Merge remote-tracking branch 'upstream/master'

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.07. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2021.04.07**
+- [ ] I've verified that I'm running youtube-dl version **2021.04.26**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2021.04.07
+ [debug] youtube-dl version 2021.04.26
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.07. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2021.04.07**
+- [ ] I've verified that I'm running youtube-dl version **2021.04.26**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.07. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2021.04.07**
+- [ ] I've verified that I'm running youtube-dl version **2021.04.26**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.07. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2021.04.07**
+- [ ] I've verified that I'm running youtube-dl version **2021.04.26**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2021.04.07
+ [debug] youtube-dl version 2021.04.26
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.07. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.04.26. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2021.04.07**
+- [ ] I've verified that I'm running youtube-dl version **2021.04.26**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

.github/workflows/ci.yml

@@ -49,11 +49,18 @@ jobs:
     - name: Install Jython
       if: ${{ matrix.python-impl == 'jython' }}
       run: |
-        wget http://search.maven.org/remotecontent?filepath=org/python/jython-installer/2.7.1/jython-installer-2.7.1.jar -O jython-installer.jar
+        wget https://repo1.maven.org/maven2/org/python/jython-installer/2.7.1/jython-installer-2.7.1.jar -O jython-installer.jar
         java -jar jython-installer.jar -s -d "$HOME/jython"
         echo "$HOME/jython/bin" >> $GITHUB_PATH
     - name: Install nose
+      if: ${{ matrix.python-impl != 'jython' }}
       run: pip install nose
+    - name: Install nose (Jython)
+      if: ${{ matrix.python-impl == 'jython' }}
+      # Working around deprecation of support for non-SNI clients at PyPI CDN (see https://status.python.org/incidents/hzmjhqsdjqgb)
+      run: |
+        wget https://files.pythonhosted.org/packages/99/4f/13fb671119e65c4dce97c60e67d3fd9e6f7f809f2b307e2611f4701205cb/nose-1.3.7-py2-none-any.whl
+        pip install nose-1.3.7-py2-none-any.whl
     - name: Run tests
       continue-on-error: ${{ matrix.ytdl-test-set == 'download' || matrix.python-impl == 'jython' }}
       env:

ChangeLog

@@ -1,3 +1,41 @@
+version 2021.04.26
+
+Extractors
++ [xfileshare] Add support for wolfstream.tv (#28858)
+* [francetvinfo] Improve video id extraction (#28792)
+* [medaltv] Fix extraction (#28807)
+* [tver] Redirect all downloads to Brightcove (#28849)
+* [go] Improve video id extraction (#25207, #25216, #26058)
+* [youtube] Fix lazy extractors (#28780)
++ [bbc] Extract description and timestamp from __INITIAL_DATA__ (#28774)
+* [cbsnews] Fix extraction for python <3.6 (#23359)
+
+
+version 2021.04.17
+
+Core
++ [utils] Add support for experimental HTTP response status code
+  308 Permanent Redirect (#27877, #28768)
+
+Extractors
++ [lbry] Add support for HLS videos (#27877, #28768)
+* [youtube] Fix stretched ratio calculation
+* [youtube] Improve stretch extraction (#28769)
+* [youtube:tab] Improve grid extraction (#28725)
++ [youtube:tab] Detect series playlist on playlists page (#28723)
++ [youtube] Add more invidious instances (#28706)
+* [pluralsight] Extend anti-throttling timeout (#28712)
+* [youtube] Improve URL to extractor routing (#27572, #28335, #28742)
++ [maoritv] Add support for maoritelevision.com (#24552)
++ [youtube:tab] Pass innertube context and x-goog-visitor-id header along with
+  continuation requests (#28702)
+* [mtv] Fix Viacom A/B Testing Video Player extraction (#28703)
++ [pornhub] Extract DASH and HLS formats from get_media end point (#28698)
+* [cbssports] Fix extraction (#28682)
+* [jamendo] Fix track extraction (#28686)
+* [curiositystream] Fix format extraction (#26845, #28668)
+
+
 version 2021.04.07
 
 Core

docs/supportedsites.md

@@ -3,6 +3,7 @@
  - **20min**
  - **220.ro**
  - **23video**
+ - **247sports**
  - **24video**
  - **3qsdn**: 3Q SDN
  - **3sat**
@@ -160,7 +161,8 @@
  - **cbsnews**: CBS News
  - **cbsnews:embed**
  - **cbsnews:livevideo**: CBS News Live Videos
- - **CBSSports**
+ - **cbssports**
+ - **cbssports:embed**
  - **CCMA**
  - **CCTV**: 央视网
  - **CDA**
@@ -490,6 +492,7 @@
  - **mangomolo:live**
  - **mangomolo:video**
  - **ManyVids**
+ - **MaoriTV**
  - **Markiza**
  - **MarkizaPage**
  - **massengeschmack.tv**
@@ -1159,7 +1162,7 @@
  - **WWE**
  - **XBef**
  - **XboxClips**
- - **XFileShare**: XFileShare based sites: Aparat, ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing
+ - **XFileShare**: XFileShare based sites: Aparat, ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, WolfStream, XVideoSharing
  - **XHamster**
  - **XHamsterEmbed**
  - **XHamsterUser**

test/test_all_urls.py

@@ -70,15 +70,6 @@ class TestAllURLsMatching(unittest.TestCase):
     #     self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
     #     self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
 
