release 2020.07.28

[ci skip]

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.05.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.07.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2020.05.03**
+- [ ] I've verified that I'm running youtube-dl version **2020.07.28**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.05.03
+ [debug] youtube-dl version 2020.07.28
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.05.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.07.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2020.05.03**
+- [ ] I've verified that I'm running youtube-dl version **2020.07.28**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.05.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.07.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.05.03**
+- [ ] I've verified that I'm running youtube-dl version **2020.07.28**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.05.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.07.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2020.05.03**
+- [ ] I've verified that I'm running youtube-dl version **2020.07.28**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.05.03
+ [debug] youtube-dl version 2020.07.28
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.05.03. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.07.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.05.03**
+- [ ] I've verified that I'm running youtube-dl version **2020.07.28**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

CONTRIBUTING.md

@@ -153,7 +153,7 @@ After you have ensured this site is distributing its content legally, you can fo
 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
-8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart):
+8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://flake8.pycqa.org/en/latest/index.html#quickstart):
 
         $ flake8 youtube_dl/extractor/yourextractor.py
 

ChangeLog

@@ -1,3 +1,96 @@
+version 2020.07.28
+
+Extractors
+* [youtube] Fix sigfunc name extraction (#26134, #26135, #26136, #26137)
+* [youtube] Improve description extraction (#25937, #25980)
+* [wistia] Restrict embed regular expression (#25969)
+* [youtube] Prevent excess HTTP 301 (#25786)
++ [youtube:playlists] Extend URL regular expression (#25810)
++ [bellmedia] Add support for cp24.com clip URLs (#25764)
+* [brightcove] Improve embed detection (#25674)
+
+
+version 2020.06.16.1
+
+Extractors
+* [youtube] Force old layout (#25682, #25683, #25680, #25686)
+* [youtube] Fix categories and improve tags extraction
+
+
+version 2020.06.16
+
+Extractors
+* [youtube] Fix uploader id and uploader URL extraction
+* [youtube] Improve view count extraction
+* [youtube] Fix upload date extraction (#25677)
+* [youtube] Fix thumbnails extraction (#25676)
+* [youtube] Fix playlist and feed extraction (#25675)
++ [facebook] Add support for single-video ID links
++ [youtube] Extract chapters from JSON (#24819)
++ [kaltura] Add support for multiple embeds on a webpage (#25523)
+
+
+version 2020.06.06
+
+Extractors
+* [tele5] Bypass geo restriction
++ [jwplatform] Add support for bypass geo restriction
+* [tele5] Prefer jwplatform over nexx (#25533)
+* [twitch:stream] Expect 400 and 410 HTTP errors from API
+* [twitch:stream] Fix extraction (#25528)
+* [twitch] Fix thumbnails extraction (#25531)
++ [twitch] Pass v5 Accept HTTP header (#25531)
+* [brightcove] Fix subtitles extraction (#25540)
++ [malltv] Add support for sk.mall.tv (#25445)
+* [periscope] Fix untitled broadcasts (#25482)
+* [jwplatform] Improve embeds extraction (#25467)
+
+
+version 2020.05.29
+
+Core
+* [postprocessor/ffmpeg] Embed series metadata with --add-metadata
+* [utils] Fix file permissions in write_json_file (#12471, #25122)
+
+Extractors
+* [ard:beta] Extend URL regular expression (#25405)
++ [youtube] Add support for more invidious instances (#25417)
+* [giantbomb] Extend URL regular expression (#25222)
+* [ard] Improve URL regular expression (#25134, #25198)
+* [redtube] Improve formats extraction and extract m3u8 formats (#25311,
+  #25321)
+* [indavideo] Switch to HTTPS for API request (#25191)
+* [redtube] Improve title extraction (#25208)
+* [vimeo] Improve format extraction and sorting (#25285)
+* [soundcloud] Reduce API playlist page limit (#25274)
++ [youtube] Add support for yewtu.be (#25226)
+* [mailru] Fix extraction (#24530, #25239)
+* [bellator] Fix mgid extraction (#25195)
+
+
+version 2020.05.08
+
+Core
+* [downloader/http] Request last data block of exact remaining size
+* [downloader/http] Finish downloading once received data length matches
+  expected
+* [extractor/common] Use compat_cookiejar_Cookie for _set_cookie to always
+  ensure cookie name and value are bytestrings on python 2 (#23256, #24776)
++ [compat] Introduce compat_cookiejar_Cookie
+* [utils] Improve cookie files support
+    + Add support for UTF-8 in cookie files
+    * Skip malformed cookie file entries instead of crashing (invalid entry
+      length, invalid expires at)
+
+Extractors
+* [youtube] Improve signature cipher extraction (#25187, #25188)
+* [iprima] Improve extraction (#25138)
+* [uol] Fix extraction (#22007)
++ [orf] Add support for more radio stations (#24938, #24968)
+* [dailymotion] Fix typo
+- [puhutv] Remove no longer available HTTP formats (#25124)
+
+
 version 2020.05.03
 
 Core

README.md

@@ -1032,7 +1032,7 @@ After you have ensured this site is distributing its content legally, you can fo
 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
-8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart):
+8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://flake8.pycqa.org/en/latest/index.html#quickstart):
 
         $ flake8 youtube_dl/extractor/yourextractor.py
 

docs/supportedsites.md

@@ -620,11 +620,21 @@
  - **Ooyala**
  - **OoyalaExternal**
  - **OraTV**
+ - **orf:burgenland**: Radio Burgenland
  - **orf:fm4**: radio FM4
  - **orf:fm4:story**: fm4.orf.at stories
  - **orf:iptv**: iptv.ORF.at
+ - **orf:kaernten**: Radio Kärnten
+ - **orf:noe**: Radio Niederösterreich
+ - **orf:oberoesterreich**: Radio Oberösterreich
  - **orf:oe1**: Radio Österreich 1
+ - **orf:oe3**: Radio Österreich 3
+ - **orf:salzburg**: Radio Salzburg
+ - **orf:steiermark**: Radio Steiermark
+ - **orf:tirol**: Radio Tirol
  - **orf:tvthek**: ORF TVthek
+ - **orf:vorarlberg**: Radio Vorarlberg
+ - **orf:wien**: Radio Wien
  - **OsnatelTV**
  - **OutsideTV**
  - **PacktPub**

test/test_YoutubeDLCookieJar.py

@@ -39,6 +39,13 @@ class TestYoutubeDLCookieJar(unittest.TestCase):
         assert_cookie_has_value('HTTPONLY_COOKIE')
         assert_cookie_has_value('JS_ACCESSIBLE_COOKIE')
 
+    def test_malformed_cookies(self):
+        cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/malformed_cookies.txt')
+        cookiejar.load(ignore_discard=True, ignore_expires=True)
+        # Cookies should be empty since all malformed cookie file entries
+        # will be ignored
+        self.assertFalse(cookiejar._cookies)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_chapters.py

@@ -267,7 +267,7 @@ class TestYoutubeChapters(unittest.TestCase):
         for description, duration, expected_chapters in self._TEST_CASES:
             ie = YoutubeIE()
             expect_value(
-                self, ie._extract_chapters(description, duration),
+                self, ie._extract_chapters_from_description(description, duration),
                 expected_chapters, None)
 
 

test/testdata/cookies/malformed_cookies.txt

@@ -0,0 +1,9 @@
+# Netscape HTTP Cookie File
+# http://curl.haxx.se/rfc/cookie_spec.html
+# This is a generated file!  Do not edit.
+
+# Cookie file entry with invalid number of fields - 6 instead of 7
+www.foobar.foobar	FALSE	/	FALSE	0	COOKIE
+
+# Cookie file entry with invalid expires at
+www.foobar.foobar	FALSE	/	FALSE	1.7976931348623157e+308	COOKIE	VALUE

youtube_dl/compat.py

@@ -57,6 +57,17 @@ try:
 except ImportError:  # Python 2
     import cookielib as compat_cookiejar
 
+if sys.version_info[0] == 2:
+    class compat_cookiejar_Cookie(compat_cookiejar.Cookie):
+        def __init__(self, version, name, value, *args, **kwargs):
+            if isinstance(name, compat_str):
+                name = name.encode()
+            if isinstance(value, compat_str):
+                value = value.encode()
+            compat_cookiejar.Cookie.__init__(self, version, name, value, *args, **kwargs)
+else:
+    compat_cookiejar_Cookie = compat_cookiejar.Cookie
+
 try:
     import http.cookies as compat_cookies
 except ImportError:  # Python 2
@@ -2987,6 +2998,7 @@ __all__ = [
     'compat_basestring',
     'compat_chr',
     'compat_cookiejar',
+    'compat_cookiejar_Cookie',
     'compat_cookies',
     'compat_ctypes_WINFUNCTYPE',
     'compat_etree_Element',

youtube_dl/downloader/http.py

@@ -227,7 +227,7 @@ class HttpFD(FileDownloader):
             while True:
                 try:
                     # Download and write
-                    data_block = ctx.data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
+                    data_block = ctx.data.read(block_size if data_len is None else min(block_size, data_len - byte_counter))
                 # socket.timeout is a subclass of socket.error but may not have
                 # errno set
                 except socket.timeout as e:
@@ -299,7 +299,7 @@ class HttpFD(FileDownloader):
                     'elapsed': now - ctx.start_time,
                 })
 
