                    formats.append({
+                        'url': video_url,
+                        'format_id': '-'.join(format_id),
+                        'height': int_or_none(height),
+                    })
         self._sort_formats(formats)
 
         return {
@@ -136,41 +156,29 @@ class DVTVIE(InfoExtractor):
             'description': data.get('description'),
             'thumbnail': data.get('image'),
             'duration': int_or_none(data.get('duration')),
-            'timestamp': int_or_none(data.get('pubtime')),
+            'timestamp': int_or_none(timestamp),
             'formats': formats
         }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
+        timestamp = parse_iso8601(self._html_search_meta(
+            'article:published_time', webpage, 'published time', default=None))
 
-        # live content
-        live_item = self._search_regex(
-            r'(?s)embedData[0-9a-f]{32}\.asset\.liveStarter\s*=\s*(\{.+?\});',
-            webpage, 'video', default=None)
-
-        # single video
-        item = self._search_regex(
-            r'(?s)embedData[0-9a-f]{32}\[["\']asset["\']\]\s*=\s*(\{.+?\});',
-            webpage, 'video', default=None)
-
-        if item:
-            return self._parse_video_metadata(item, video_id, live_item)
-
-        # playlist
-        items = re.findall(
-            r"(?s)BBX\.context\.assets\['[0-9a-f]{32}'\]\.push\(({.+?})\);",
-            webpage)
-        if not items:
-            items = re.findall(r'(?s)var\s+asset\s*=\s*({.+?});\n', webpage)
-
+        items = re.findall(r'(?s)playlist\.push\(({.+?})\);', webpage)
         if items:
-            return {
-                '_type': 'playlist',
-                'id': video_id,
-                'title': self._og_search_title(webpage),
-                'entries': [self._parse_video_metadata(i, video_id) for i in items]
-            }
+            return self.playlist_result(
+                [self._parse_video_metadata(i, video_id, timestamp) for i in items],
+                video_id, self._html_search_meta('twitter:title', webpage))
+
+        item = self._search_regex(
+            r'(?s)BBXPlayer\.setup\((.+?)\);',
+            webpage, 'video', default=None)
+        if item:
+            # remove function calls (ex. htmldeentitize)
+            # TODO this should be fixed in a general way in the js_to_json
+            item = re.sub(r'\w+?\((.+)\)', r'\1', item)
+            return self._parse_video_metadata(item, video_id, timestamp)
 
         raise ExtractorError('Could not find neither video nor playlist')

youtube_dl/extractor/escapist.py

@@ -1,14 +1,11 @@
 from __future__ import unicode_literals
 
-import json
-
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
     clean_html,
     int_or_none,
     float_or_none,
-    sanitized_Request,
 )
 
 
@@ -36,7 +33,7 @@ def _decrypt_config(key, string):
 
 
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'https?://?(?:www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
+    _VALID_URL = r'https?://?(?:(?:www|v1)\.)?escapistmagazine\.com/videos/view/[^/]+/(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
@@ -61,6 +58,12 @@ class EscapistIE(InfoExtractor):
             'duration': 304,
             'uploader': 'The Escapist',
         }
+    }, {
+        'url': 'http://escapistmagazine.com/videos/view/the-escapist-presents/6618',
+        'only_matching': True,
+    }, {
+        'url': 'https://v1.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -74,19 +77,20 @@ class EscapistIE(InfoExtractor):
         video_id = ims_video['videoID']
         key = ims_video['hash']
 
-        config_req = sanitized_Request(
-            'http://www.escapistmagazine.com/videos/'
-            'vidconfig.php?videoID=%s&hash=%s' % (video_id, key))
-        config_req.add_header('Referer', url)
-        config = self._download_webpage(config_req, video_id, 'Downloading video config')
+        config = self._download_webpage(
+            'http://www.escapistmagazine.com/videos/vidconfig.php',
+            video_id, 'Downloading video config', headers={
+                'Referer': url,
+            }, query={
+                'videoID': video_id,
+                'hash': key,
+            })
 
-        data = json.loads(_decrypt_config(key, config))
+        data = self._parse_json(_decrypt_config(key, config), video_id)
 
         video_data = data['videoData']
 
         title = clean_html(video_data['title'])
-        duration = float_or_none(video_data.get('duration'), 1000)
-        uploader = video_data.get('publisher')
 
         formats = [{
             'url': video['src'],
@@ -99,8 +103,9 @@ class EscapistIE(InfoExtractor):
             'id': video_id,
             'formats': formats,
             'title': title,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage) or data.get('poster'),
             'description': self._og_search_description(webpage),
-            'duration': duration,
-            'uploader': uploader,
+            'duration': float_or_none(video_data.get('duration'), 1000),
+            'uploader': video_data.get('publisher'),
+            'series': video_data.get('show'),
         }

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

@@ -20,6 +20,7 @@ from .acast import (
 )
 from .addanime import AddAnimeIE
 from .adn import ADNIE
+from .adobeconnect import AdobeConnectIE
 from .adobetv import (
     AdobeTVIE,
     AdobeTVShowIE,
@@ -38,9 +39,7 @@ from .alphaporno import AlphaPornoIE
 from .amcnetworks import AMCNetworksIE
 from .americastestkitchen import AmericasTestKitchenIE
 from .animeondemand import AnimeOnDemandIE
-from .anitube import AnitubeIE
 from .anvato import AnvatoIE
-from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aliexpress import AliExpressLiveIE
@@ -108,6 +107,7 @@ from .behindkink import BehindKinkIE
 from .bellmedia import BellMediaIE
 from .beatport import BeatportIE
 from .bet import BetIE
+from .bfi import BFIPlayerIE
 from .bigflix import BigflixIE
 from .bild import BildIE
 from .bilibili import (
@@ -442,10 +442,7 @@ from .goshgay import GoshgayIE
 from .gputechconf import GPUTechConfIE
 from .groupon import GrouponIE
 from .hark import HarkIE
-from .hbo import (
-    HBOIE,
-    HBOEpisodeIE,
-)
+from .hbo import HBOIE
 from .hearthisat import HearThisAtIE
 from .heise import HeiseIE
 from .hellporno import HellPornoIE
@@ -593,6 +590,7 @@ from .linkedin import (
     LinkedInLearningIE,
     LinkedInLearningCourseIE,
 )
+from .linuxacademy import LinuxAcademyIE
 from .litv import LiTVIE
 from .liveleak import (
     LiveLeakIE,
@@ -619,6 +617,7 @@ from .mailru import (
     MailRuMusicSearchIE,
 )
 from .makertv import MakerTVIE
+from .malltv import MallTVIE
 from .mangomolo import (
     MangomoloVideoIE,
     MangomoloLiveIE,
@@ -632,7 +631,11 @@ from .massengeschmacktv import MassengeschmackTVIE
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .mediaset import MediasetIE
-from .mediasite import MediasiteIE
+from .mediasite import (
+    MediasiteIE,
+    MediasiteCatalogIE,
+    MediasiteNamedCatalogIE,
+)
 from .medici import MediciIE
 from .megaphone import MegaphoneIE
 from .meipai import MeipaiIE
@@ -865,6 +868,10 @@ from .picarto import (
 from .piksel import PikselIE
 from .pinkbike import PinkbikeIE
 from .pladform import PladformIE
+from .platzi import (
+    PlatziIE,
+    PlatziCourseIE,
+)
 from .playfm import PlayFMIE
 from .playplustv import PlayPlusTVIE
 from .plays import PlaysTVIE
@@ -899,7 +906,6 @@ from .puhutv import (
     PuhuTVSerieIE,
 )
 from .presstv import PressTVIE
-from .primesharetv import PrimeShareTVIE
 from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .puls4 import Puls4IE
@@ -976,7 +982,6 @@ from .rtvnh import RTVNHIE
 from .rtvs import RTVSIE
 from .rudo import RudoIE
 from .ruhd import RUHDIE
-from .ruleporn import RulePornIE
 from .rutube import (
     RutubeIE,
     RutubeChannelIE,
@@ -1058,7 +1063,10 @@ 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
@@ -1113,6 +1121,7 @@ from .teachertube import (
 )
 from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
+from .teamtreehouse import TeamTreeHouseIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
 from .tele5 import Tele5IE
@@ -1167,6 +1176,7 @@ 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
@@ -1212,7 +1222,7 @@ from .tvnow import (
 from .tvp import (
     TVPEmbedIE,
     TVPIE,
-    TVPSeriesIE,
+    TVPWebsiteIE,
 )
 from .tvplay import (
     TVPlayIE,
@@ -1293,7 +1303,6 @@ from .viddler import ViddlerIE
 from .videa import VideaIE
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
-from .videomega import VideoMegaIE
 from .videomore import (
     VideomoreIE,
     VideomoreVideoIE,
@@ -1362,7 +1371,6 @@ from .voxmedia import (
     VoxMediaVolumeIE,
     VoxMediaIE,
 )
-from .vporn import VpornIE
 from .vrt import VRTIE
 from .vrak import VrakIE
 from .vrv import (
@@ -1400,7 +1408,7 @@ from .webofstories import (
     WebOfStoriesPlaylistIE,
 )
 from .weibo import (
-    WeiboIE, 
+    WeiboIE,
     WeiboMobileIE
 )
 from .weiqitv import WeiqiTVIE
@@ -1444,12 +1452,13 @@ from .yahoo import (
     YahooIE,
     YahooSearchIE,
 )
+from .yandexdisk import YandexDiskIE
 from .yandexmusic import (
     YandexMusicTrackIE,
     YandexMusicAlbumIE,
     YandexMusicPlaylistIE,
 )
-from .yandexdisk import YandexDiskIE
+from .yandexvideo import YandexVideoIE
 from .yapfiles import YapFilesIE
 from .yesjapan import YesJapanIE
 from .yinyuetai import YinYueTaiIE