-    def test_youtube_extract(self):
-        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
-        assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
-        assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
-        assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
-        assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
-        assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
-        assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
-
     def test_facebook_matching(self):
         self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
         self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))

test/test_execution.py

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

test/test_youtube_misc.py

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

youtube_dl/YoutubeDL.py

@@ -773,11 +773,20 @@ class YoutubeDL(object):
 
     def extract_info(self, url, download=True, ie_key=None, extra_info={},
                      process=True, force_generic_extractor=False):
-        '''
+        """
-        Returns a list with a dictionary for each video we find.
+        Return a list with a dictionary for each video extracted.
-        If 'download', also downloads the videos.
+
-        extra_info is a dict containing the extra values to add to each result
+        Arguments:
-        '''
+        url -- URL to extract
+
+        Keyword arguments:
+        download -- whether to download videos during extraction
+        ie_key -- extractor key hint
+        extra_info -- dictionary containing the extra values to add to each result
+        process -- whether to resolve all unresolved references (URLs, playlist items),
+            must be True for download to work.
+        force_generic_extractor -- force using the generic extractor
+        """
 
         if not ie_key and force_generic_extractor:
             ie_key = 'Generic'

youtube_dl/extractor/bbc.py

@@ -11,6 +11,7 @@ from ..compat import (
     compat_etree_Element,
     compat_HTTPError,
     compat_parse_qs,
+    compat_str,
     compat_urllib_parse_urlparse,
     compat_urlparse,
 )
@@ -25,8 +26,10 @@ from ..utils import (
     js_to_json,
     parse_duration,
     parse_iso8601,
+    strip_or_none,
     try_get,
     unescapeHTML,
+    unified_timestamp,
     url_or_none,
     urlencode_postdata,
     urljoin,
@@ -761,8 +764,17 @@ class BBCIE(BBCCoUkIE):
         'only_matching': True,
     }, {
         # custom redirection to www.bbc.com
+        # also, video with window.__INITIAL_DATA__
         'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
-        'only_matching': True,
+        'info_dict': {
+            'id': 'p02xzws1',
+            'ext': 'mp4',
+            'title': "Pluto may have 'nitrogen glaciers'",
+            'description': 'md5:6a95b593f528d7a5f2605221bc56912f',
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'timestamp': 1437785037,
+            'upload_date': '20150725',
+        },
     }, {
         # single video article embedded with data-media-vpid
         'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
@@ -1164,12 +1176,29 @@ class BBCIE(BBCCoUkIE):
                         continue
                     formats, subtitles = self._download_media_selector(item_id)
                     self._sort_formats(formats)
+                    item_desc = None
+                    blocks = try_get(media, lambda x: x['summary']['blocks'], list)
+                    if blocks:
+                        summary = []
+                        for block in blocks:
+                            text = try_get(block, lambda x: x['model']['text'], compat_str)
+                            if text:
+                                summary.append(text)
+                        if summary:
+                            item_desc = '\n\n'.join(summary)
+                    item_time = None
+                    for meta in try_get(media, lambda x: x['metadata']['items'], list) or []:
+                        if try_get(meta, lambda x: x['label']) == 'Published':
+                            item_time = unified_timestamp(meta.get('timestamp'))
+                            break
                     entries.append({
                         'id': item_id,
                         'title': item_title,
                         'thumbnail': item.get('holdingImageUrl'),
                         'formats': formats,
                         'subtitles': subtitles,
+                        'timestamp': item_time,
+                        'description': strip_or_none(item_desc),
                     })
             for resp in (initial_data.get('data') or {}).values():
                 name = resp.get('name')

youtube_dl/extractor/blinkx.py

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

youtube_dl/extractor/cbsnews.py

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

youtube_dl/extractor/cda.py

@@ -133,6 +133,8 @@ class CDAIE(InfoExtractor):
             'age_limit': 18 if need_confirm_age else 0,
         }
 