-                if is_test and byte_counter == data_len:
+                if data_len is not None and byte_counter == data_len:
                     break
 
             if not is_test and ctx.chunk_size and ctx.data_len is not None and byte_counter < ctx.data_len:

youtube_dl/extractor/ard.py

@@ -249,7 +249,7 @@ class ARDMediathekIE(ARDMediathekBaseIE):
 
 
 class ARDIE(InfoExtractor):
-    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
     _TESTS = [{
         # available till 14.02.2019
         'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html',
@@ -263,6 +263,9 @@ class ARDIE(InfoExtractor):
             'upload_date': '20180214',
             'thumbnail': r're:^https?://.*\.jpg$',
         },
+    }, {
+        'url': 'https://www.daserste.de/information/reportage-dokumentation/erlebnis-erde/videosextern/woelfe-und-herdenschutzhunde-ungleiche-brueder-102.html',
+        'only_matching': True,
     }, {
         'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
         'only_matching': True,
@@ -310,9 +313,9 @@ class ARDIE(InfoExtractor):
 
 
 class ARDBetaMediathekIE(ARDMediathekBaseIE):
-    _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/(?P<client>[^/]+)/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?'
+    _VALID_URL = r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?P<client>[^/]+)/(?:player|live|video)/(?P<display_id>(?:[^/]+/)*)(?P<video_id>[a-zA-Z0-9]+)'
     _TESTS = [{
-        'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita',
+        'url': 'https://ardmediathek.de/ard/video/die-robuste-roswita/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
         'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f',
         'info_dict': {
             'display_id': 'die-robuste-roswita',
@@ -325,6 +328,15 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
             'upload_date': '20191222',
             'ext': 'mp4',
         },
+    }, {
+        'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
+        'only_matching': True,
+    }, {
+        'url': 'https://ardmediathek.de/ard/video/saartalk/saartalk-gesellschaftsgift-haltung-gegen-hass/sr-fernsehen/Y3JpZDovL3NyLW9ubGluZS5kZS9TVF84MTY4MA/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ardmediathek.de/ard/video/trailer/private-eyes-s01-e01/one/Y3JpZDovL3dkci5kZS9CZWl0cmFnLTE1MTgwYzczLWNiMTEtNGNkMS1iMjUyLTg5MGYzOWQxZmQ1YQ/',
+        'only_matching': True,
     }, {
         'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/',
         'only_matching': True,
@@ -336,7 +348,11 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
-        display_id = mobj.group('display_id') or video_id
+        display_id = mobj.group('display_id')
+        if display_id:
+            display_id = display_id.rstrip('/')
+        if not display_id:
+            display_id = video_id
 
         player_page = self._download_json(
             'https://api.ardmediathek.de/public-gateway',

youtube_dl/extractor/bbc.py

@@ -528,7 +528,7 @@ class BBCCoUkIE(InfoExtractor):
 
             def get_programme_id(item):
                 def get_from_attributes(item):
-                    for p in('identifier', 'group'):
+                    for p in ('identifier', 'group'):
                         value = item.get(p)
                         if value and re.match(r'^[pb][\da-z]{7}$', value):
                             return value

youtube_dl/extractor/bellmedia.py

@@ -25,8 +25,8 @@ class BellMediaIE(InfoExtractor):
                 etalk|
                 marilyn
             )\.ca|
-            much\.com
-        )/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
+            (?:much|cp24)\.com
+        )/.*?(?:\b(?:vid(?:eoid)?|clipId)=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
     _TESTS = [{
         'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070',
         'md5': '36d3ef559cfe8af8efe15922cd3ce950',
@@ -62,6 +62,9 @@ class BellMediaIE(InfoExtractor):
     }, {
         'url': 'http://www.etalk.ca/video?videoid=663455',
         'only_matching': True,
+    }, {
+        'url': 'https://www.cp24.com/video?clipId=1982548',
+        'only_matching': True,
     }]
     _DOMAINS = {
         'thecomedynetwork': 'comedy',

youtube_dl/extractor/brightcove.py

@@ -5,32 +5,34 @@ import base64
 import re
 import struct
 
-from .common import InfoExtractor
 from .adobepass import AdobePassIE
+from .common import InfoExtractor
 from ..compat import (
     compat_etree_fromstring,
+    compat_HTTPError,
     compat_parse_qs,
     compat_urllib_parse_urlparse,
     compat_urlparse,
     compat_xml_parse_error,
-    compat_HTTPError,
 )
 from ..utils import (
-    ExtractorError,
+    clean_html,
     extract_attributes,
+    ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
     float_or_none,
-    js_to_json,
     int_or_none,
+    js_to_json,
+    mimetype2ext,
     parse_iso8601,
     smuggle_url,
+    str_or_none,
     unescapeHTML,
     unsmuggle_url,
-    update_url_query,
-    clean_html,
-    mimetype2ext,
     UnsupportedError,
+    update_url_query,
+    url_or_none,
 )
 
 
@@ -424,7 +426,7 @@ class BrightcoveNewIE(AdobePassIE):
         # [2] looks like:
         for video, script_tag, account_id, player_id, embed in re.findall(
                 r'''(?isx)
-                    (<video\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)
+                    (<video(?:-js)?\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)
                     (?:.*?
                         (<script[^>]+
                             src=["\'](?:https?:)?//players\.brightcove\.net/
@@ -553,10 +555,16 @@ class BrightcoveNewIE(AdobePassIE):
 
         subtitles = {}
         for text_track in json_data.get('text_tracks', []):
-            if text_track.get('src'):
-                subtitles.setdefault(text_track.get('srclang'), []).append({
-                    'url': text_track['src'],
-                })
+            if text_track.get('kind') != 'captions':
+                continue
+            text_track_url = url_or_none(text_track.get('src'))
+            if not text_track_url:
+                continue
+            lang = (str_or_none(text_track.get('srclang'))
+                    or str_or_none(text_track.get('label')) or 'en').lower()
+            subtitles.setdefault(lang, []).append({
+                'url': text_track_url,
+            })
 
         is_live = False
         duration = float_or_none(json_data.get('duration'), 1000)

youtube_dl/extractor/common.py

@@ -15,7 +15,7 @@ import time
 import math
 
 from ..compat import (
-    compat_cookiejar,
+    compat_cookiejar_Cookie,
     compat_cookies,
     compat_etree_Element,
     compat_etree_fromstring,
@@ -2843,7 +2843,7 @@ class InfoExtractor(object):
 
     def _set_cookie(self, domain, name, value, expire_time=None, port=None,
                     path='/', secure=False, discard=False, rest={}, **kwargs):
-        cookie = compat_cookiejar.Cookie(
+        cookie = compat_cookiejar_Cookie(
             0, name, value, port, port is not None, domain, True,
             domain.startswith('.'), path, True, secure, expire_time,
             discard, None, None, rest)

youtube_dl/extractor/dailymotion.py

@@ -32,7 +32,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
 
     @staticmethod
     def _get_cookie_value(cookies, name):
-        cookie = cookies.get('name')
+        cookie = cookies.get(name)
         if cookie:
             return cookie.value
 

youtube_dl/extractor/extractors.py

@@ -804,6 +804,16 @@ from .orf import (
     ORFFM4IE,
     ORFFM4StoryIE,
     ORFOE1IE,
+    ORFOE3IE,
+    ORFNOEIE,
+    ORFWIEIE,
+    ORFBGLIE,
+    ORFOOEIE,
+    ORFSTMIE,
+    ORFKTNIE,
+    ORFSBGIE,
+    ORFTIRIE,
+    ORFVBGIE,
     ORFIPTVIE,
 )
 from .outsidetv import OutsideTVIE

youtube_dl/extractor/facebook.py

@@ -466,15 +466,18 @@ class FacebookIE(InfoExtractor):
             return info_dict
 
         if '/posts/' in url:
-            entries = [
-                self.url_result('facebook:%s' % vid, FacebookIE.ie_key())
-                for vid in self._parse_json(
-                    self._search_regex(
-                        r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])',
-                        webpage, 'video ids', group='ids'),
-                    video_id)]
+            video_id_json = self._search_regex(
+                r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', webpage, 'video ids', group='ids',
+                default='')
+            if video_id_json:
+                entries = [
+                    self.url_result('facebook:%s' % vid, FacebookIE.ie_key())
+                    for vid in self._parse_json(video_id_json, video_id)]
+                return self.playlist_result(entries, video_id)
 