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

@@ -6,10 +6,12 @@ import uuid
 
 from .adobepass import AdobePassIE
 from ..compat import (
+    compat_HTTPError,
     compat_str,
     compat_urllib_parse_unquote,
 )
 from ..utils import (
+    ExtractorError,
     int_or_none,
     parse_age_limit,
     parse_duration,
@@ -48,6 +50,7 @@ class FOXIE(AdobePassIE):
         'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
         'only_matching': True,
     }]
+    _GEO_BYPASS = False
     _HOME_PAGE_URL = 'https://www.fox.com/'
     _API_KEY = 'abdcbed02c124d393b39e818a4312055'
     _access_token = None
@@ -58,9 +61,22 @@ class FOXIE(AdobePassIE):
         }
         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)
+        try:
+            return self._download_json(
+                'https://api2.fox.com/v2.0/' + path,
+                video_id, data=data, headers=headers)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.status == 403:
+                entitlement_issues = self._parse_json(
+                    e.cause.read().decode(), video_id)['entitlementIssues']
+                for e in entitlement_issues:
+                    if e.get('errorCode') == 1005:
+                        raise ExtractorError(
+                            'This video is only available via cable service provider '
+                            'subscription. You may want to use --cookies.', expected=True)
+                messages = ', '.join([e['message'] for e in entitlement_issues])
+                raise ExtractorError(messages, expected=True)
+            raise
 
     def _real_initialize(self):
         if not self._access_token:
@@ -81,7 +97,15 @@ class FOXIE(AdobePassIE):
 
         title = video['name']
         release_url = video['url']
-        m3u8_url = self._download_json(release_url, video_id)['playURL']
+        try:
+            m3u8_url = self._download_json(release_url, video_id)['playURL']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.status == 403:
+                error = self._parse_json(e.cause.read().decode(), video_id)
+                if error.get('exception') == 'GeoLocationBlocked':
+                    self.raise_geo_restricted(countries=['US'])
+                raise ExtractorError(error['description'], expected=True)
+            raise
         formats = self._extract_m3u8_formats(
             m3u8_url, video_id, 'mp4',
             entry_protocol='m3u8_native', m3u8_id='hls')

youtube_dl/extractor/francetv.py

@@ -143,7 +143,7 @@ class FranceTVIE(InfoExtractor):
             ext = determine_ext(video_url)
             if ext == 'f4m':
                 if georestricted:
-                    # See https://github.com/rg3/youtube-dl/issues/3963
+                    # See https://github.com/ytdl-org/youtube-dl/issues/3963
                     # m3u8 urls work fine
                     continue
                 formats.extend(self._extract_f4m_formats(
@@ -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/gaia.py

@@ -4,12 +4,17 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_unquote,
+)
 from ..utils import (
+    ExtractorError,
     int_or_none,
     str_or_none,
     strip_or_none,
     try_get,
+    urlencode_postdata,
 )
 
 
@@ -46,6 +51,29 @@ class GaiaIE(InfoExtractor):
             'skip_download': True,
         },
     }]
+    _NETRC_MACHINE = 'gaia'
+    _jwt = None
+
+    def _real_initialize(self):
+        auth = self._get_cookies('https://www.gaia.com/').get('auth')
+        if auth:
+            auth = self._parse_json(
+                compat_urllib_parse_unquote(auth.value),
+                None, fatal=False)
+        if not auth:
+            username, password = self._get_login_info()
+            if username is None:
+                return
+            auth = self._download_json(
+                'https://auth.gaia.com/v1/login',
+                None, data=urlencode_postdata({
+                    'username': username,
+                    'password': password
+                }))
+            if auth.get('success') is False:
+                raise ExtractorError(', '.join(auth['messages']), expected=True)
+        if auth:
+            self._jwt = auth.get('jwt')
 
     def _real_extract(self, url):
         display_id, vtype = re.search(self._VALID_URL, url).groups()
@@ -59,8 +87,12 @@ class GaiaIE(InfoExtractor):
         media_id = compat_str(vdata['nid'])
         title = node['title']
 
+        headers = None
+        if self._jwt:
+            headers = {'Authorization': 'Bearer ' + self._jwt}
         media = self._download_json(
-            'https://brooklyn.gaia.com/media/' + media_id, media_id)
+            'https://brooklyn.gaia.com/media/' + media_id,
+            media_id, headers=headers)
         formats = self._extract_m3u8_formats(
             media['mediaUrls']['bcHLS'], media_id, 'mp4')
         self._sort_formats(formats)

youtube_dl/extractor/generic.py

@@ -430,7 +430,7 @@ class GenericIE(InfoExtractor):
             },
         },
         {
-            # https://github.com/rg3/youtube-dl/issues/2253
+            # https://github.com/ytdl-org/youtube-dl/issues/2253
             'url': 'http://bcove.me/i6nfkrc3',
             'md5': '0ba9446db037002366bab3b3eb30c88c',
             'info_dict': {
@@ -455,7 +455,7 @@ class GenericIE(InfoExtractor):
             },
         },
         {
-            # https://github.com/rg3/youtube-dl/issues/3541
+            # https://github.com/ytdl-org/youtube-dl/issues/3541
             'add_ie': ['BrightcoveLegacy'],
             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
             'info_dict': {
@@ -919,7 +919,7 @@ class GenericIE(InfoExtractor):
             }
         },
         # Multiple brightcove videos
-        # https://github.com/rg3/youtube-dl/issues/2283
+        # https://github.com/ytdl-org/youtube-dl/issues/2283
         {
             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
             'info_dict': {
@@ -2371,7 +2371,7 @@ class GenericIE(InfoExtractor):
             return camtasia_res
 
         # Sometimes embedded video player is hidden behind percent encoding
-        # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
+        # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
         # Unescaping the whole page allows to handle those cases in a generic way
         webpage = compat_urllib_parse_unquote(webpage)
 
@@ -3177,7 +3177,7 @@ class GenericIE(InfoExtractor):
                     jwplayer_data, video_id, require_title=False, base_url=url)
                 return merge_dicts(info, info_dict)
             except ExtractorError:
-                # See https://github.com/rg3/youtube-dl/pull/16735
+                # See https://github.com/ytdl-org/youtube-dl/pull/16735
                 pass
 
         # Video.js embed

youtube_dl/extractor/googledrive.py

@@ -36,7 +36,7 @@ class GoogleDriveIE(InfoExtractor):
         }
     }, {
         # video can't be watched anonymously due to view count limit reached,
-        # but can be downloaded (see https://github.com/rg3/youtube-dl/issues/14046)
+        # but can be downloaded (see https://github.com/ytdl-org/youtube-dl/issues/14046)
         'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
         'md5': 'bfbd670d03a470bb1e6d4a257adec12e',
         'info_dict': {

youtube_dl/extractor/hbo.py

@@ -4,16 +4,28 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     xpath_text,
     xpath_element,
     int_or_none,
     parse_duration,
+    urljoin,
 )
 