+        info = self._search_json_ld(webpage, video_id, default={})
+
         # Source: https://www.cda.pl/js/player.js?t=1606154898
         def decrypt_file(a):
             for p in ('_XDDD', '_CDA', '_ADC', '_CXD', '_QWE', '_Q5', '_IKSDE'):
@@ -197,7 +199,7 @@ class CDAIE(InfoExtractor):
                 handler = self._download_webpage
 
             webpage = handler(
-                self._BASE_URL + href, video_id,
+                urljoin(self._BASE_URL, href), video_id,
                 'Downloading %s version information' % resolution, fatal=False)
             if not webpage:
                 # Manually report warning because empty page is returned when
@@ -209,6 +211,4 @@ class CDAIE(InfoExtractor):
 
         self._sort_formats(formats)
 
-        info = self._search_json_ld(webpage, video_id, default={})
-
         return merge_dicts(info_dict, info)

youtube_dl/extractor/dispeak.py

@@ -32,6 +32,18 @@ class DigitallySpeakingIE(InfoExtractor):
         # From http://www.gdcvault.com/play/1013700/Advanced-Material
         'url': 'http://sevt.dispeak.com/ubm/gdc/eur10/xml/11256_1282118587281VNIT.xml',
         'only_matching': True,
+    }, {
+        # From https://gdcvault.com/play/1016624, empty speakerVideo
+        'url': 'https://sevt.dispeak.com/ubm/gdc/online12/xml/201210-822101_1349794556671DDDD.xml',
+        'info_dict': {
+            'id': '201210-822101_1349794556671DDDD',
+            'ext': 'flv',
+            'title': 'Pre-launch - Preparing to Take the Plunge',
+        },
+    }, {
+        # From http://www.gdcvault.com/play/1014846/Conference-Keynote-Shigeru, empty slideVideo
+        'url': 'http://events.digitallyspeaking.com/gdc/project25/xml/p25-miyamoto1999_1282467389849HSVB.xml',
+        'only_matching': True,
     }]
 
     def _parse_mp4(self, metadata):
@@ -84,26 +96,20 @@ class DigitallySpeakingIE(InfoExtractor):
                 'vcodec': 'none',
                 'format_id': audio.get('code'),
             })
-        slide_video_path = xpath_text(metadata, './slideVideo', fatal=True)
+        for video_key, format_id, preference in (
-        formats.append({
+                ('slide', 'slides', -2), ('speaker', 'speaker', -1)):
-            'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
+            video_path = xpath_text(metadata, './%sVideo' % video_key)
-            'play_path': remove_end(slide_video_path, '.flv'),
+            if not video_path:
-            'ext': 'flv',
+                continue
-            'format_note': 'slide deck video',
+            formats.append({
-            'quality': -2,
+                'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
-            'preference': -2,
+                'play_path': remove_end(video_path, '.flv'),
-            'format_id': 'slides',
+                'ext': 'flv',
-        })
+                'format_note': '%s video' % video_key,
-        speaker_video_path = xpath_text(metadata, './speakerVideo', fatal=True)
+                'quality': preference,
-        formats.append({
+                'preference': preference,
-            'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
+                'format_id': format_id,
-            'play_path': remove_end(speaker_video_path, '.flv'),
+            })
-            'ext': 'flv',
-            'format_note': 'speaker video',
-            'quality': -1,
-            'preference': -1,
-            'format_id': 'speaker',
-        })
         return formats
 
     def _real_extract(self, url):

youtube_dl/extractor/extractors.py

@@ -132,7 +132,6 @@ from .bleacherreport import (
     BleacherReportIE,
     BleacherReportCMSIE,
 )
-from .blinkx import BlinkxIE
 from .bloomberg import BloombergIE
 from .bokecc import BokeCCIE
 from .bongacams import BongaCamsIE

youtube_dl/extractor/francetv.py

@@ -383,6 +383,10 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
     }, {
         'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
         'only_matching': True,
+    }, {
+        # "<figure id=" pattern (#28792)
+        'url': 'https://www.francetvinfo.fr/culture/patrimoine/incendie-de-notre-dame-de-paris/notre-dame-de-paris-de-l-incendie-de-la-cathedrale-a-sa-reconstruction_4372291.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -400,7 +404,7 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
             (r'player\.load[^;]+src:\s*["\']([^"\']+)',
              r'id-video=([^@]+@[^"]+)',
              r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"',
-             r'data-id=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'),
+             r'(?:data-id|<figure[^<]+\bid)=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'),
             webpage, 'video id')
 
         return self._make_url_result(video_id)