-            return self.playlist_result(entries, video_id)
+            # Single Video?
+            video_id = self._search_regex(r'video_id:\s*"([0-9]+)"', webpage, 'single video id')
+            return self.url_result('facebook:%s' % video_id, FacebookIE.ie_key())
         else:
             _, info_dict = self._extract_from_url(
                 self._VIDEO_PAGE_TEMPLATE % video_id,

youtube_dl/extractor/generic.py

@@ -1708,6 +1708,15 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Kaltura'],
         },
+        {
+            # multiple kaltura embeds, nsfw
+            'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
+            'info_dict': {
+                'id': 'kamila-avec-video-jaime-sadomie',
+                'title': "Kamila avec vídeo “J'aime sadomie”",
+            },
+            'playlist_count': 8,
+        },
         {
             # Non-standard Vimeo embed
             'url': 'https://openclassrooms.com/courses/understanding-the-web',
@@ -2844,9 +2853,12 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'Zapiks')
 
         # Look for Kaltura embeds
-        kaltura_url = KalturaIE._extract_url(webpage)
-        if kaltura_url:
-            return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
+        kaltura_urls = KalturaIE._extract_urls(webpage)
+        if kaltura_urls:
+            return self.playlist_from_matches(
+                kaltura_urls, video_id, video_title,
+                getter=lambda x: smuggle_url(x, {'source_url': url}),
+                ie=KalturaIE.ie_key())
 
         # Look for EaglePlatform embeds
         eagleplatform_url = EaglePlatformIE._extract_url(webpage)

youtube_dl/extractor/giantbomb.py

@@ -13,10 +13,10 @@ from ..utils import (
 
 
 class GiantBombIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/videos/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/(?:videos|shows)/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)'
+    _TESTS = [{
         'url': 'http://www.giantbomb.com/videos/quick-look-destiny-the-dark-below/2300-9782/',
-        'md5': 'c8ea694254a59246a42831155dec57ac',
+        'md5': '132f5a803e7e0ab0e274d84bda1e77ae',
         'info_dict': {
             'id': '2300-9782',
             'display_id': 'quick-look-destiny-the-dark-below',
@@ -26,7 +26,10 @@ class GiantBombIE(InfoExtractor):
             'duration': 2399,
             'thumbnail': r're:^https?://.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'https://www.giantbomb.com/shows/ben-stranding/2970-20212',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/indavideo.py

@@ -58,7 +58,7 @@ class IndavideoEmbedIE(InfoExtractor):
         video_id = self._match_id(url)
 
         video = self._download_json(
-            'http://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id,
+            'https://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id,
             video_id)['data']
 
         title = video['title']

youtube_dl/extractor/iprima.py

@@ -16,12 +16,22 @@ class IPrimaIE(InfoExtractor):
     _GEO_BYPASS = False
 
     _TESTS = [{
-        'url': 'http://play.iprima.cz/gondici-s-r-o-33',
+        'url': 'https://prima.iprima.cz/particka/92-epizoda',
         'info_dict': {
-            'id': 'p136534',
+            'id': 'p51388',
             'ext': 'mp4',
-            'title': 'Gondíci s. r. o. (34)',
-            'description': 'md5:16577c629d006aa91f59ca8d8e7f99bd',
+            'title': 'Partička (92)',
+            'description': 'md5:859d53beae4609e6dd7796413f1b6cac',
+        },
+        'params': {
+            'skip_download': True,  # m3u8 download
+        },
+    }, {
+        'url': 'https://cnn.iprima.cz/videa/70-epizoda',
+        'info_dict': {
+            'id': 'p681554',
+            'ext': 'mp4',
+            'title': 'HLAVNÍ ZPRÁVY 3.5.2020',
         },
         'params': {
             'skip_download': True,  # m3u8 download
@@ -68,9 +78,15 @@ class IPrimaIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        title = self._og_search_title(
+            webpage, default=None) or self._search_regex(
+            r'<h1>([^<]+)', webpage, 'title')
+
         video_id = self._search_regex(
             (r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)',
-             r'data-product="([^"]+)">'),
+             r'data-product="([^"]+)">',
+             r'id=["\']player-(p\d+)"',
+             r'playerId\s*:\s*["\']player-(p\d+)'),
             webpage, 'real id')
 
         playerpage = self._download_webpage(
@@ -125,8 +141,8 @@ class IPrimaIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'formats': formats,
-            'description': self._og_search_description(webpage),
+            'description': self._og_search_description(webpage, default=None),
         }

youtube_dl/extractor/jwplatform.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import unsmuggle_url
 
 
 class JWPlatformIE(InfoExtractor):
@@ -32,10 +33,14 @@ class JWPlatformIE(InfoExtractor):
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//content\.jwplatform\.com/players/[a-zA-Z0-9]{8})',
+            r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//(?:content\.jwplatform|cdn\.jwplayer)\.com/players/[a-zA-Z0-9]{8})',
             webpage)
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        self._initialize_geo_bypass({
+            'countries': smuggled_data.get('geo_countries'),
+        })
         video_id = self._match_id(url)
         json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id)
         return self._parse_jwplayer_data(json_data, video_id)

youtube_dl/extractor/kaltura.py

@@ -113,9 +113,14 @@ class KalturaIE(InfoExtractor):
 
     @staticmethod
     def _extract_url(webpage):
+        urls = KalturaIE._extract_urls(webpage)
+        return urls[0] if urls else None
+
+    @staticmethod
+    def _extract_urls(webpage):
         # Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
-        mobj = (
-            re.search(
+        finditer = (
+            re.finditer(
                 r"""(?xs)
                     kWidget\.(?:thumb)?[Ee]mbed\(
                     \{.*?
@@ -124,7 +129,7 @@ class KalturaIE(InfoExtractor):
                         (?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
                         (?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
                 """, webpage)
-            or re.search(
+            or re.finditer(
                 r'''(?xs)
                     (?P<q1>["'])
                         (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
@@ -138,7 +143,7 @@ class KalturaIE(InfoExtractor):
                     )
                     (?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
                 ''', webpage)
-            or re.search(
+            or re.finditer(
                 r'''(?xs)
                     <(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
                       (?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
@@ -148,7 +153,8 @@ class KalturaIE(InfoExtractor):
                     (?P=q1)
                 ''', webpage)
         )
-        if mobj:
+        urls = []
+        for mobj in finditer:
             embed_info = mobj.groupdict()
             for k, v in embed_info.items():
                 if v:
@@ -160,7 +166,8 @@ class KalturaIE(InfoExtractor):
                 webpage)
             if service_mobj:
                 url = smuggle_url(url, {'service_url': service_mobj.group('id')})
-            return url
+            urls.append(url)
+        return urls
 
     def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs):
         params = actions[0]

youtube_dl/extractor/mailru.py

@@ -128,6 +128,12 @@ class MailRuIE(InfoExtractor):
                 'http://api.video.mail.ru/videos/%s.json?new=1' % video_id,
                 video_id, 'Downloading video JSON')
 
+        headers = {}
+
+        video_key = self._get_cookies('https://my.mail.ru').get('video_key')
+        if video_key:
+            headers['Cookie'] = 'video_key=%s' % video_key.value
+
         formats = []
         for f in video_data['videos']:
             video_url = f.get('url')
@@ -140,6 +146,7 @@ class MailRuIE(InfoExtractor):
                 'url': video_url,
                 'format_id': format_id,
                 'height': height,
+                'http_headers': headers,
             })
         self._sort_formats(formats)
 

youtube_dl/extractor/malltv.py

@@ -8,7 +8,7 @@ from ..utils import merge_dicts
 
 
 class MallTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|sk)\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
         'md5': '1c4a37f080e1f3023103a7b43458e518',
@@ -26,6 +26,9 @@ class MallTVIE(InfoExtractor):
     }, {
         'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
         'only_matching': True,
+    }, {
+        'url': 'https://sk.mall.tv/gejmhaus/reklamacia-nehreje-vyrobnik-tepla-alebo-spekacka',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/orf.py

@@ -162,13 +162,12 @@ class ORFTVthekIE(InfoExtractor):
 class ORFRadioIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        station = mobj.group('station')
         show_date = mobj.group('date')
         show_id = mobj.group('show')
 
         data = self._download_json(
             'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
-            % (station, show_id, show_date), show_id)
+            % (self._API_STATION, show_id, show_date), show_id)
 
         entries = []
         for info in data['streams']:
@@ -183,7 +182,7 @@ class ORFRadioIE(InfoExtractor):
             duration = end - start if end and start else None
             entries.append({
                 'id': loop_stream_id.replace('.mp3', ''),
-                'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, loop_stream_id),
+                'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
                 'title': title,
                 'description': clean_html(data.get('subtitle')),
                 'duration': duration,
@@ -205,6 +204,8 @@ class ORFFM4IE(ORFRadioIE):
     IE_NAME = 'orf:fm4'
     IE_DESC = 'radio FM4'
     _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>4\w+)'
+    _API_STATION = 'fm4'
+    _LOOP_STATION = 'fm4'
 