 
-class HBOBaseIE(InfoExtractor):
+class HBOIE(InfoExtractor):
+    IE_NAME = 'hbo'
+    _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?:video|embed)(?:/[^/]+)*/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'https://www.hbo.com/video/game-of-thrones/seasons/season-8/videos/trailer',
+        'md5': '8126210656f433c452a21367f9ad85b3',
+        'info_dict': {
+            'id': '22113301',
+            'ext': 'mp4',
+            'title': 'Game of Thrones - Trailer',
+        },
+        'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'],
+    }
     _FORMATS_INFO = {
         'pro7': {
             'width': 1280,
@@ -53,10 +65,17 @@ class HBOBaseIE(InfoExtractor):
         },
     }
 
-    def _extract_from_id(self, video_id):
-        video_data = self._download_xml(
-            'http://render.lv3.hbo.com/data/content/global/videos/data/%s.xml' % video_id, video_id)
-        title = xpath_text(video_data, 'title', 'title', True)
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        location_path = self._parse_json(self._html_search_regex(
+            r'data-state="({.+?})"', webpage, 'state'), display_id)['video']['locationUrl']
+        video_data = self._download_xml(urljoin(url, location_path), display_id)
+        video_id = xpath_text(video_data, 'id', fatal=True)
+        episode_title = title = xpath_text(video_data, 'title', fatal=True)
+        series = xpath_text(video_data, 'program')
+        if series:
+            title = '%s - %s' % (series, title)
 
         formats = []
         for source in xpath_element(video_data, 'videos', 'sources', True):
@@ -128,68 +147,23 @@ class HBOBaseIE(InfoExtractor):
                     'width': width,
                 })
 
+        subtitles = None
+        caption_url = xpath_text(video_data, 'captionUrl')
+        if caption_url:
+            subtitles = {
+                'en': [{
+                    'url': caption_url,
+                    'ext': 'ttml'
+                }],
+            }
+
         return {
             'id': video_id,
             'title': title,
             'duration': parse_duration(xpath_text(video_data, 'duration/tv14')),
+            'series': series,
+            'episode': episode_title,
             'formats': formats,
             'thumbnails': thumbnails,
+            'subtitles': subtitles,
         }
-
-
-class HBOIE(HBOBaseIE):
-    IE_NAME = 'hbo'
-    _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
-        'md5': '2c6a6bc1222c7e91cb3334dad1746e5a',
-        'info_dict': {
-            'id': '1437839',
-            'ext': 'mp4',
-            'title': 'Ep. 64 Clip: Encryption',
-            'thumbnail': r're:https?://.*\.jpg$',
-            'duration': 1072,
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        return self._extract_from_id(video_id)
-
-
-class HBOEpisodeIE(HBOBaseIE):
-    IE_NAME = 'hbo:episode'
-    _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?P<path>(?!video)(?:(?:[^/]+/)+video|watch-free-episodes)/(?P<id>[0-9a-z-]+))(?:\.html)?'
-
-    _TESTS = [{
-        'url': 'http://www.hbo.com/girls/episodes/5/52-i-love-you-baby/video/ep-52-inside-the-episode.html?autoplay=true',
-        'md5': '61ead79b9c0dfa8d3d4b07ef4ac556fb',
-        'info_dict': {
-            'id': '1439518',
-            'display_id': 'ep-52-inside-the-episode',
-            'ext': 'mp4',
-            'title': 'Ep. 52: Inside the Episode',
-            'thumbnail': r're:https?://.*\.jpg$',
-            'duration': 240,
-        },
-    }, {
-        'url': 'http://www.hbo.com/game-of-thrones/about/video/season-5-invitation-to-the-set.html?autoplay=true',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.hbo.com/watch-free-episodes/last-week-tonight-with-john-oliver',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        path, display_id = re.match(self._VALID_URL, url).groups()
-
-        content = self._download_json(
-            'http://www.hbo.com/api/content/' + path, display_id)['content']
-
-        video_id = compat_str((content.get('parsed', {}).get(
-            'common:FullBleedVideo', {}) or content['selectedEpisode'])['videoId'])
-
-        info_dict = self._extract_from_id(video_id)
-        info_dict['display_id'] = display_id
-
-        return info_dict

youtube_dl/extractor/hypem.py

@@ -1,18 +1,11 @@
 from __future__ import unicode_literals
 
-import json
-import time
-
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlencode
-from ..utils import (
-    ExtractorError,
-    sanitized_Request,
-)
+from ..utils import int_or_none
 
 
 class HypemIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/'
+    _VALID_URL = r'https?://(?:www\.)?hypem\.com/track/(?P<id>[0-9a-z]{5})'
     _TEST = {
         'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
         'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
@@ -21,41 +14,36 @@ class HypemIE(InfoExtractor):
             'ext': 'mp3',
             'title': 'Tame',
             'uploader': 'BODYWORK',
+            'timestamp': 1371810457,
+            'upload_date': '20130621',
         }
     }
 
     def _real_extract(self, url):
         track_id = self._match_id(url)
 
-        data = {'ax': 1, 'ts': time.time()}
-        request = sanitized_Request(url + '?' + compat_urllib_parse_urlencode(data))
-        response, urlh = self._download_webpage_handle(
-            request, track_id, 'Downloading webpage with the url')
+        response = self._download_webpage(url, track_id)
 
-        html_tracks = self._html_search_regex(
-            r'(?ms)<script type="application/json" id="displayList-data">(.+?)</script>',
-            response, 'tracks')
-        try:
-            track_list = json.loads(html_tracks)
-            track = track_list['tracks'][0]
-        except ValueError:
-            raise ExtractorError('Hypemachine contained invalid JSON.')
+        track = self._parse_json(self._html_search_regex(
+            r'(?s)<script\s+type="application/json"\s+id="displayList-data">(.+?)</script>',
+            response, 'tracks'), track_id)['tracks'][0]
 
-        key = track['key']
         track_id = track['id']
         title = track['song']
 
-        request = sanitized_Request(
-            'http://hypem.com/serve/source/%s/%s' % (track_id, key),
-            '', {'Content-Type': 'application/json'})
-        song_data = self._download_json(request, track_id, 'Downloading metadata')
-        final_url = song_data['url']
-        artist = track.get('artist')
+        final_url = self._download_json(
+            'http://hypem.com/serve/source/%s/%s' % (track_id, track['key']),
+            track_id, 'Downloading metadata', headers={
+                'Content-Type': 'application/json'
+            })['url']
 
         return {
             'id': track_id,
             'url': final_url,
             'ext': 'mp3',
             'title': title,
-            'uploader': artist,
+            'uploader': track.get('artist'),
+            'duration': int_or_none(track.get('time')),
+            'timestamp': int_or_none(track.get('ts')),
+            'track': title,
         }

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/ina.py

@@ -1,36 +1,83 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    strip_or_none,
+    xpath_attr,
+    xpath_text,
+)
 
 
 class InaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?ina\.fr/(?:video|audio)/(?P<id>[A-Z0-9_]+)'
+    _TESTS = [{
         'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
         'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
         'info_dict': {
             'id': 'I12055569',
             'ext': 'mp4',
             'title': 'François Hollande "Je crois que c\'est clair"',
+            'description': 'md5:3f09eb072a06cb286b8f7e4f77109663',
         }
-    }
+    }, {
+        'url': 'https://www.ina.fr/video/S806544_001/don-d-organes-des-avancees-mais-d-importants-besoins-video.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ina.fr/audio/P16173408',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ina.fr/video/P16173408-video.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
+        info_doc = self._download_xml(
+            'http://player.ina.fr/notices/%s.mrss' % video_id, video_id)
+        item = info_doc.find('channel/item')
+        title = xpath_text(item, 'title', fatal=True)
+        media_ns_xpath = lambda x: self._xpath_ns(x, 'http://search.yahoo.com/mrss/')
+        content = item.find(media_ns_xpath('content'))
 