youtube_dl/extractor/funimation.py

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

youtube_dl/extractor/gdcvault.py

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

youtube_dl/extractor/go.py

@@ -4,10 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .adobepass import AdobePassIE
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     determine_ext,
     parse_age_limit,
+    try_get,
     urlencode_postdata,
     ExtractorError,
 )
@@ -116,6 +118,18 @@ class GoIE(AdobePassIE):
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        'url': 'https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot',
+        'info_dict': {
+            'id': 'VDKA22600213',
+            'ext': 'mp4',
+            'title': 'Pilot',
+            'description': 'md5:74306df917cfc199d76d061d66bebdb4',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
         'only_matching': True,
@@ -149,14 +163,30 @@ class GoIE(AdobePassIE):
         brand = site_info.get('brand')
         if not video_id or not site_info:
             webpage = self._download_webpage(url, display_id or video_id)
-            video_id = self._search_regex(
+            data = self._parse_json(
-                (
+                self._search_regex(
-                    # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
+                    r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
-                    # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
+                    'data', default='{}'),
-                    r'data-video-id=["\']*(VDKA\w+)',
+                display_id or video_id, fatal=False)
-                    # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
+            # https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
-                    r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
+            layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
-                ), webpage, 'video id', default=video_id)
+            video_id = None
+            if layout:
+                video_id = try_get(
+                    layout,
+                    (lambda x: x['videoid'], lambda x: x['video']['id']),
+                    compat_str)
+            if not video_id:
+                video_id = self._search_regex(
+                    (
+                        # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
+                        # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
+                        r'data-video-id=["\']*(VDKA\w+)',
+                        # page.analytics.videoIdCode
+                        r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
+                        # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
+                        r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
+                    ), webpage, 'video id', default=video_id)
             if not site_info:
                 brand = self._search_regex(
                     (r'data-brand=\s*["\']\s*(\d+)',

youtube_dl/extractor/kaltura.py

@@ -120,7 +120,7 @@ class KalturaIE(InfoExtractor):
     def _extract_urls(webpage):
         # Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
         finditer = (
-            re.finditer(
+            list(re.finditer(
                 r"""(?xs)
                     kWidget\.(?:thumb)?[Ee]mbed\(
                     \{.*?
@@ -128,8 +128,8 @@ class KalturaIE(InfoExtractor):
                         (?P<q2>['"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
                         (?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
                         (?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
-                """, webpage)
+                """, webpage))
-            or re.finditer(
+            or list(re.finditer(
                 r'''(?xs)
                     (?P<q1>["'])
                         (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
@@ -142,16 +142,16 @@ class KalturaIE(InfoExtractor):
                         \[\s*(?P<q2_1>["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s*
                     )
                     (?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
-                ''', webpage)
+                ''', webpage))
-            or re.finditer(
+            or list(re.finditer(
                 r'''(?xs)
-                    <(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
+                    <(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])\s*
                       (?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
                       (?:(?!(?P=q1)).)*
                       [?&;]entry_id=(?P<id>(?:(?!(?P=q1))[^&])+)
                       (?:(?!(?P=q1)).)*
                     (?P=q1)
-                ''', webpage)
+                ''', webpage))
         )
         urls = []
         for mobj in finditer:

youtube_dl/extractor/lbry.py

@@ -120,6 +120,26 @@ class LBRYIE(LBRYBaseIE):
             'channel_url': 'https://lbry.tv/@LBRYFoundation:0ed629d2b9c601300cacf7eabe9da0be79010212',
             'vcodec': 'none',
         }
+    }, {
+        # HLS
+        'url': 'https://odysee.com/@gardeningincanada:b/plants-i-will-never-grow-again.-the:e',
+        'md5': 'fc82f45ea54915b1495dd7cb5cc1289f',
+        'info_dict': {
+            'id': 'e51671357333fe22ae88aad320bde2f6f96b1410',
+            'ext': 'mp4',
+            'title': 'PLANTS I WILL NEVER GROW AGAIN. THE BLACK LIST PLANTS FOR A CANADIAN GARDEN | Gardening in Canada 🍁',
+            'description': 'md5:9c539c6a03fb843956de61a4d5288d5e',
+            'timestamp': 1618254123,
+            'upload_date': '20210412',
+            'release_timestamp': 1618254002,
+            'release_date': '20210412',
+            'tags': list,
+            'duration': 554,
+            'channel': 'Gardening In Canada',
+            'channel_id': 'b8be0e93b423dad221abe29545fbe8ec36e806bc',
+            'channel_url': 'https://odysee.com/@gardeningincanada:b8be0e93b423dad221abe29545fbe8ec36e806bc',
+            'formats': 'mincount:3',
+        }
     }, {
         'url': 'https://odysee.com/@BrodieRobertson:5/apple-is-tracking-everything-you-do-on:e',
         'only_matching': True,
@@ -163,10 +183,18 @@ class LBRYIE(LBRYBaseIE):
         streaming_url = self._call_api_proxy(
             'get', claim_id, {'uri': uri}, 'streaming url')['streaming_url']
         info = self._parse_stream(result, url)
+        urlh = self._request_webpage(
+            streaming_url, display_id, note='Downloading streaming redirect url info')
+        if determine_ext(urlh.geturl()) == 'm3u8':
+            info['formats'] = self._extract_m3u8_formats(
+                urlh.geturl(), display_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls')
+            self._sort_formats(info['formats'])
+        else:
+            info['url'] = streaming_url
         info.update({
             'id': claim_id,
             'title': title,
-            'url': streaming_url,
         })
         return info
 