     _TEST = {
         'url': 'http://fm4.orf.at/player/20170107/4CC',
@@ -223,10 +224,142 @@ class ORFFM4IE(ORFRadioIE):
     }
 
 
+class ORFNOEIE(ORFRadioIE):
+    IE_NAME = 'orf:noe'
+    IE_DESC = 'Radio Niederösterreich'
+    _VALID_URL = r'https?://(?P<station>noe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'noe'
+    _LOOP_STATION = 'oe2n'
+
+    _TEST = {
+        'url': 'https://noe.orf.at/player/20200423/NGM',
+        'only_matching': True,
+    }
+
+
+class ORFWIEIE(ORFRadioIE):
+    IE_NAME = 'orf:wien'
+    IE_DESC = 'Radio Wien'
+    _VALID_URL = r'https?://(?P<station>wien)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'wie'
+    _LOOP_STATION = 'oe2w'
+
+    _TEST = {
+        'url': 'https://wien.orf.at/player/20200423/WGUM',
+        'only_matching': True,
+    }
+
+
+class ORFBGLIE(ORFRadioIE):
+    IE_NAME = 'orf:burgenland'
+    IE_DESC = 'Radio Burgenland'
+    _VALID_URL = r'https?://(?P<station>burgenland)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'bgl'
+    _LOOP_STATION = 'oe2b'
+
+    _TEST = {
+        'url': 'https://burgenland.orf.at/player/20200423/BGM',
+        'only_matching': True,
+    }
+
+
+class ORFOOEIE(ORFRadioIE):
+    IE_NAME = 'orf:oberoesterreich'
+    IE_DESC = 'Radio Oberösterreich'
+    _VALID_URL = r'https?://(?P<station>ooe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'ooe'
+    _LOOP_STATION = 'oe2o'
+
+    _TEST = {
+        'url': 'https://ooe.orf.at/player/20200423/OGMO',
+        'only_matching': True,
+    }
+
+
+class ORFSTMIE(ORFRadioIE):
+    IE_NAME = 'orf:steiermark'
+    IE_DESC = 'Radio Steiermark'
+    _VALID_URL = r'https?://(?P<station>steiermark)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'stm'
+    _LOOP_STATION = 'oe2st'
+
+    _TEST = {
+        'url': 'https://steiermark.orf.at/player/20200423/STGMS',
+        'only_matching': True,
+    }
+
+
+class ORFKTNIE(ORFRadioIE):
+    IE_NAME = 'orf:kaernten'
+    IE_DESC = 'Radio Kärnten'
+    _VALID_URL = r'https?://(?P<station>kaernten)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'ktn'
+    _LOOP_STATION = 'oe2k'
+
+    _TEST = {
+        'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
+        'only_matching': True,
+    }
+
+
+class ORFSBGIE(ORFRadioIE):
+    IE_NAME = 'orf:salzburg'
+    IE_DESC = 'Radio Salzburg'
+    _VALID_URL = r'https?://(?P<station>salzburg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'sbg'
+    _LOOP_STATION = 'oe2s'
+
+    _TEST = {
+        'url': 'https://salzburg.orf.at/player/20200423/SGUM',
+        'only_matching': True,
+    }
+
+
+class ORFTIRIE(ORFRadioIE):
+    IE_NAME = 'orf:tirol'
+    IE_DESC = 'Radio Tirol'
+    _VALID_URL = r'https?://(?P<station>tirol)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'tir'
+    _LOOP_STATION = 'oe2t'
+
+    _TEST = {
+        'url': 'https://tirol.orf.at/player/20200423/TGUMO',
+        'only_matching': True,
+    }
+
+
+class ORFVBGIE(ORFRadioIE):
+    IE_NAME = 'orf:vorarlberg'
+    IE_DESC = 'Radio Vorarlberg'
+    _VALID_URL = r'https?://(?P<station>vorarlberg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'vbg'
+    _LOOP_STATION = 'oe2v'
+
+    _TEST = {
+        'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
+        'only_matching': True,
+    }
+
+
+class ORFOE3IE(ORFRadioIE):
+    IE_NAME = 'orf:oe3'
+    IE_DESC = 'Radio Österreich 3'
+    _VALID_URL = r'https?://(?P<station>oe3)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'oe3'
+    _LOOP_STATION = 'oe3'
+
+    _TEST = {
+        'url': 'https://oe3.orf.at/player/20200424/3WEK',
+        'only_matching': True,
+    }
+
+
 class ORFOE1IE(ORFRadioIE):
     IE_NAME = 'orf:oe1'
     IE_DESC = 'Radio Österreich 1'
     _VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _API_STATION = 'oe1'
+    _LOOP_STATION = 'oe1'
 
     _TEST = {
         'url': 'http://oe1.orf.at/player/20170108/456544',

youtube_dl/extractor/periscope.py

@@ -18,7 +18,7 @@ class PeriscopeBaseIE(InfoExtractor):
             item_id, query=query)
 
     def _parse_broadcast_data(self, broadcast, video_id):
-        title = broadcast['status']
+        title = broadcast.get('status') or 'Periscope Broadcast'
         uploader = broadcast.get('user_display_name') or broadcast.get('username')
         title = '%s - %s' % (uploader, title) if uploader else title
         is_live = broadcast.get('state').lower() == 'running'

youtube_dl/extractor/puhutv.py

@@ -82,17 +82,6 @@ class PuhuTVIE(InfoExtractor):
         urls = []
         formats = []
 
-        def add_http_from_hls(m3u8_f):
-            http_url = m3u8_f['url'].replace('/hls/', '/mp4/').replace('/chunklist.m3u8', '.mp4')
-            if http_url != m3u8_f['url']:
-                f = m3u8_f.copy()
-                f.update({
-                    'format_id': f['format_id'].replace('hls', 'http'),
-                    'protocol': 'http',
-                    'url': http_url,
-                })
-                formats.append(f)
-
         for video in videos['data']['videos']:
             media_url = url_or_none(video.get('url'))
             if not media_url or media_url in urls:
@@ -101,12 +90,9 @@ class PuhuTVIE(InfoExtractor):
 
             playlist = video.get('is_playlist')
             if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url:
-                m3u8_formats = self._extract_m3u8_formats(
+                formats.extend(self._extract_m3u8_formats(
                     media_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False)
-                for m3u8_f in m3u8_formats:
-                    formats.append(m3u8_f)
-                    add_http_from_hls(m3u8_f)
+                    m3u8_id='hls', fatal=False))
                 continue
 
             quality = int_or_none(video.get('quality'))
@@ -128,8 +114,6 @@ class PuhuTVIE(InfoExtractor):
                 format_id += '-%sp' % quality
             f['format_id'] = format_id
             formats.append(f)
-            if is_hls:
-                add_http_from_hls(f)
         self._sort_formats(formats)
 
         creator = try_get(

youtube_dl/extractor/redtube.py

@@ -4,6 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     ExtractorError,
     int_or_none,
     merge_dicts,
@@ -57,7 +58,7 @@ class RedTubeIE(InfoExtractor):
 
         if not info.get('title'):
             info['title'] = self._html_search_regex(
-                (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
+                (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle|video_title)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
                  r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
                 webpage, 'title', group='title',
                 default=None) or self._og_search_title(webpage)
@@ -77,7 +78,7 @@ class RedTubeIE(InfoExtractor):
                     })
         medias = self._parse_json(
             self._search_regex(
-                r'mediaDefinition\s*:\s*(\[.+?\])', webpage,
+                r'mediaDefinition["\']?\s*:\s*(\[.+?}\s*\])', webpage,
                 'media definitions', default='{}'),
             video_id, fatal=False)
         if medias and isinstance(medias, list):
@@ -85,6 +86,12 @@ class RedTubeIE(InfoExtractor):
                 format_url = url_or_none(media.get('videoUrl'))
                 if not format_url:
                     continue
+                if media.get('format') == 'hls' or determine_ext(format_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id='hls',
+                        fatal=False))
+                    continue
                 format_id = media.get('quality')
                 formats.append({
                     'url': format_url,

youtube_dl/extractor/soundcloud.py

@@ -559,7 +559,7 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
 class SoundcloudPagedPlaylistBaseIE(SoundcloudIE):
     def _extract_playlist(self, base_url, playlist_id, playlist_title):
         COMMON_QUERY = {
-            'limit': 2000000000,
+            'limit': 80000,
             'linked_partitioning': '1',
         }
 

youtube_dl/extractor/spike.py

@@ -8,15 +8,10 @@ class BellatorIE(MTVServicesInfoExtractor):
     _TESTS = [{
         'url': 'http://www.bellator.com/fight/atwr7k/bellator-158-michael-page-vs-evangelista-cyborg',
         'info_dict': {
-            'id': 'b55e434e-fde1-4a98-b7cc-92003a034de4',
-            'ext': 'mp4',
-            'title': 'Douglas Lima vs. Paul Daley - Round 1',
-            'description': 'md5:805a8dd29310fd611d32baba2f767885',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+            'title': 'Michael Page vs. Evangelista Cyborg',
+            'description': 'md5:0d917fc00ffd72dd92814963fc6cbb05',
         },
+        'playlist_count': 3,
     }, {
         'url': 'http://www.bellator.com/video-clips/bw6k7n/bellator-158-foundations-michael-venom-page',
         'only_matching': True,
@@ -25,6 +20,9 @@ class BellatorIE(MTVServicesInfoExtractor):
     _FEED_URL = 'http://www.bellator.com/feeds/mrss/'
     _GEO_COUNTRIES = ['US']
 