-        video_id = mobj.group('id')
-        mrss_url = 'http://player.ina.fr/notices/%s.mrss' % video_id
-        info_doc = self._download_xml(mrss_url, video_id)
+        get_furl = lambda x: xpath_attr(content, media_ns_xpath(x), 'url')
+        formats = []
+        for q, w, h in (('bq', 400, 300), ('mq', 512, 384), ('hq', 768, 576)):
+            q_url = get_furl(q)
+            if not q_url:
+                continue
+            formats.append({
+                'format_id': q,
+                'url': q_url,
+                'width': w,
+                'height': h,
+            })
+        if not formats:
+            furl = get_furl('player') or content.attrib['url']
+            ext = determine_ext(furl)
+            formats = [{
+                'url': furl,
+                'vcodec': 'none' if ext == 'mp3' else None,
+                'ext': ext,
+            }]
 
-        self.report_extraction(video_id)
-
-        video_url = info_doc.find('.//{http://search.yahoo.com/mrss/}player').attrib['url']
+        thumbnails = []
+        for thumbnail in content.findall(media_ns_xpath('thumbnail')):
+            thumbnail_url = thumbnail.get('url')
+            if not thumbnail_url:
+                continue
+            thumbnails.append({
+                'url': thumbnail_url,
+                'height': int_or_none(thumbnail.get('height')),
+                'width': int_or_none(thumbnail.get('width')),
+            })
 
         return {
             'id': video_id,
-            'url': video_url,
-            'title': info_doc.find('.//title').text,
+            'formats': formats,
+            'title': title,
+            'description': strip_or_none(xpath_text(item, 'description')),
+            'thumbnails': thumbnails,
         }

youtube_dl/extractor/kuwo.py

@@ -215,7 +215,7 @@ class KuwoSingerIE(InfoExtractor):
             'title': 'Ali',
         },
         'playlist_mincount': 95,
-        'skip': 'Regularly stalls travis build',  # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
+        'skip': 'Regularly stalls travis build',  # See https://travis-ci.org/ytdl-org/youtube-dl/jobs/78878540
     }]
 
     PAGE_SIZE = 15

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

@@ -44,7 +44,7 @@ class LiveLeakIE(InfoExtractor):
         },
         'skip': 'Video is dead',
     }, {
-        # Covers https://github.com/rg3/youtube-dl/pull/5983
+        # Covers https://github.com/ytdl-org/youtube-dl/pull/5983
         # Multiple resolutions
         'url': 'http://www.liveleak.com/view?i=801_1409392012',
         'md5': 'c3a449dbaca5c0d1825caecd52a57d7b',
@@ -57,7 +57,7 @@ class LiveLeakIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.jpg$'
         }
     }, {
-        # Covers https://github.com/rg3/youtube-dl/pull/10664#issuecomment-247439521
+        # Covers https://github.com/ytdl-org/youtube-dl/pull/10664#issuecomment-247439521
         'url': 'http://m.liveleak.com/view?i=763_1473349649',
         'add_ie': ['Youtube'],
         'info_dict': {
@@ -130,7 +130,7 @@ class LiveLeakIE(InfoExtractor):
 
                 # 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)
+                # https://github.com/ytdl-org/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')

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/mediasite.py

@@ -13,6 +13,8 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     mimetype2ext,
+    str_or_none,
+    try_get,
     unescapeHTML,
     unsmuggle_url,
     url_or_none,
@@ -20,8 +22,11 @@ from ..utils import (
 )
 
 
+_ID_RE = r'(?:[0-9a-f]{32,34}|[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12,14})'
+
+
 class MediasiteIE(InfoExtractor):
-    _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/(?:default|livebroadcast)/Presentation)/(?P<id>[0-9a-f]{32,34})(?P<query>\?[^#]+|)'
+    _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/(?:default|livebroadcast)/Presentation)/(?P<id>%s)(?P<query>\?[^#]+|)' % _ID_RE
     _TESTS = [
         {
             'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d',
@@ -93,6 +98,11 @@ class MediasiteIE(InfoExtractor):
             'url': 'https://mediasite.ntnu.no/Mediasite/Showcase/default/Presentation/7d8b913259334b688986e970fae6fcb31d',
             'only_matching': True,
         },
+        {
+            # dashed id
+            'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271-681e-4f19-9af3-c60d1f82869b1d',
+            'only_matching': True,
+        }
     ]
 
     # look in Mediasite.Core.js (Mediasite.ContentStreamType[*])
@@ -109,7 +119,7 @@ class MediasiteIE(InfoExtractor):
         return [
             unescapeHTML(mobj.group('url'))
             for mobj in re.finditer(
-                r'(?xi)<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:(?:https?:)?//[^/]+)?/Mediasite/Play/[0-9a-f]{32,34}(?:\?.*?)?)\1',
+                r'(?xi)<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:(?:https?:)?//[^/]+)?/Mediasite/Play/%s(?:\?.*?)?)\1' % _ID_RE,
                 webpage)]
 
     def _real_extract(self, url):
@@ -221,3 +231,136 @@ class MediasiteIE(InfoExtractor):
             'formats': formats,
             'thumbnails': thumbnails,
         }
+
+
+class MediasiteCatalogIE(InfoExtractor):
+    _VALID_URL = r'''(?xi)
+                        (?P<url>https?://[^/]+/Mediasite)
+                        /Catalog/Full/
+                        (?P<catalog_id>{0})
+                        (?:
+                            /(?P<current_folder_id>{0})
+                            /(?P<root_dynamic_folder_id>{0})
+                        )?
+                    '''.format(_ID_RE)
+    _TESTS = [{
+        'url': 'http://events7.mediasite.com/Mediasite/Catalog/Full/631f9e48530d454381549f955d08c75e21',
+        'info_dict': {
+            'id': '631f9e48530d454381549f955d08c75e21',
+            'title': 'WCET Summit: Adaptive Learning in Higher Ed: Improving Outcomes Dynamically',
+        },
+        'playlist_count': 6,
+        'expected_warnings': ['is not a supported codec'],
+    }, {
+        # with CurrentFolderId and RootDynamicFolderId
+        'url': 'https://medaudio.medicine.iu.edu/Mediasite/Catalog/Full/9518c4a6c5cf4993b21cbd53e828a92521/97a9db45f7ab47428c77cd2ed74bb98f14/9518c4a6c5cf4993b21cbd53e828a92521',
+        'info_dict': {
+            'id': '9518c4a6c5cf4993b21cbd53e828a92521',
+            'title': 'IUSM Family and Friends Sessions',
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'http://uipsyc.mediasite.com/mediasite/Catalog/Full/d5d79287c75243c58c50fef50174ec1b21',
+        'only_matching': True,
+    }, {
+        # no AntiForgeryToken
+        'url': 'https://live.libraries.psu.edu/Mediasite/Catalog/Full/8376d4b24dd1457ea3bfe4cf9163feda21',
+        'only_matching': True,
+    }, {
+        'url': 'https://medaudio.medicine.iu.edu/Mediasite/Catalog/Full/9518c4a6c5cf4993b21cbd53e828a92521/97a9db45f7ab47428c77cd2ed74bb98f14/9518c4a6c5cf4993b21cbd53e828a92521',
+        'only_matching': True,
+    }, {
+        # dashed id
+        'url': 'http://events7.mediasite.com/Mediasite/Catalog/Full/631f9e48-530d-4543-8154-9f955d08c75e',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        mediasite_url = mobj.group('url')
+        catalog_id = mobj.group('catalog_id')
+        current_folder_id = mobj.group('current_folder_id') or catalog_id
+        root_dynamic_folder_id = mobj.group('root_dynamic_folder_id')
+
+        webpage = self._download_webpage(url, catalog_id)
+
+        # AntiForgeryToken is optional (e.g. [1])
+        # 1. https://live.libraries.psu.edu/Mediasite/Catalog/Full/8376d4b24dd1457ea3bfe4cf9163feda21
+        anti_forgery_token = self._search_regex(
+            r'AntiForgeryToken\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+            webpage, 'anti forgery token', default=None, group='value')
+        if anti_forgery_token:
+            anti_forgery_header = self._search_regex(
+                r'AntiForgeryHeaderName\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+                webpage, 'anti forgery header name',
+                default='X-SOFO-AntiForgeryHeader', group='value')
+
+        data = {
+            'IsViewPage': True,
+            'IsNewFolder': True,
+            'AuthTicket': None,
+            'CatalogId': catalog_id,
+            'CurrentFolderId': current_folder_id,
+            'RootDynamicFolderId': root_dynamic_folder_id,
+            'ItemsPerPage': 1000,
+            'PageIndex': 0,
+            'PermissionMask': 'Execute',
+            'CatalogSearchType': 'SearchInFolder',
+            'SortBy': 'Date',
+            'SortDirection': 'Descending',
+            'StartDate': None,
+            'EndDate': None,
+            'StatusFilterList': None,
+            'PreviewKey': None,
+            'Tags': [],
+        }
+
+        headers = {
+            'Content-Type': 'application/json; charset=UTF-8',
+            'Referer': url,
+            'X-Requested-With': 'XMLHttpRequest',
+        }
+        if anti_forgery_token:
+            headers[anti_forgery_header] = anti_forgery_token
+
+        catalog = self._download_json(
+            '%s/Catalog/Data/GetPresentationsForFolder' % mediasite_url,
+            catalog_id, data=json.dumps(data).encode(), headers=headers)
+
+        entries = []
+        for video in catalog['PresentationDetailsList']:
+            if not isinstance(video, dict):
+                continue
+            video_id = str_or_none(video.get('Id'))
+            if not video_id:
+                continue
+            entries.append(self.url_result(
+                '%s/Play/%s' % (mediasite_url, video_id),
+                ie=MediasiteIE.ie_key(), video_id=video_id))
+
+        title = try_get(
+            catalog, lambda x: x['CurrentFolder']['Name'], compat_str)
+
+        return self.playlist_result(entries, catalog_id, title,)
+
+
+class MediasiteNamedCatalogIE(InfoExtractor):
+    _VALID_URL = r'(?xi)(?P<url>https?://[^/]+/Mediasite)/Catalog/catalogs/(?P<catalog_name>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://msite.misis.ru/Mediasite/Catalog/catalogs/2016-industrial-management-skriabin-o-o',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        mediasite_url = mobj.group('url')
+        catalog_name = mobj.group('catalog_name')
+
+        webpage = self._download_webpage(url, catalog_name)
+
+        catalog_id = self._search_regex(
+            r'CatalogId\s*:\s*["\'](%s)' % _ID_RE, webpage, 'catalog id')
+
+        return self.url_result(
+            '%s/Catalog/Full/%s' % (mediasite_url, catalog_id),
+            ie=MediasiteCatalogIE.ie_key(), video_id=catalog_id)