youtube_dl/extractor/medaltv.py

@@ -15,33 +15,39 @@ from ..utils import (
 
 
 class MedalTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?medal\.tv/clips/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?medal\.tv/clips/(?P<id>[^/?#&]+)'
     _TESTS = [{
-        'url': 'https://medal.tv/clips/34934644/3Is9zyGMoBMr',
+        'url': 'https://medal.tv/clips/2mA60jWAGQCBH',
         'md5': '7b07b064331b1cf9e8e5c52a06ae68fa',
         'info_dict': {
-            'id': '34934644',
+            'id': '2mA60jWAGQCBH',
             'ext': 'mp4',
             'title': 'Quad Cold',
             'description': 'Medal,https://medal.tv/desktop/',
             'uploader': 'MowgliSB',
             'timestamp': 1603165266,
             'upload_date': '20201020',
-            'uploader_id': 10619174,
+            'uploader_id': '10619174',
         }
     }, {
-        'url': 'https://medal.tv/clips/36787208',
+        'url': 'https://medal.tv/clips/2um24TWdty0NA',
         'md5': 'b6dc76b78195fff0b4f8bf4a33ec2148',
         'info_dict': {
-            'id': '36787208',
+            'id': '2um24TWdty0NA',
             'ext': 'mp4',
             'title': 'u tk me i tk u bigger',
             'description': 'Medal,https://medal.tv/desktop/',
             'uploader': 'Mimicc',
             'timestamp': 1605580939,
             'upload_date': '20201117',
-            'uploader_id': 5156321,
+            'uploader_id': '5156321',
         }
+    }, {
+        'url': 'https://medal.tv/clips/37rMeFpryCC-9',
+        'only_matching': True,
+    }, {
+        'url': 'https://medal.tv/clips/2WRj40tpY_EU9',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/pluralsight.py

@@ -393,7 +393,7 @@ query viewClip {
                 # To somewhat reduce the probability of these consequences
                 # we will sleep random amount of time before each call to ViewClip.
                 self._sleep(
-                    random.randint(2, 5), display_id,
+                    random.randint(5, 10), display_id,
                     '%(video_id)s: Waiting for %(timeout)s seconds to avoid throttling')
 
                 if not viewclip:

youtube_dl/extractor/svt.py

@@ -146,7 +146,7 @@ class SVTPlayIE(SVTPlayBaseIE):
                         )
                         (?P<svt_id>[^/?#&]+)|
                         https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)
-                        (?:.*?modalId=(?P<modal_id>[\da-zA-Z-]+))?
+                        (?:.*?(?:modalId|id)=(?P<modal_id>[\da-zA-Z-]+))?
                     )
                     '''
     _TESTS = [{
@@ -177,6 +177,9 @@ class SVTPlayIE(SVTPlayBaseIE):
     }, {
         'url': 'https://www.svtplay.se/video/30479064/husdrommar/husdrommar-sasong-8-designdrommar-i-stenungsund?modalId=8zVbDPA',
         'only_matching': True,
+    }, {
+        'url': 'https://www.svtplay.se/video/30684086/rapport/rapport-24-apr-18-00-7?id=e72gVpa',
+        'only_matching': True,
     }, {
         # geo restricted to Sweden
         'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
@@ -259,7 +262,7 @@ class SVTPlayIE(SVTPlayBaseIE):
         if not svt_id:
             svt_id = self._search_regex(
                 (r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
-                 r'<[^>]+\bdata-rt=["\']top-area-play-button["\'][^>]+\bhref=["\'][^"\']*video/%s/[^"\']*\bmodalId=([\da-zA-Z-]+)' % re.escape(video_id),
+                 r'<[^>]+\bdata-rt=["\']top-area-play-button["\'][^>]+\bhref=["\'][^"\']*video/%s/[^"\']*\b(?:modalId|id)=([\da-zA-Z-]+)' % re.escape(video_id),
                  r'["\']videoSvtId["\']\s*:\s*["\']([\da-zA-Z-]+)',
                  r'["\']videoSvtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)',
                  r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"',