+    def _extract_mgid(self, webpage):
+        return self._extract_triforce_mgid(webpage)
+
 
 class ParamountNetworkIE(MTVServicesInfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)'

youtube_dl/extractor/tele5.py

@@ -6,18 +6,16 @@ import re
 from .common import InfoExtractor
 from .jwplatform import JWPlatformIE
 from .nexx import NexxIE
-from ..compat import (
-    compat_str,
-    compat_urlparse,
-)
+from ..compat import compat_urlparse
 from ..utils import (
     NO_DEFAULT,
-    try_get,
+    smuggle_url,
 )
 
 
 class Tele5IE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _GEO_COUNTRIES = ['DE']
     _TESTS = [{
         'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
         'info_dict': {
@@ -30,6 +28,21 @@ class Tele5IE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # jwplatform, nexx unavailable
+        'url': 'https://www.tele5.de/filme/ghoul-das-geheimnis-des-friedhofmonsters/',
+        'info_dict': {
+            'id': 'WJuiOlUp',
+            'ext': 'mp4',
+            'upload_date': '20200603',
+            'timestamp': 1591214400,
+            'title': 'Ghoul - Das Geheimnis des Friedhofmonsters',
+            'description': 'md5:42002af1d887ff3d5b2b3ca1f8137d97',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [JWPlatformIE.ie_key()],
     }, {
         'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
         'only_matching': True,
@@ -88,15 +101,8 @@ class Tele5IE(InfoExtractor):
             if not jwplatform_id:
                 jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id')
 
-            media = self._download_json(
-                'https://cdn.jwplayer.com/v2/media/' + jwplatform_id,
-                display_id)
-            nexx_id = try_get(
-                media, lambda x: x['playlist'][0]['nexx_id'], compat_str)
-
-            if nexx_id:
-                return nexx_result(nexx_id)
-
         return self.url_result(
-            'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
-            video_id=jwplatform_id)
+            smuggle_url(
+                'jwplatform:%s' % jwplatform_id,
+                {'geo_countries': self._GEO_COUNTRIES}),
+            ie=JWPlatformIE.ie_key(), video_id=jwplatform_id)

youtube_dl/extractor/twitch.py

@@ -21,6 +21,8 @@ from ..utils import (
     orderedSet,
     parse_duration,
     parse_iso8601,
+    qualities,
+    str_or_none,
     try_get,
     unified_timestamp,
     update_url_query,
@@ -50,8 +52,14 @@ class TwitchBaseIE(InfoExtractor):
 
     def _call_api(self, path, item_id, *args, **kwargs):
         headers = kwargs.get('headers', {}).copy()
-        headers['Client-ID'] = self._CLIENT_ID
-        kwargs['headers'] = headers
+        headers.update({
+            'Accept': 'application/vnd.twitchtv.v5+json; charset=UTF-8',
+            'Client-ID': self._CLIENT_ID,
+        })
+        kwargs.update({
+            'headers': headers,
+            'expected_status': (400, 410),
+        })
         response = self._download_json(
             '%s/%s' % (self._API_BASE, path), item_id,
             *args, **compat_kwargs(kwargs))
@@ -186,12 +194,27 @@ class TwitchItemBaseIE(TwitchBaseIE):
             is_live = False
         else:
             is_live = None
+        _QUALITIES = ('small', 'medium', 'large')
+        quality_key = qualities(_QUALITIES)
+        thumbnails = []
+        preview = info.get('preview')
+        if isinstance(preview, dict):
+            for thumbnail_id, thumbnail_url in preview.items():
+                thumbnail_url = url_or_none(thumbnail_url)
+                if not thumbnail_url:
+                    continue
+                if thumbnail_id not in _QUALITIES:
+                    continue
+                thumbnails.append({
+                    'url': thumbnail_url,
+                    'preference': quality_key(thumbnail_id),
+                })
         return {
             'id': info['_id'],
             'title': info.get('title') or 'Untitled Broadcast',
             'description': info.get('description'),
             'duration': int_or_none(info.get('length')),
-            'thumbnail': info.get('preview'),
+            'thumbnails': thumbnails,
             'uploader': info.get('channel', {}).get('display_name'),
             'uploader_id': info.get('channel', {}).get('name'),
             'timestamp': parse_iso8601(info.get('recorded_at')),
@@ -572,10 +595,18 @@ class TwitchStreamIE(TwitchBaseIE):
                 else super(TwitchStreamIE, cls).suitable(url))
 
     def _real_extract(self, url):
-        channel_id = self._match_id(url)
+        channel_name = self._match_id(url)
+
+        access_token = self._call_api(
+            'api/channels/%s/access_token' % channel_name, channel_name,
+            'Downloading access token JSON')
+
+        token = access_token['token']
+        channel_id = compat_str(self._parse_json(
+            token, channel_name)['channel_id'])
 
         stream = self._call_api(
-            'kraken/streams/%s?stream_type=all' % channel_id.lower(),
+            'kraken/streams/%s?stream_type=all' % channel_id,
             channel_id, 'Downloading stream JSON').get('stream')
 
         if not stream:
@@ -585,11 +616,9 @@ class TwitchStreamIE(TwitchBaseIE):
         # (e.g. http://www.twitch.tv/TWITCHPLAYSPOKEMON) that will lead to constructing
         # an invalid m3u8 URL. Working around by use of original channel name from stream
         # JSON and fallback to lowercase if it's not available.
-        channel_id = stream.get('channel', {}).get('name') or channel_id.lower()
-
-        access_token = self._call_api(
-            'api/channels/%s/access_token' % channel_id, channel_id,
-            'Downloading channel access token')
+        channel_name = try_get(
+            stream, lambda x: x['channel']['name'],
+            compat_str) or channel_name.lower()
 
         query = {
             'allow_source': 'true',
@@ -600,11 +629,11 @@ class TwitchStreamIE(TwitchBaseIE):
             'playlist_include_framerate': 'true',
             'segment_preference': '4',
             'sig': access_token['sig'].encode('utf-8'),
-            'token': access_token['token'].encode('utf-8'),
+            'token': token.encode('utf-8'),
         }
         formats = self._extract_m3u8_formats(
             '%s/api/channel/hls/%s.m3u8?%s'
-            % (self._USHER_BASE, channel_id, compat_urllib_parse_urlencode(query)),
+            % (self._USHER_BASE, channel_name, compat_urllib_parse_urlencode(query)),
             channel_id, 'mp4')
         self._prefer_source(formats)
 
@@ -627,8 +656,8 @@ class TwitchStreamIE(TwitchBaseIE):
             })
 
         return {
-            'id': compat_str(stream['_id']),
-            'display_id': channel_id,
+            'id': str_or_none(stream.get('_id')) or channel_id,
+            'display_id': channel_name,
             'title': title,
             'description': description,
             'thumbnails': thumbnails,

youtube_dl/extractor/twitter.py

@@ -578,6 +578,18 @@ class TwitterBroadcastIE(TwitterBaseIE, PeriscopeBaseIE):
     IE_NAME = 'twitter:broadcast'
     _VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/broadcasts/(?P<id>[0-9a-zA-Z]{13})'
 
+    _TEST = {
+        # untitled Periscope video
+        'url': 'https://twitter.com/i/broadcasts/1yNGaQLWpejGj',
+        'info_dict': {
+            'id': '1yNGaQLWpejGj',
+            'ext': 'mp4',
+            'title': 'Andrea May Sahouri - Periscope Broadcast',
+            'uploader': 'Andrea May Sahouri',
+            'uploader_id': '1PXEdBZWpGwKe',
+        },
+    }
+
     def _real_extract(self, url):
         broadcast_id = self._match_id(url)
         broadcast = self._call_api(

youtube_dl/extractor/uol.py

@@ -2,12 +2,17 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_urlencode,
+)
 from ..utils import (
     clean_html,
     int_or_none,
     parse_duration,
+    parse_iso8601,
+    qualities,
     update_url_query,
-    str_or_none,
 )
 