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/moevideo.py

@@ -1,15 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
+    clean_html,
     int_or_none,
-    sanitized_Request,
-    urlencode_postdata,
 )
 
 
@@ -17,8 +14,8 @@ class MoeVideoIE(InfoExtractor):
     IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?
-        (?:(?:moevideo|playreplay|videochart)\.net))/
-        (?:video|framevideo)/(?P<id>[0-9]+\.[0-9A-Za-z]+)'''
+        (?:(?:moevideo|playreplay|videochart)\.net|thesame\.tv))/
+        (?:video|framevideo|embed)/(?P<id>[0-9a-z]+\.[0-9A-Za-z]+)'''
     _API_URL = 'http://api.letitbit.net/'
     _API_KEY = 'tVL0gjqo5'
     _TESTS = [
@@ -57,58 +54,26 @@ class MoeVideoIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        host, video_id = re.match(self._VALID_URL, url).groups()
 
         webpage = self._download_webpage(
-            'http://%s/video/%s' % (mobj.group('host'), video_id),
+            'http://%s/video/%s' % (host, video_id),
             video_id, 'Downloading webpage')
 
         title = self._og_search_title(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
-        description = self._og_search_description(webpage)
 
-        r = [
-            self._API_KEY,
-            [
-                'preview/flv_link',
-                {
-                    'uid': video_id,
-                },
-            ],
-        ]
-        r_json = json.dumps(r)
-        post = urlencode_postdata({'r': r_json})
-        req = sanitized_Request(self._API_URL, post)
-        req.add_header('Content-type', 'application/x-www-form-urlencoded')
-
-        response = self._download_json(req, video_id)
-        if response['status'] != 'OK':
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, response['data']),
-                expected=True
-            )
-        item = response['data'][0]
-        video_url = item['link']
-        duration = int_or_none(item['length'])
-        width = int_or_none(item['width'])
-        height = int_or_none(item['height'])
-        filesize = int_or_none(item['convert_size'])
-
-        formats = [{
-            'format_id': 'sd',
-            'http_headers': {'Range': 'bytes=0-'},  # Required to download
-            'url': video_url,
-            'width': width,
-            'height': height,
-            'filesize': filesize,
-        }]
+        embed_webpage = self._download_webpage(
+            'http://%s/embed/%s' % (host, video_id),
+            video_id, 'Downloading embed webpage')
+        video = self._parse_json(self._search_regex(
+            r'mvplayer\("#player"\s*,\s*({.+})',
+            embed_webpage, 'mvplayer'), video_id)['video']
 
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': thumbnail,
-            'description': description,
-            'duration': duration,
-            'formats': formats,
+            'thumbnail': video.get('poster') or self._og_search_thumbnail(webpage),
+            'description': clean_html(self._og_search_description(webpage)),
+            'duration': int_or_none(self._og_search_property('video:duration', webpage)),
+            'url': video['ourUrl'],
         }

youtube_dl/extractor/msn.py

@@ -70,7 +70,7 @@ class MSNIE(InfoExtractor):
                 continue
             if 'm3u8' in format_url:
                 # m3u8_native should not be used here until
-                # https://github.com/rg3/youtube-dl/issues/9913 is fixed
+                # https://github.com/ytdl-org/youtube-dl/issues/9913 is fixed
                 m3u8_formats = self._extract_m3u8_formats(
                     format_url, display_id, 'mp4',
                     m3u8_id='hls', fatal=False)

youtube_dl/extractor/newstube.py

@@ -1,12 +1,17 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
+import base64
+import hashlib
 
 from .common import InfoExtractor
+from ..aes import aes_cbc_decrypt
 from ..utils import (
-    ExtractorError,
+    bytes_to_intlist,
     int_or_none,
+    intlist_to_bytes,
+    parse_codecs,
+    parse_duration,
 )
 
 
@@ -14,7 +19,7 @@ class NewstubeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?newstube\.ru/media/(?P<id>.+)'
     _TEST = {
         'url': 'http://www.newstube.ru/media/telekanal-cnn-peremestil-gorod-slavyansk-v-krym',
-        'md5': '801eef0c2a9f4089fa04e4fe3533abdc',
+        'md5': '9d10320ad473444352f72f746ccb8b8c',
         'info_dict': {
             'id': '728e0ef2-e187-4012-bac0-5a081fdcb1f6',
             'ext': 'mp4',
@@ -25,84 +30,45 @@ class NewstubeIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
-        page = self._download_webpage(url, video_id, 'Downloading page')
+        page = self._download_webpage(url, video_id)
+        title = self._html_search_meta(['og:title', 'twitter:title'], page, fatal=True)
 
         video_guid = self._html_search_regex(
-            r'<meta property="og:video:url" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
+            r'<meta\s+property="og:video(?::(?:(?:secure_)?url|iframe))?"\s+content="https?://(?:www\.)?newstube\.ru/embed/(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
             page, 'video GUID')
 