youtube_dl/extractor/tv2dk.py

@@ -74,6 +74,12 @@ class TV2DKIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         entries = []
+
+        def add_entry(partner_id, kaltura_id):
+            entries.append(self.url_result(
+                'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
+                video_id=kaltura_id))
+
         for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage):
             video = extract_attributes(video_el)
             kaltura_id = video.get('data-entryid')
@@ -82,9 +88,14 @@ class TV2DKIE(InfoExtractor):
             partner_id = video.get('data-partnerid')
             if not partner_id:
                 continue
-            entries.append(self.url_result(
+            add_entry(partner_id, kaltura_id)
-                'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
+        if not entries:
-                video_id=kaltura_id))
+            kaltura_id = self._search_regex(
+                r'entry_id\s*:\s*["\']([0-9a-z_]+)', webpage, 'kaltura id')
+            partner_id = self._search_regex(
+                (r'\\u002Fp\\u002F(\d+)\\u002F', r'/p/(\d+)/'), webpage,
+                'partner id')
+            add_entry(partner_id, kaltura_id)
         return self.playlist_result(entries)
 
 

youtube_dl/extractor/tver.py

@@ -9,7 +9,6 @@ from ..utils import (
     int_or_none,
     remove_start,
     smuggle_url,
-    strip_or_none,
     try_get,
 )
 
@@ -45,32 +44,18 @@ class TVerIE(InfoExtractor):
             query={'token': self._TOKEN})['main']
         p_id = main['publisher_id']
         service = remove_start(main['service'], 'ts_')
-        info = {
+
+        r_id = main['reference_id']
+        if service not in ('tx', 'russia2018', 'sebare2018live', 'gorin'):
+            r_id = 'ref:' + r_id
+        bc_url = smuggle_url(
+            self.BRIGHTCOVE_URL_TEMPLATE % (p_id, r_id),
+            {'geo_countries': ['JP']})
+
+        return {
             '_type': 'url_transparent',
             'description': try_get(main, lambda x: x['note'][0]['text'], compat_str),
             'episode_number': int_or_none(try_get(main, lambda x: x['ext']['episode_number'])),
+            'url': bc_url,
+            'ie_key': 'BrightcoveNew',
         }
-
-        if service == 'cx':
-            title = main['title']
-            subtitle = strip_or_none(main.get('subtitle'))
-            if subtitle:
-                title += ' - ' + subtitle
-            info.update({
-                'title': title,
-                'url': 'https://i.fod.fujitv.co.jp/plus7/web/%s/%s.html' % (p_id[:4], p_id),
-                'ie_key': 'FujiTVFODPlus7',
-            })
-        else:
-            r_id = main['reference_id']
-            if service not in ('tx', 'russia2018', 'sebare2018live', 'gorin'):
-                r_id = 'ref:' + r_id
-            bc_url = smuggle_url(
-                self.BRIGHTCOVE_URL_TEMPLATE % (p_id, r_id),
-                {'geo_countries': ['JP']})
-            info.update({
-                'url': bc_url,
-                'ie_key': 'BrightcoveNew',
-            })
-
-        return info

youtube_dl/extractor/twitter.py

@@ -19,6 +19,7 @@ from ..utils import (
     strip_or_none,
     unified_timestamp,
     update_url_query,
+    url_or_none,
     xpath_text,
 )
 
@@ -52,6 +53,9 @@ class TwitterBaseIE(InfoExtractor):
             return [f]
 
     def _extract_formats_from_vmap_url(self, vmap_url, video_id):
+        vmap_url = url_or_none(vmap_url)
+        if not vmap_url:
+            return []
         vmap_data = self._download_xml(vmap_url, video_id)
         formats = []
         urls = []

youtube_dl/extractor/xfileshare.py

@@ -58,6 +58,7 @@ class XFileShareIE(InfoExtractor):
         (r'vidlocker\.xyz', 'VidLocker'),
         (r'vidshare\.tv', 'VidShare'),
         (r'vup\.to', 'VUp'),
+        (r'wolfstream\.tv', 'WolfStream'),
         (r'xvideosharing\.com', 'XVideoSharing'),
     )
 
@@ -82,6 +83,9 @@ class XFileShareIE(InfoExtractor):
     }, {
         'url': 'https://aparat.cam/n4d6dh0wvlpr',
         'only_matching': True,
+    }, {
+        'url': 'https://wolfstream.tv/nthme29v9u2x',
+        'only_matching': True,
     }]
 
     @staticmethod

youtube_dl/extractor/xtube.py

@@ -11,6 +11,7 @@ from ..utils import (
     parse_duration,
     sanitized_Request,
     str_to_int,
+    url_or_none,
 )
 
 
@@ -87,10 +88,10 @@ class XTubeIE(InfoExtractor):
                 'Cookie': 'age_verified=1; cookiesAccepted=1',
             })
 