 
@@ -16,21 +21,25 @@ class UOLIE(InfoExtractor):
     _VALID_URL = r'https?://(?:.+?\.)?uol\.com\.br/.*?(?:(?:mediaId|v)=|view/(?:[a-z0-9]+/)?|video(?:=|/(?:\d{4}/\d{2}/\d{2}/)?))(?P<id>\d+|[\w-]+-[A-Z0-9]+)'
     _TESTS = [{
         'url': 'http://player.mais.uol.com.br/player_video_v3.swf?mediaId=15951931',
-        'md5': '25291da27dc45e0afb5718a8603d3816',
+        'md5': '4f1e26683979715ff64e4e29099cf020',
         'info_dict': {
             'id': '15951931',
             'ext': 'mp4',
             'title': 'Miss simpatia é encontrada morta',
             'description': 'md5:3f8c11a0c0556d66daf7e5b45ef823b2',
+            'timestamp': 1470421860,
+            'upload_date': '20160805',
         }
     }, {
         'url': 'http://tvuol.uol.com.br/video/incendio-destroi-uma-das-maiores-casas-noturnas-de-londres-04024E9A3268D4C95326',
-        'md5': 'e41a2fb7b7398a3a46b6af37b15c00c9',
+        'md5': '2850a0e8dfa0a7307e04a96c5bdc5bc2',
         'info_dict': {
             'id': '15954259',
             'ext': 'mp4',
             'title': 'Incêndio destrói uma das maiores casas noturnas de Londres',
             'description': 'Em Londres, um incêndio destruiu uma das maiores boates da cidade. Não há informações sobre vítimas.',
+            'timestamp': 1470674520,
+            'upload_date': '20160808',
         }
     }, {
         'url': 'http://mais.uol.com.br/static/uolplayer/index.html?mediaId=15951931',
@@ -55,91 +64,55 @@ class UOLIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    _FORMATS = {
-        '2': {
-            'width': 640,
-            'height': 360,
-        },
-        '5': {
-            'width': 1280,
-            'height': 720,
-        },
-        '6': {
-            'width': 426,
-            'height': 240,
-        },
-        '7': {
-            'width': 1920,
-            'height': 1080,
-        },
-        '8': {
-            'width': 192,
-            'height': 144,
-        },
-        '9': {
-            'width': 568,
-            'height': 320,
-        },
-        '11': {
-            'width': 640,
-            'height': 360,
-        }
-    }
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        media_id = None
-
-        if video_id.isdigit():
-            media_id = video_id
-
-        if not media_id:
-            embed_page = self._download_webpage(
-                'https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id,
-                video_id, 'Downloading embed page', fatal=False)
-            if embed_page:
-                media_id = self._search_regex(
-                    (r'uol\.com\.br/(\d+)', r'mediaId=(\d+)'),
-                    embed_page, 'media id', default=None)
-
-        if not media_id:
-            webpage = self._download_webpage(url, video_id)
-            media_id = self._search_regex(r'mediaId=(\d+)', webpage, 'media id')
 
         video_data = self._download_json(
-            'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % media_id,
-            media_id)['item']
+            # https://api.mais.uol.com.br/apiuol/v4/player/data/[MEDIA_ID]
+            'https://api.mais.uol.com.br/apiuol/v3/media/detail/' + video_id,
+            video_id)['item']
+        media_id = compat_str(video_data['mediaId'])
         title = video_data['title']
+        ver = video_data.get('revision', 2)
 
-        query = {
-            'ver': video_data.get('numRevision', 2),
-            'r': 'http://mais.uol.com.br',
-        }
-        for k in ('token', 'sign'):
-            v = video_data.get(k)
-            if v:
-                query[k] = v
-
+        uol_formats = self._download_json(
+            'https://croupier.mais.uol.com.br/v3/formats/%s/jsonp' % media_id,
+            media_id)
+        quality = qualities(['mobile', 'WEBM', '360p', '720p', '1080p'])
         formats = []
-        for f in video_data.get('formats', []):
+        for format_id, f in uol_formats.items():
+            if not isinstance(f, dict):
+                continue
             f_url = f.get('url') or f.get('secureUrl')
             if not f_url:
                 continue
+            query = {
+                'ver': ver,
+                'r': 'http://mais.uol.com.br',
+            }
+            for k in ('token', 'sign'):
+                v = f.get(k)
+                if v:
+                    query[k] = v
             f_url = update_url_query(f_url, query)
-            format_id = str_or_none(f.get('id'))
-            if format_id == '10':
-                formats.extend(self._extract_m3u8_formats(
-                    f_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id='hls', fatal=False))
+            format_id = format_id
+            if format_id == 'HLS':
+                m3u8_formats = self._extract_m3u8_formats(
+                    f_url, media_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False)
+                encoded_query = compat_urllib_parse_urlencode(query)
+                for m3u8_f in m3u8_formats:
+                    m3u8_f['extra_param_to_segment_url'] = encoded_query
+                    m3u8_f['url'] = update_url_query(m3u8_f['url'], query)
+                formats.extend(m3u8_formats)
                 continue
-            fmt = {
+            formats.append({
                 'format_id': format_id,
                 'url': f_url,
-                'source_preference': 1,
-            }
-            fmt.update(self._FORMATS.get(format_id, {}))
-            formats.append(fmt)
-        self._sort_formats(formats, ('height', 'width', 'source_preference', 'tbr', 'ext'))
+                'quality': quality(format_id),
+                'preference': -1,
+            })
+        self._sort_formats(formats)
 
         tags = []
         for tag in video_data.get('tags', []):
@@ -148,12 +121,24 @@ class UOLIE(InfoExtractor):
                 continue
             tags.append(tag_description)
 
+        thumbnails = []
+        for q in ('Small', 'Medium', 'Wmedium', 'Large', 'Wlarge', 'Xlarge'):
+            q_url = video_data.get('thumb' + q)
+            if not q_url:
+                continue
+            thumbnails.append({
+                'id': q,
+                'url': q_url,
+            })
+
         return {
             'id': media_id,
             'title': title,
-            'description': clean_html(video_data.get('desMedia')),
-            'thumbnail': video_data.get('thumbnail'),
-            'duration': int_or_none(video_data.get('durationSeconds')) or parse_duration(video_data.get('duration')),
+            'description': clean_html(video_data.get('description')),
+            'thumbnails': thumbnails,
+            'duration': parse_duration(video_data.get('duration')),
             'tags': tags,
             'formats': formats,
+            'timestamp': parse_iso8601(video_data.get('publishDate'), ' '),
+            'view_count': int_or_none(video_data.get('viewsQtty')),
         }

youtube_dl/extractor/vimeo.py

@@ -140,28 +140,28 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             })
 
         # TODO: fix handling of 308 status code returned for live archive manifest requests
+        sep_pattern = r'/sep/video/'
         for files_type in ('hls', 'dash'):
             for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
                 manifest_url = cdn_data.get('url')
                 if not manifest_url:
                     continue
                 format_id = '%s-%s' % (files_type, cdn_name)
-                if files_type == 'hls':
-                    formats.extend(self._extract_m3u8_formats(
-                        manifest_url, video_id, 'mp4',
-                        'm3u8' if is_live else 'm3u8_native', m3u8_id=format_id,
-                        note='Downloading %s m3u8 information' % cdn_name,
-                        fatal=False))
-                elif files_type == 'dash':
-                    mpd_pattern = r'/%s/(?:sep/)?video/' % video_id
-                    mpd_manifest_urls = []
-                    if re.search(mpd_pattern, manifest_url):
-                        for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
-                            mpd_manifest_urls.append((format_id + suffix, re.sub(
-                                mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url)))
-                    else:
-                        mpd_manifest_urls = [(format_id, manifest_url)]
-                    for f_id, m_url in mpd_manifest_urls:
+                sep_manifest_urls = []
+                if re.search(sep_pattern, manifest_url):
+                    for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
+                        sep_manifest_urls.append((format_id + suffix, re.sub(
+                            sep_pattern, '/%s/' % repl, manifest_url)))
+                else:
+                    sep_manifest_urls = [(format_id, manifest_url)]
+                for f_id, m_url in sep_manifest_urls:
+                    if files_type == 'hls':
+                        formats.extend(self._extract_m3u8_formats(
+                            m_url, video_id, 'mp4',
+                            'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id,
+                            note='Downloading %s m3u8 information' % cdn_name,
+                            fatal=False))
+                    elif files_type == 'dash':
                         if 'json=1' in m_url:
                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
                             if real_m_url:
@@ -170,11 +170,6 @@ class VimeoBaseInfoExtractor(InfoExtractor):
                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
                             'Downloading %s MPD information' % cdn_name,
                             fatal=False)
-                        for f in mpd_formats:
-                            if f.get('vcodec') == 'none':
-                                f['preference'] = -50
-                            elif f.get('acodec') == 'none':
-                                f['preference'] = -40
                         formats.extend(mpd_formats)
 
         live_archive = live_event.get('archive') or {}
@@ -186,6 +181,12 @@ class VimeoBaseInfoExtractor(InfoExtractor):
                 'preference': 1,
             })
 