-        player = self._download_xml(
-            'http://p.newstube.ru/v2/player.asmx/GetAutoPlayInfo6?state=&url=%s&sessionId=&id=%s&placement=profile&location=n2' % (url, video_guid),
-            video_guid, 'Downloading player XML')
-
-        def ns(s):
-            return s.replace('/', '/%(ns)s') % {'ns': '{http://app1.newstube.ru/N2SiteWS/player.asmx}'}
-
-        error_message = player.find(ns('./ErrorMessage'))
-        if error_message is not None:
-            raise ExtractorError('%s returned error: %s' % (self.IE_NAME, error_message.text), expected=True)
-
-        session_id = player.find(ns('./SessionId')).text
-        media_info = player.find(ns('./Medias/MediaInfo'))
-        title = media_info.find(ns('./Name')).text
-        description = self._og_search_description(page)
-        thumbnail = media_info.find(ns('./KeyFrame')).text
-        duration = int(media_info.find(ns('./Duration')).text) / 1000.0
+        enc_data = base64.b64decode(self._download_webpage(
+            'https://www.newstube.ru/embed/api/player/getsources2',
+            video_guid, query={
+                'guid': video_guid,
+                'ff': 3,
+            }))
+        key = hashlib.pbkdf2_hmac(
+            'sha1', video_guid.replace('-', '').encode(), enc_data[:16], 1)[:16]
+        dec_data = aes_cbc_decrypt(
+            bytes_to_intlist(enc_data[32:]), bytes_to_intlist(key),
+            bytes_to_intlist(enc_data[16:32]))
+        sources = self._parse_json(intlist_to_bytes(dec_data[:-dec_data[-1]]), video_guid)
 
         formats = []
-
-        for stream_info in media_info.findall(ns('./Streams/StreamInfo')):
-            media_location = stream_info.find(ns('./MediaLocation'))
-            if media_location is None:
+        for source in sources:
+            source_url = source.get('Src')
+            if not source_url:
                 continue
-
-            server = media_location.find(ns('./Server')).text
-            app = media_location.find(ns('./App')).text
-            media_id = stream_info.find(ns('./Id')).text
-            name = stream_info.find(ns('./Name')).text
-            width = int(stream_info.find(ns('./Width')).text)
-            height = int(stream_info.find(ns('./Height')).text)
-
-            formats.append({
-                'url': 'rtmp://%s/%s' % (server, app),
-                'app': app,
-                'play_path': '01/%s' % video_guid.upper(),
-                'rtmp_conn': ['S:%s' % session_id, 'S:%s' % media_id, 'S:n2'],
-                'page_url': url,
-                'ext': 'flv',
-                'format_id': 'rtmp' + ('-%s' % name if name else ''),
-                'width': width,
+            height = int_or_none(source.get('Height'))
+            f = {
+                'format_id': 'http' + ('-%dp' % height if height else ''),
+                'url': source_url,
+                'width': int_or_none(source.get('Width')),
                 'height': height,
-            })
-
-        sources_data = self._download_json(
-            'http://www.newstube.ru/player2/getsources?guid=%s' % video_guid,
-            video_guid, fatal=False)
-        if sources_data:
-            for source in sources_data.get('Sources', []):
-                source_url = source.get('Src')
-                if not source_url:
-                    continue
-                height = int_or_none(source.get('Height'))
-                f = {
-                    'format_id': 'http' + ('-%dp' % height if height else ''),
-                    'url': source_url,
-                    'width': int_or_none(source.get('Width')),
-                    'height': height,
-                }
-                source_type = source.get('Type')
-                if source_type:
-                    mobj = re.search(r'codecs="([^,]+),\s*([^"]+)"', source_type)
-                    if mobj:
-                        vcodec, acodec = mobj.groups()
-                        f.update({
-                            'vcodec': vcodec,
-                            'acodec': acodec,
-                        })
-                formats.append(f)
+            }
+            source_type = source.get('Type')
+            if source_type:
+                f.update(parse_codecs(self._search_regex(
+                    r'codecs="([^"]+)"', source_type, 'codecs', fatal=False)))
+            formats.append(f)
 
         self._check_formats(formats, video_guid)
         self._sort_formats(formats)
@@ -110,8 +76,8 @@ class NewstubeIE(InfoExtractor):
         return {
             'id': video_guid,
             'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
+            'description': self._html_search_meta(['description', 'og:description'], page),
+            'thumbnail': self._html_search_meta(['og:image:secure_url', 'og:image', 'twitter:image'], page),
+            'duration': parse_duration(self._html_search_meta('duration', page)),
             'formats': formats,
         }

youtube_dl/extractor/nhl.py

@@ -108,7 +108,7 @@ class NHLIE(NHLBaseIE):
             'timestamp': 1454544904,
         },
     }, {
-        # Some m3u8 URLs are invalid (https://github.com/rg3/youtube-dl/issues/10713)
+        # Some m3u8 URLs are invalid (https://github.com/ytdl-org/youtube-dl/issues/10713)
         'url': 'https://www.nhl.com/predators/video/poile-laviolette-on-subban-trade/t-277437416/c-44315003',
         'md5': '50b2bb47f405121484dda3ccbea25459',
         'info_dict': {

youtube_dl/extractor/noco.py

@@ -115,7 +115,7 @@ class NocoIE(InfoExtractor):
 
         # Timestamp adjustment offset between server time and local time
         # must be calculated in order to use timestamps closest to server's
-        # in all API requests (see https://github.com/rg3/youtube-dl/issues/7864)
+        # in all API requests (see https://github.com/ytdl-org/youtube-dl/issues/7864)
         webpage = self._download_webpage(url, video_id)
 
         player_url = self._search_regex(

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 +181,122 @@ class NPOIE(NPOBaseIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        return self._get_info(video_id)
+        return self._get_info(url, video_id) or 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']
+
+        drm = False
+        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 or stream.get('keySystemOptions') is not None:
+                drm = True
+                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,
+                })
+
+        if not formats:
+            if drm:
+                raise ExtractorError('This video is DRM protected.', expected=True)
+            return
+
+        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 +398,7 @@ 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':

youtube_dl/extractor/npr.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlencode
 from ..utils import (
     int_or_none,
     qualities,
@@ -9,16 +8,16 @@ from ..utils import (
 
 
 class NprIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?npr\.org/player/v2/mediaPlayer\.html\?.*\bid=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?npr\.org/(?:sections/[^/]+/)?\d{4}/\d{2}/\d{2}/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://www.npr.org/player/v2/mediaPlayer.html?id=449974205',
+        'url': 'https://www.npr.org/sections/allsongs/2015/10/21/449974205/new-music-from-beach-house-chairlift-cmj-discoveries-and-more',
         'info_dict': {
             'id': '449974205',
             'title': 'New Music From Beach House, Chairlift, CMJ Discoveries And More'
         },
         'playlist_count': 7,
     }, {
-        'url': 'http://www.npr.org/player/v2/mediaPlayer.html?action=1&t=1&islist=false&id=446928052&m=446929930&live=1',
+        'url': 'https://www.npr.org/sections/deceptivecadence/2015/10/09/446928052/music-from-the-shadows-ancient-armenian-hymns-and-piano-jazz',
         'info_dict': {
             'id': '446928052',
             'title': "Songs We Love: Tigran Hamasyan, 'Your Mercy is Boundless'"
@@ -32,30 +31,46 @@ class NprIE(InfoExtractor):
                 'duration': 402,
             },
         }],
+    }, {
+        # mutlimedia, not media title
+        'url': 'https://www.npr.org/2017/06/19/533198237/tigers-jaw-tiny-desk-concert',
+        'info_dict': {
+            'id': '533198237',
+            'title': 'Tigers Jaw: Tiny Desk Concert',
+        },
+        'playlist': [{
+            'md5': '12fa60cb2d3ed932f53609d4aeceabf1',
+            'info_dict': {
+                'id': '533201718',
+                'ext': 'mp4',
+                'title': 'Tigers Jaw: Tiny Desk Concert',
+                'duration': 402,
+            },
+        }],
+        'expected_warnings': ['Failed to download m3u8 information'],
     }]
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
-        config = self._download_json(
-            'http://api.npr.org/query?%s' % compat_urllib_parse_urlencode({
+        story = self._download_json(
+            'http://api.npr.org/query', playlist_id, query={
                 'id': playlist_id,
-                'fields': 'titles,audio,show',
+                'fields': 'audio,multimedia,title',
                 'format': 'json',
                 'apiKey': 'MDAzMzQ2MjAyMDEyMzk4MTU1MDg3ZmM3MQ010',
-            }), playlist_id)
+            })['list']['story'][0]
+        playlist_title = story.get('title', {}).get('$text')
 