-        title, thumbnail, duration = [None] * 3
+        title, thumbnail, duration, sources, media_definition = [None] * 5
 
         config = self._parse_json(self._search_regex(
-            r'playerConf\s*=\s*({.+?})\s*,\s*(?:\n|loaderConf)', webpage, 'config',
+            r'playerConf\s*=\s*({.+?})\s*,\s*(?:\n|loaderConf|playerWrapper)', webpage, 'config',
             default='{}'), video_id, transform_source=js_to_json, fatal=False)
         if config:
             config = config.get('mainRoll')
@@ -99,20 +100,52 @@ class XTubeIE(InfoExtractor):
                 thumbnail = config.get('poster')
                 duration = int_or_none(config.get('duration'))
                 sources = config.get('sources') or config.get('format')
+                media_definition = config.get('mediaDefinition')
 
-        if not isinstance(sources, dict):
+        if not isinstance(sources, dict) and not media_definition:
             sources = self._parse_json(self._search_regex(
                 r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
                 webpage, 'sources', group='sources'), video_id,
                 transform_source=js_to_json)
 
         formats = []
-        for format_id, format_url in sources.items():
+        format_urls = set()
-            formats.append({
+
-                'url': format_url,
+        if isinstance(sources, dict):
-                'format_id': format_id,
+            for format_id, format_url in sources.items():
-                'height': int_or_none(format_id),
+                format_url = url_or_none(format_url)
-            })
+                if not format_url:
+                    continue
+                if format_url in format_urls:
+                    continue
+                format_urls.add(format_url)
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                    'height': int_or_none(format_id),
+                })
+
+        if isinstance(media_definition, list):
+            for media in media_definition:
+                video_url = url_or_none(media.get('videoUrl'))
+                if not video_url:
+                    continue
+                if video_url in format_urls:
+                    continue
+                format_urls.add(video_url)
+                format_id = media.get('format')
+                if format_id == 'hls':
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id='hls', fatal=False))
+                elif format_id == 'mp4':
+                    height = int_or_none(media.get('quality'))
+                    formats.append({
+                        'url': video_url,
+                        'format_id': '%s-%d' % (format_id, height) if height else format_id,
+                        'height': height,
+                    })
+
         self._remove_duplicate_formats(formats)
         self._sort_formats(formats)
 

youtube_dl/extractor/youtube.py

@@ -46,6 +46,10 @@ from ..utils import (
 )
 
 
+def parse_qs(url):
+    return compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+
+
 class YoutubeBaseInfoExtractor(InfoExtractor):
     """Provide base functions for Youtube extractors"""
     _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
@@ -61,11 +65,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
     _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM)'
 
-    def _ids_to_results(self, ids):
-        return [
-            self.url_result(vid_id, 'Youtube', video_id=vid_id)
-            for vid_id in ids]
-
     def _login(self):
         """
         Attempt to log in to YouTube.
@@ -355,21 +354,28 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         r'(?:www\.)?invidious\.mastodon\.host',
         r'(?:www\.)?invidious\.zapashcanon\.fr',
         r'(?:www\.)?invidious\.kavin\.rocks',
+        r'(?:www\.)?invidious\.tinfoil-hat\.net',
+        r'(?:www\.)?invidious\.himiko\.cloud',
+        r'(?:www\.)?invidious\.reallyancient\.tech',
         r'(?:www\.)?invidious\.tube',
         r'(?:www\.)?invidiou\.site',
         r'(?:www\.)?invidious\.site',
         r'(?:www\.)?invidious\.xyz',
         r'(?:www\.)?invidious\.nixnet\.xyz',
+        r'(?:www\.)?invidious\.048596\.xyz',
         r'(?:www\.)?invidious\.drycat\.fr',
+        r'(?:www\.)?inv\.skyn3t\.in',
         r'(?:www\.)?tube\.poal\.co',
         r'(?:www\.)?tube\.connect\.cafe',
         r'(?:www\.)?vid\.wxzm\.sx',
         r'(?:www\.)?vid\.mint\.lgbt',
+        r'(?:www\.)?vid\.puffyan\.us',
         r'(?:www\.)?yewtu\.be',
         r'(?:www\.)?yt\.elukerio\.org',
         r'(?:www\.)?yt\.lelux\.fi',
         r'(?:www\.)?invidious\.ggc-project\.de',
         r'(?:www\.)?yt\.maisputain\.ovh',
+        r'(?:www\.)?ytprivate\.com',
         r'(?:www\.)?invidious\.13ad\.de',
         r'(?:www\.)?invidious\.toot\.koeln',
         r'(?:www\.)?invidious\.fdn\.fr',
@@ -413,16 +419,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                          |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
                          )
                      )?                                                       # all until now is optional -> you can pass the naked ID
-                     (?P<id>[0-9A-Za-z_-]{11})                                      # here is it! the YouTube video ID
+                     (?P<id>[0-9A-Za-z_-]{11})                                # here is it! the YouTube video ID
-                     (?!.*?\blist=
-                        (?:
-                            %(playlist_id)s|                                  # combined list/video URLs are handled by the playlist IE
-                            WL                                                # WL are handled by the watch later IE
-                        )
-                     )
                      (?(1).+)?                                                # if we found the ID, everything can follow
                      $""" % {
-        'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
         'invidious': '|'.join(_INVIDIOUS_SITES),
     }
     _PLAYER_INFO_RE = (
@@ -808,6 +807,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             },
             'skip': 'This video does not exist.',
         },
+        {
+            # Video with incomplete 'yt:stretch=16:'
+            'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
+            'only_matching': True,
+        },
         {
             # Video licensed under Creative Commons
             'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
@@ -1208,6 +1212,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
     }
 