+        for f in formats:
+            if f.get('vcodec') == 'none':
+                f['preference'] = -50
+            elif f.get('acodec') == 'none':
+                f['preference'] = -40
+
         subtitles = {}
         text_tracks = config['request'].get('text_tracks')
         if text_tracks:

youtube_dl/extractor/wistia.py

@@ -56,7 +56,7 @@ class WistiaIE(InfoExtractor):
             urls.append(unescapeHTML(match.group('url')))
         for match in re.finditer(
                 r'''(?sx)
-                    <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
+                    <div[^>]+class=(["'])(?:(?!\1).)*?\bwistia_async_(?P<id>[a-z0-9]{10})\b(?:(?!\1).)*?\1
                 ''', webpage):
             urls.append('wistia:%s' % match.group('id'))
         for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):

youtube_dl/extractor/youtube.py

@@ -70,9 +70,14 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
     _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}'
 
+    _YOUTUBE_CLIENT_HEADERS = {
+        'x-youtube-client-name': '1',
+        'x-youtube-client-version': '1.20200609.04.02',
+    }
+
     def _set_language(self):
         self._set_cookie(
-            '.youtube.com', 'PREF', 'f1=50000000&hl=en',
+            '.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en',
             # YouTube sets the expire time to about two months
             expire_time=time.time() + 2 * 30 * 24 * 3600)
 
@@ -298,10 +303,11 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
                     # Downloading page may result in intermittent 5xx HTTP error
                     # that is usually worked around with a retry
                     more = self._download_json(
-                        'https://youtube.com/%s' % mobj.group('more'), playlist_id,
+                        'https://www.youtube.com/%s' % mobj.group('more'), playlist_id,
                         'Downloading page #%s%s'
                         % (page_num, ' (retry #%d)' % count if count else ''),
-                        transform_source=uppercase_escape)
+                        transform_source=uppercase_escape,
+                        headers=self._YOUTUBE_CLIENT_HEADERS)
                     break
                 except ExtractorError as e:
                     if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
@@ -388,8 +394,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:www\.)?invidious\.drycat\.fr/|
                             (?:www\.)?tube\.poal\.co/|
                             (?:www\.)?vid\.wxzm\.sx/|
+                            (?:www\.)?yewtu\.be/|
                             (?:www\.)?yt\.elukerio\.org/|
                             (?:www\.)?yt\.lelux\.fi/|
+                            (?:www\.)?invidious\.ggc-project\.de/|
+                            (?:www\.)?yt\.maisputain\.ovh/|
+                            (?:www\.)?invidious\.13ad\.de/|
+                            (?:www\.)?invidious\.toot\.koeln/|
+                            (?:www\.)?invidious\.fdn\.fr/|
+                            (?:www\.)?watch\.nettohikari\.com/|
                             (?:www\.)?kgg2m7yk5aybusll\.onion/|
                             (?:www\.)?qklhadlycap4cnod\.onion/|
                             (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
@@ -397,6 +410,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
                             (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
                             (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
+                            (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:
@@ -1370,7 +1384,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         funcname = self._search_regex(
             (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
+             r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
              r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
              # Obsolete patterns
              r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
@@ -1644,8 +1658,63 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         video_id = mobj.group(2)
         return video_id
 
+    def _extract_chapters_from_json(self, webpage, video_id, duration):
+        if not webpage:
+            return
+        player = self._parse_json(
+            self._search_regex(
+                r'RELATED_PLAYER_ARGS["\']\s*:\s*({.+})\s*,?\s*\n', webpage,
+                'player args', default='{}'),
+            video_id, fatal=False)
+        if not player or not isinstance(player, dict):
+            return
+        watch_next_response = player.get('watch_next_response')
+        if not isinstance(watch_next_response, compat_str):
+            return
+        response = self._parse_json(watch_next_response, video_id, fatal=False)
+        if not response or not isinstance(response, dict):
+            return
+        chapters_list = try_get(
+            response,
+            lambda x: x['playerOverlays']
+                       ['playerOverlayRenderer']
+                       ['decoratedPlayerBarRenderer']
+                       ['decoratedPlayerBarRenderer']
+                       ['playerBar']
+                       ['chapteredPlayerBarRenderer']
+                       ['chapters'],
+            list)
+        if not chapters_list:
+            return
+
+        def chapter_time(chapter):
+            return float_or_none(
+                try_get(
+                    chapter,
+                    lambda x: x['chapterRenderer']['timeRangeStartMillis'],
+                    int),
+                scale=1000)
+        chapters = []
+        for next_num, chapter in enumerate(chapters_list, start=1):
+            start_time = chapter_time(chapter)
+            if start_time is None:
+                continue
+            end_time = (chapter_time(chapters_list[next_num])
+                        if next_num < len(chapters_list) else duration)
+            if end_time is None:
+                continue
+            title = try_get(
+                chapter, lambda x: x['chapterRenderer']['title']['simpleText'],
+                compat_str)
+            chapters.append({
+                'start_time': start_time,
+                'end_time': end_time,
+                'title': title,
+            })
+        return chapters
+
     @staticmethod
-    def _extract_chapters(description, duration):
+    def _extract_chapters_from_description(description, duration):
         if not description:
             return None
         chapter_lines = re.findall(
@@ -1679,6 +1748,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             })
         return chapters
 
+    def _extract_chapters(self, webpage, description, video_id, duration):
+        return (self._extract_chapters_from_json(webpage, video_id, duration)
+                or self._extract_chapters_from_description(description, duration))
+
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
 
@@ -1825,6 +1898,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         video_details = try_get(
             player_response, lambda x: x['videoDetails'], dict) or {}
 
+        microformat = try_get(
+            player_response, lambda x: x['microformat']['playerMicroformatRenderer'], dict) or {}
+
         video_title = video_info.get('title', [None])[0] or video_details.get('title')
         if not video_title:
             self._downloader.report_warning('Unable to extract video title')
@@ -1854,7 +1930,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             ''', replace_url, video_description)
             video_description = clean_html(video_description)
         else:
-            video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription')
+            video_description = video_details.get('shortDescription') or self._html_search_meta('description', video_webpage)
 
         if not smuggled_data.get('force_singlefeed', False):
             if not self._downloader.params.get('noplaylist'):
@@ -1902,6 +1978,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             view_count = extract_view_count(video_info)
         if view_count is None and video_details:
             view_count = int_or_none(video_details.get('viewCount'))
+        if view_count is None and microformat:
+            view_count = int_or_none(microformat.get('viewCount'))
 
         if is_live is None:
             is_live = bool_or_none(video_details.get('isLive'))
@@ -1966,7 +2044,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 url = url_or_none(fmt.get('url'))
 
                 if not url:
-                    cipher = fmt.get('cipher')
+                    cipher = fmt.get('cipher') or fmt.get('signatureCipher')
                     if not cipher:
                         continue
                     url_data = compat_parse_qs(cipher)
@@ -2153,7 +2231,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             video_uploader_id = mobj.group('uploader_id')
             video_uploader_url = mobj.group('uploader_url')
         else:
-            self._downloader.report_warning('unable to extract uploader nickname')
+            owner_profile_url = url_or_none(microformat.get('ownerProfileUrl'))
+            if owner_profile_url:
+                video_uploader_id = self._search_regex(
+                    r'(?:user|channel)/([^/]+)', owner_profile_url, 'uploader id',
+                    default=None)
+                video_uploader_url = owner_profile_url
 
         channel_id = (
             str_or_none(video_details.get('channelId'))
@@ -2164,17 +2247,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 video_webpage, 'channel id', default=None, group='id'))
         channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
 
-        # thumbnail image
-        # We try first to get a high quality image:
-        m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
-                            video_webpage, re.DOTALL)
-        if m_thumb is not None:
-            video_thumbnail = m_thumb.group(1)
-        elif 'thumbnail_url' not in video_info:
-            self._downloader.report_warning('unable to extract video thumbnail')
+        thumbnails = []
+        thumbnails_list = try_get(
+            video_details, lambda x: x['thumbnail']['thumbnails'], list) or []
+        for t in thumbnails_list:
+            if not isinstance(t, dict):
+                continue
+            thumbnail_url = url_or_none(t.get('url'))
+            if not thumbnail_url:
+                continue
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': int_or_none(t.get('width')),
+                'height': int_or_none(t.get('height')),
+            })
+
+        if not thumbnails:
             video_thumbnail = None
-        else:   # don't panic if we can't find it
-            video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
+            # We try first to get a high quality image:
+            m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
+                                video_webpage, re.DOTALL)
+            if m_thumb is not None:
+                video_thumbnail = m_thumb.group(1)
+            thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url'][0], compat_str)
+            if thumbnail_url:
+                video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url)
+            if video_thumbnail:
+                thumbnails.append({'url': video_thumbnail})
 