-        story = config['list']['story'][0]
-
-        KNOWN_FORMATS = ('threegp', 'mp4', 'mp3')
+        KNOWN_FORMATS = ('threegp', 'm3u8', 'smil', 'mp4', 'mp3')
         quality = qualities(KNOWN_FORMATS)
 
         entries = []
-        for audio in story.get('audio', []):
-            title = audio.get('title', {}).get('$text')
-            duration = int_or_none(audio.get('duration', {}).get('$text'))
+        for media in story.get('audio', []) + story.get('multimedia', []):
+            media_id = media['id']
+
             formats = []
-            for format_id, formats_entry in audio.get('format', {}).items():
+            for format_id, formats_entry in media.get('format', {}).items():
                 if not formats_entry:
                     continue
                 if isinstance(formats_entry, list):
@@ -64,19 +79,30 @@ class NprIE(InfoExtractor):
                 if not format_url:
                     continue
                 if format_id in KNOWN_FORMATS:
-                    formats.append({
-                        'url': format_url,
-                        'format_id': format_id,
-                        'ext': formats_entry.get('type'),
-                        'quality': quality(format_id),
-                    })
+                    if format_id == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            format_url, media_id, 'mp4', 'm3u8_native',
+                            m3u8_id='hls', fatal=False))
+                    elif format_id == 'smil':
+                        smil_formats = self._extract_smil_formats(
+                            format_url, media_id, transform_source=lambda s: s.replace(
+                                'rtmp://flash.npr.org/ondemand/', 'https://ondemand.npr.org/'))
+                        self._check_formats(smil_formats, media_id)
+                        formats.extend(smil_formats)
+                    else:
+                        formats.append({
+                            'url': format_url,
+                            'format_id': format_id,
+                            'quality': quality(format_id),
+                        })
             self._sort_formats(formats)
+
             entries.append({
-                'id': audio['id'],
-                'title': title,
-                'duration': duration,
+                'id': media_id,
+                'title': media.get('title', {}).get('$text') or playlist_title,
+                'thumbnail': media.get('altImageUrl', {}).get('$text'),
+                'duration': int_or_none(media.get('duration', {}).get('$text')),
                 'formats': formats,
             })
 
-        playlist_title = story.get('title', {}).get('$text')
         return self.playlist_result(entries, playlist_id, playlist_title)

youtube_dl/extractor/once.py

@@ -21,7 +21,7 @@ class OnceIE(InfoExtractor):
         progressive_formats = []
         for adaptive_format in formats:
             # Prevent advertisement from embedding into m3u8 playlist (see
-            # https://github.com/rg3/youtube-dl/issues/8893#issuecomment-199912684)
+            # https://github.com/ytdl-org/youtube-dl/issues/8893#issuecomment-199912684)
             adaptive_format['url'] = re.sub(
                 r'\badsegmentlength=\d+', r'adsegmentlength=0', adaptive_format['url'])
             rendition_id = self._search_regex(

youtube_dl/extractor/openload.py

@@ -243,18 +243,16 @@ class PhantomJSwrapper(object):
 
 
 class OpenloadIE(InfoExtractor):
+    _DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space))'
     _VALID_URL = r'''(?x)
                     https?://
                         (?P<host>
                             (?:www\.)?
-                            (?:
-                                openload\.(?:co|io|link)|
-                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club)
-                            )
+                            %s
                         )/
                         (?:f|embed)/
                         (?P<id>[a-zA-Z0-9-_]+)
-                    '''
+                    ''' % _DOMAINS
 
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -337,6 +335,21 @@ class OpenloadIE(InfoExtractor):
     }, {
         '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'
@@ -344,8 +357,8 @@ class OpenloadIE(InfoExtractor):
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
-            webpage)
+            r'<iframe[^>]+src=["\']((?:https?://)?%s/embed/[a-zA-Z0-9-_]+)'
+            % OpenloadIE._DOMAINS, webpage)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/orf.py

@@ -176,7 +176,8 @@ class ORFRadioIE(InfoExtractor):
                 'description': subtitle,
                 'duration': (info['end'] - info['start']) / 1000,
                 'timestamp': info['start'] / 1000,
-                'ext': 'mp3'
+                'ext': 'mp3',
+                'series': data.get('programTitle')
             }
 
         entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]

youtube_dl/extractor/pandatv.py

@@ -36,7 +36,7 @@ class PandaTVIE(InfoExtractor):
             'https://www.panda.tv/api_room_v2?roomid=%s' % video_id, video_id)
 
         error_code = config.get('errno', 0)
-        if error_code is not 0:
+        if error_code != 0:
             raise ExtractorError(
                 '%s returned error %s: %s'
                 % (self.IE_NAME, error_code, config['errmsg']),

youtube_dl/extractor/pbs.py

@@ -305,7 +305,7 @@ class PBSIE(InfoExtractor):
         {
             # Video embedded in iframe containing angle brackets as attribute's value (e.g.
             # "<iframe style='position: absolute;<br />\ntop: 0; left: 0;' ...", see
-            # https://github.com/rg3/youtube-dl/issues/7059)
+            # https://github.com/ytdl-org/youtube-dl/issues/7059)
             'url': 'http://www.pbs.org/food/features/a-chefs-life-season-3-episode-5-prickly-business/',
             'md5': '59b0ef5009f9ac8a319cc5efebcd865e',
             'info_dict': {
@@ -348,7 +348,7 @@ class PBSIE(InfoExtractor):
             },
         },
         {
-            # https://github.com/rg3/youtube-dl/issues/13801
+            # https://github.com/ytdl-org/youtube-dl/issues/13801
             'url': 'https://www.pbs.org/video/pbs-newshour-full-episode-july-31-2017-1501539057/',
             'info_dict': {
                 'id': '3003333873',
@@ -642,7 +642,7 @@ class PBSIE(InfoExtractor):
                 # we won't try extracting them.
                 # Since summer 2016 higher quality formats (4500k and 6500k) are also available
                 # albeit they are not documented in [2].
-                # 1. https://github.com/rg3/youtube-dl/commit/cbc032c8b70a038a69259378c92b4ba97b42d491#commitcomment-17313656
+                # 1. https://github.com/ytdl-org/youtube-dl/commit/cbc032c8b70a038a69259378c92b4ba97b42d491#commitcomment-17313656
                 # 2. https://projects.pbs.org/confluence/display/coveapi/COVE+Video+Specifications
                 if not bitrate or int(bitrate) < 400:
                     continue

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/platzi.py

@@ -0,0 +1,217 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_b64decode,
+    compat_str,
+)
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    int_or_none,
+    str_or_none,
+    try_get,
+    url_or_none,
+    urlencode_postdata,
+    urljoin,
+)
+
+
+class PlatziIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            platzi\.com/clases|           # es version
+                            courses\.platzi\.com/classes  # en version
+                        )/[^/]+/(?P<id>\d+)-[^/?\#&]+
+                    '''
+    _LOGIN_URL = 'https://platzi.com/login/'
+    _NETRC_MACHINE = 'platzi'
+
+    _TESTS = [{
+        'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/',
+        'md5': '8f56448241005b561c10f11a595b37e3',
+        'info_dict': {
+            'id': '12074',
+            'ext': 'mp4',
+            'title': 'Creando nuestra primera página',
+            'description': 'md5:4c866e45034fc76412fbf6e60ae008bc',
+            'duration': 420,
+        },
+        'skip': 'Requires platzi account credentials',
+    }, {
+        'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/',
+        'info_dict': {
+            'id': '13430',
+            'ext': 'mp4',
+            'title': 'Background',
+            'description': 'md5:49c83c09404b15e6e71defaf87f6b305',
+            'duration': 360,
+        },
+        'skip': 'Requires platzi account credentials',
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        username, password = self._get_login_info()
+        if username is None:
+            return
+
+        login_page = self._download_webpage(
+            self._LOGIN_URL, None, 'Downloading login page')
+
+        login_form = self._hidden_inputs(login_page)
+
+        login_form.update({
+            'email': username,
+            'password': password,
+        })
+
+        urlh = self._request_webpage(
+            self._LOGIN_URL, None, 'Logging in',
+            data=urlencode_postdata(login_form),
+            headers={'Referer': self._LOGIN_URL})
+
+        # login succeeded
+        if 'platzi.com/login' not in compat_str(urlh.geturl()):
+            return
+
+        login_error = self._webpage_read_content(
+            urlh, self._LOGIN_URL, None, 'Downloading login error page')
+
+        login = self._parse_json(
+            self._search_regex(
+                r'login\s*=\s*({.+?})(?:\s*;|\s*</script)', login_error, 'login'),
+            None)
+
+        for kind in ('error', 'password', 'nonFields'):
+            error = str_or_none(login.get('%sError' % kind))
+            if error:
+                raise ExtractorError(
+                    'Unable to login: %s' % error, expected=True)
+        raise ExtractorError('Unable to log in')
+
+    def _real_extract(self, url):
+        lecture_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, lecture_id)
+
+        data = self._parse_json(
+            self._search_regex(
+                r'client_data\s*=\s*({.+?})\s*;', webpage, 'client data'),
+            lecture_id)
+
+        material = data['initialState']['material']
+        desc = material['description']
+        title = desc['title']
+
+        formats = []
+        for server_id, server in material['videos'].items():
+            if not isinstance(server, dict):
+                continue
+            for format_id in ('hls', 'dash'):
+                format_url = url_or_none(server.get(format_id))
+                if not format_url:
+                    continue
+                if format_id == 'hls':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, lecture_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id=format_id,
+                        note='Downloading %s m3u8 information' % server_id,
+                        fatal=False))
+                elif format_id == 'dash':
+                    formats.extend(self._extract_mpd_formats(
+                        format_url, lecture_id, mpd_id=format_id,
+                        note='Downloading %s MPD manifest' % server_id,
+                        fatal=False))
+        self._sort_formats(formats)
+
+        content = str_or_none(desc.get('content'))
+        description = (clean_html(compat_b64decode(content).decode('utf-8'))
+                       if content else None)
+        duration = int_or_none(material.get('duration'), invscale=60)
+
+        return {
+            'id': lecture_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+        }
+
+
+class PlatziCourseIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            platzi\.com/clases|           # es version
+                            courses\.platzi\.com/classes  # en version
+                        )/(?P<id>[^/?\#&]+)
+                    '''
+    _TESTS = [{
+        'url': 'https://platzi.com/clases/next-js/',
+        'info_dict': {
+            'id': '1311',
+            'title': 'Curso de Next.js',
+        },
+        'playlist_count': 22,
+    }, {
+        'url': 'https://courses.platzi.com/classes/communication-codestream/',
+        'info_dict': {
+            'id': '1367',
+            'title': 'Codestream Course',
+        },
+        'playlist_count': 14,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PlatziIE.suitable(url) else super(PlatziCourseIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        course_name = self._match_id(url)
+
+        webpage = self._download_webpage(url, course_name)
+
+        props = self._parse_json(
+            self._search_regex(r'data\s*=\s*({.+?})\s*;', webpage, 'data'),
+            course_name)['initialProps']
+
+        entries = []
+        for chapter_num, chapter in enumerate(props['concepts'], 1):
+            if not isinstance(chapter, dict):
+                continue
+            materials = chapter.get('materials')
+            if not materials or not isinstance(materials, list):
+                continue
+            chapter_title = chapter.get('title')
+            chapter_id = str_or_none(chapter.get('id'))
+            for material in materials:
+                if not isinstance(material, dict):
+                    continue
+                if material.get('material_type') != 'video':
+                    continue
+                video_url = urljoin(url, material.get('url'))
+                if not video_url:
+                    continue
+                entries.append({
+                    '_type': 'url_transparent',
+                    'url': video_url,
+                    'title': str_or_none(material.get('name')),
+                    'id': str_or_none(material.get('id')),
+                    'ie_key': PlatziIE.ie_key(),
+                    'chapter': chapter_title,
+                    'chapter_number': chapter_num,
+                    'chapter_id': chapter_id,
+                })
+
+        course_id = compat_str(try_get(props, lambda x: x['course']['id']))
+        course_title = try_get(props, lambda x: x['course']['name'], compat_str)
+
+        return self.playlist_result(entries, course_id, course_title)

youtube_dl/extractor/pluralsight.py

@@ -327,7 +327,7 @@ query viewClip {
         )
 
         # Some courses also offer widescreen resolution for high quality (see
-        # https://github.com/rg3/youtube-dl/issues/7766)
+        # https://github.com/ytdl-org/youtube-dl/issues/7766)
         widescreen = course.get('supportsWideScreenVideoFormats') is True
         best_quality = 'high-widescreen' if widescreen else 'high'
         if widescreen:
@@ -388,8 +388,8 @@ query viewClip {
 
                 # Pluralsight tracks multiple sequential calls to ViewClip API and start
                 # to return 429 HTTP errors after some time (see
-                # https://github.com/rg3/youtube-dl/pull/6989). Moreover it may even lead
-                # to account ban (see https://github.com/rg3/youtube-dl/issues/6842).
+                # https://github.com/ytdl-org/youtube-dl/pull/6989). Moreover it may even lead
+                # to account ban (see https://github.com/ytdl-org/youtube-dl/issues/6842).
                 # To somewhat reduce the probability of these consequences
                 # we will sleep random amount of time before each call to ViewClip.
                 self._sleep(

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

@@ -14,9 +14,9 @@ from ..compat import (
 )
 from .openload import PhantomJSwrapper
 from ..utils import (
+    determine_ext,
     ExtractorError,
     int_or_none,
-    js_to_json,
     orderedSet,
     remove_quotes,
     str_to_int,
@@ -276,6 +276,10 @@ class PornHubIE(PornHubBaseIE):
                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
                 if upload_date:
                     upload_date = upload_date.replace('/', '')
+            if determine_ext(video_url) == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    video_url, video_id, mpd_id='dash', fatal=False))
+                continue
             tbr = None
             mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
             if mobj:
@@ -303,14 +307,12 @@ class PornHubIE(PornHubBaseIE):
         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,
@@ -325,8 +327,8 @@ class PornHubIE(PornHubBaseIE):
             'comment_count': comment_count,
             'formats': formats,
             'age_limit': 18,
-            'tags': tags,
-            'categories': categories,
+            'tags': extract_list('tags'),
+            'categories': extract_list('categories'),
             'subtitles': subtitles,
         }
 
@@ -335,7 +337,7 @@ 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
-        # https://github.com/rg3/youtube-dl/issues/11594).
+        # https://github.com/ytdl-org/youtube-dl/issues/11594).
         container = self._search_regex(
             r'(?s)(<div[^>]+class=["\']container.+)', webpage,
             'container', default=webpage)

youtube_dl/extractor/primesharetv.py

@@ -1,62 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    sanitized_Request,
-    urlencode_postdata,
-)
-
-
-class PrimeShareTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P<id>[\da-zA-Z]+)'
-
-    _TEST = {
-        'url': 'http://primeshare.tv/download/238790B611',
-        'md5': 'b92d9bf5461137c36228009f31533fbc',
-        'info_dict': {
-            'id': '238790B611',
-            'ext': 'mp4',
-            'title': 'Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        if '>File not exist<' in webpage:
-            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
-
-        fields = self._hidden_inputs(webpage)
-
-        headers = {
-            'Referer': url,
-            'Content-Type': 'application/x-www-form-urlencoded',
-        }
-
-        wait_time = int(self._search_regex(
-            r'var\s+cWaitTime\s*=\s*(\d+)',
-            webpage, 'wait time', default=7)) + 1
-        self._sleep(wait_time, video_id)
-
-        req = sanitized_Request(
-            url, urlencode_postdata(fields), headers)
-        video_page = self._download_webpage(
-            req, video_id, 'Downloading video page')
-
-        video_url = self._search_regex(
-            r"url\s*:\s*'([^']+\.primeshare\.tv(?::443)?/file/[^']+)'",
-            video_page, 'video url')
-
-        title = self._html_search_regex(
-            r'<h1>Watch\s*(?:&nbsp;)?\s*\((.+?)(?:\s*\[\.\.\.\])?\)\s*(?:&nbsp;)?\s*<strong>',
-            video_page, 'title')
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': title,
-            'ext': 'mp4',
-        }

youtube_dl/extractor/prosiebensat1.py

@@ -140,8 +140,8 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
 
     _TESTS = [
         {
-            # Tests changes introduced in https://github.com/rg3/youtube-dl/pull/6242
-            # in response to fixing https://github.com/rg3/youtube-dl/issues/6215:
+            # Tests changes introduced in https://github.com/ytdl-org/youtube-dl/pull/6242
+            # in response to fixing https://github.com/ytdl-org/youtube-dl/issues/6215:
             # - malformed f4m manifest support
             # - proper handling of URLs starting with `https?://` in 2.0 manifests
             # - recursive child f4m manifests extraction

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,
 )
 
 
@@ -61,107 +57,67 @@ class RadioCanadaIE(InfoExtractor):
             '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).
+        # https://github.com/ytdl-org/youtube-dl/pull/18609).
         if get_meta('protectionType'):
             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 = {}
@@ -186,11 +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 = {
+    IE_NAME = 'radiocanada:audiovideo'
+    _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',
@@ -203,7 +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):