         # upload date
         upload_date = self._html_search_meta(
@@ -2184,6 +2283,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 [r'(?s)id="eow-date.*?>(.*?)</span>',
                  r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
                 video_webpage, 'upload date', default=None)
+        if not upload_date:
+            upload_date = microformat.get('publishDate') or microformat.get('uploadDate')
         upload_date = unified_strdate(upload_date)
 
         video_license = self._html_search_regex(
@@ -2255,17 +2356,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         m_cat_container = self._search_regex(
             r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
             video_webpage, 'categories', default=None)
+        category = None
         if m_cat_container:
             category = self._html_search_regex(
                 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
                 default=None)
-            video_categories = None if category is None else [category]
-        else:
-            video_categories = None
+        if not category:
+            category = try_get(
+                microformat, lambda x: x['category'], compat_str)
+        video_categories = None if category is None else [category]
 
         video_tags = [
             unescapeHTML(m.group('content'))
             for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
+        if not video_tags:
+            video_tags = try_get(video_details, lambda x: x['keywords'], list)
 
         def _extract_count(count_name):
             return str_to_int(self._search_regex(
@@ -2316,7 +2421,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     errnote='Unable to download video annotations', fatal=False,
                     data=urlencode_postdata({xsrf_field_name: xsrf_token}))
 
-        chapters = self._extract_chapters(description_original, video_duration)
+        chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration)
 
         # Look for the DASH manifest
         if self._downloader.params.get('youtube_include_dash_manifest', True):
@@ -2407,7 +2512,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'creator': video_creator or artist,
             'title': video_title,
             'alt_title': video_alt_title or track,
-            'thumbnail': video_thumbnail,
+            'thumbnails': thumbnails,
             'description': video_description,
             'categories': video_categories,
             'tags': video_tags,
@@ -2671,7 +2776,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
         ids = []
         last_id = playlist_id[-11:]
         for n in itertools.count(1):
-            url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
+            url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
             webpage = self._download_webpage(
                 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
             new_ids = orderedSet(re.findall(
@@ -3011,7 +3116,7 @@ class YoutubeLiveIE(YoutubeBaseInfoExtractor):
 
 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
     IE_DESC = 'YouTube.com user/channel playlists'
-    _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
+    _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists'
     IE_NAME = 'youtube:playlists'
 
     _TESTS = [{
@@ -3037,6 +3142,9 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
             'title': 'Chem Player',
         },
         'skip': 'Blocked',
+    }, {
+        'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
+        'only_matching': True,
     }]
 
 
@@ -3181,9 +3289,10 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
                 break
 
             more = self._download_json(
-                'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
+                'https://www.youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
                 'Downloading page #%s' % page_num,
-                transform_source=uppercase_escape)
+                transform_source=uppercase_escape,
+                headers=self._YOUTUBE_CLIENT_HEADERS)
             content_html = more['content_html']
             more_widget_html = more['load_more_widget_html']
 

youtube_dl/postprocessor/ffmpeg.py

@@ -447,6 +447,13 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
                         metadata[meta_f] = info[info_f]
                     break
 
+        # See [1-4] for some info on media metadata/metadata supported
+        # by ffmpeg.
+        # 1. https://kdenlive.org/en/project/adding-meta-data-to-mp4-video/
+        # 2. https://wiki.multimedia.cx/index.php/FFmpeg_Metadata
+        # 3. https://kodi.wiki/view/Video_file_tagging
+        # 4. http://atomicparsley.sourceforge.net/mpeg-4files.html
+
         add('title', ('track', 'title'))
         add('date', 'upload_date')
         add(('description', 'comment'), 'description')
@@ -457,6 +464,10 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
         add('album')
         add('album_artist')
         add('disc', 'disc_number')
+        add('show', 'series')
+        add('season_number')
+        add('episode_id', ('episode', 'episode_id'))
+        add('episode_sort', 'episode_number')
 
         if not metadata:
             self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')

youtube_dl/utils.py

@@ -7,6 +7,7 @@ import base64
 import binascii
 import calendar
 import codecs
+import collections
 import contextlib
 import ctypes
 import datetime
@@ -30,6 +31,7 @@ import ssl
 import subprocess
 import sys
 import tempfile
+import time
 import traceback
 import xml.etree.ElementTree
 import zlib
@@ -1835,6 +1837,12 @@ def write_json_file(obj, fn):
                 os.unlink(fn)
             except OSError:
                 pass
+        try:
+            mask = os.umask(0)
+            os.umask(mask)
+            os.chmod(tf.name, 0o666 & ~mask)
+        except OSError:
+            pass
         os.rename(tf.name, fn)
     except Exception:
         try:
@@ -2735,14 +2743,66 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
     1. https://curl.haxx.se/docs/http-cookies.html
     """
     _HTTPONLY_PREFIX = '#HttpOnly_'
+    _ENTRY_LEN = 7
+    _HEADER = '''# Netscape HTTP Cookie File
+# This file is generated by youtube-dl.  Do not edit.
+
+'''
+    _CookieFileEntry = collections.namedtuple(
+        'CookieFileEntry',
+        ('domain_name', 'include_subdomains', 'path', 'https_only', 'expires_at', 'name', 'value'))
 
     def save(self, filename=None, ignore_discard=False, ignore_expires=False):
+        """
+        Save cookies to a file.
+
+        Most of the code is taken from CPython 3.8 and slightly adapted
+        to support cookie files with UTF-8 in both python 2 and 3.
+        """
+        if filename is None:
+            if self.filename is not None:
+                filename = self.filename
+            else:
+                raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
+
         # Store session cookies with `expires` set to 0 instead of an empty
         # string
         for cookie in self:
             if cookie.expires is None:
                 cookie.expires = 0
-        compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires)
+
+        with io.open(filename, 'w', encoding='utf-8') as f:
+            f.write(self._HEADER)
+            now = time.time()
+            for cookie in self:
+                if not ignore_discard and cookie.discard:
+                    continue
+                if not ignore_expires and cookie.is_expired(now):
+                    continue
+                if cookie.secure:
+                    secure = 'TRUE'
+                else:
+                    secure = 'FALSE'
+                if cookie.domain.startswith('.'):
+                    initial_dot = 'TRUE'
+                else:
+                    initial_dot = 'FALSE'
+                if cookie.expires is not None:
+                    expires = compat_str(cookie.expires)
+                else:
+                    expires = ''
+                if cookie.value is None:
+                    # cookies.txt regards 'Set-Cookie: foo' as a cookie
+                    # with no name, whereas http.cookiejar regards it as a
+                    # cookie with no value.
+                    name = ''
+                    value = cookie.name
+                else:
+                    name = cookie.name
+                    value = cookie.value
+                f.write(
+                    '\t'.join([cookie.domain, initial_dot, cookie.path,
+                               secure, expires, name, value]) + '\n')
 
     def load(self, filename=None, ignore_discard=False, ignore_expires=False):
         """Load cookies from a file."""
@@ -2752,12 +2812,30 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
             else:
                 raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
 
+        def prepare_line(line):
+            if line.startswith(self._HTTPONLY_PREFIX):
+                line = line[len(self._HTTPONLY_PREFIX):]
+            # comments and empty lines are fine
+            if line.startswith('#') or not line.strip():
+                return line
+            cookie_list = line.split('\t')
+            if len(cookie_list) != self._ENTRY_LEN:
+                raise compat_cookiejar.LoadError('invalid length %d' % len(cookie_list))
+            cookie = self._CookieFileEntry(*cookie_list)
+            if cookie.expires_at and not cookie.expires_at.isdigit():
+                raise compat_cookiejar.LoadError('invalid expires at %s' % cookie.expires_at)
+            return line
+
         cf = io.StringIO()
-        with open(filename) as f:
+        with io.open(filename, encoding='utf-8') as f:
             for line in f:
-                if line.startswith(self._HTTPONLY_PREFIX):
-                    line = line[len(self._HTTPONLY_PREFIX):]
-                cf.write(compat_str(line))
+                try:
+                    cf.write(prepare_line(line))
+                except compat_cookiejar.LoadError as e:
+                    write_string(
+                        'WARNING: skipping cookie file entry due to %s: %r\n'
+                        % (e, line), sys.stderr)
+                    continue
         cf.seek(0)
         self._really_load(cf, filename, ignore_discard, ignore_expires)
         # Session cookies are denoted by either `expires` field set to

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2020.05.03'
+__version__ = '2020.07.28'