+    @classmethod
+    def suitable(cls, url):
+        # Hack for lazy extractors until more generic solution is implemented
+        # (see #28780)
+        from .youtube import parse_qs
+        qs = parse_qs(url)
+        if qs.get('list', [None])[0]:
+            return False
+        return super(YoutubeIE, cls).suitable(url)
+
     def __init__(self, *args, **kwargs):
         super(YoutubeIE, self).__init__(*args, **kwargs)
         self._code_cache = {}
@@ -1706,13 +1720,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
         for keyword in keywords:
             if keyword.startswith('yt:stretch='):
-                w, h = keyword.split('=')[1].split(':')
+                mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
-                w, h = int(w), int(h)
+                if mobj:
-                if w > 0 and h > 0:
+                    # NB: float is intentional for forcing float division
-                    ratio = w / h
+                    w, h = (float(v) for v in mobj.groups())
-                    for f in formats:
+                    if w > 0 and h > 0:
-                        if f.get('vcodec') != 'none':
+                        ratio = w / h
-                            f['stretched_ratio'] = ratio
+                        for f in formats:
+                            if f.get('vcodec') != 'none':
+                                f['stretched_ratio'] = ratio
+                        break
 
         thumbnails = []
         for container in (video_details, microformat):
@@ -2008,6 +2025,15 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             'title': 'Игорь Клейнер - Playlists',
             'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
         },
+    }, {
+        # playlists, series
+        'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
+        'playlist_mincount': 5,
+        'info_dict': {
+            'id': 'UCYO_jab_esuFRV4b17AJtAw',
+            'title': '3Blue1Brown - Playlists',
+            'description': 'md5:e1384e8a133307dd10edee76e875d62f',
+        },
     }, {
         # playlists, singlepage
         'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
@@ -2275,6 +2301,9 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             'title': '#cctv9',
         },
         'playlist_mincount': 350,
+    }, {
+        'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
+        'only_matching': True,
     }]
 
     @classmethod
@@ -2297,10 +2326,13 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
 
     @staticmethod
     def _extract_grid_item_renderer(item):
-        for item_kind in ('Playlist', 'Video', 'Channel'):
+        assert isinstance(item, dict)
-            renderer = item.get('grid%sRenderer' % item_kind)
+        for key, renderer in item.items():
-            if renderer:
+            if not key.startswith('grid') or not key.endswith('Renderer'):
-                return renderer
+                continue
+            if not isinstance(renderer, dict):
+                continue
+            return renderer
 
     def _grid_entries(self, grid_renderer):
         for item in grid_renderer['items']:
@@ -2310,7 +2342,8 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             if not isinstance(renderer, dict):
                 continue
             title = try_get(
-                renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
+                renderer, (lambda x: x['title']['runs'][0]['text'],
+                           lambda x: x['title']['simpleText']), compat_str)
             # playlist
             playlist_id = renderer.get('playlistId')
             if playlist_id:
@@ -2318,10 +2351,12 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
                     'https://www.youtube.com/playlist?list=%s' % playlist_id,
                     ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
                     video_title=title)
+                continue
             # video
             video_id = renderer.get('videoId')
             if video_id:
                 yield self._extract_video(renderer)
+                continue
             # channel
             channel_id = renderer.get('channelId')
             if channel_id:
@@ -2330,6 +2365,17 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
                 yield self.url_result(
                     'https://www.youtube.com/channel/%s' % channel_id,
                     ie=YoutubeTabIE.ie_key(), video_title=title)
+                continue
+            # generic endpoint URL support
+            ep_url = urljoin('https://www.youtube.com/', try_get(
+                renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
+                compat_str))
+            if ep_url:
+                for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
+                    if ie.suitable(ep_url):
+                        yield self.url_result(
+                            ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
+                        break
 
     def _shelf_entries_from_content(self, shelf_renderer):
         content = shelf_renderer.get('content')
@@ -2764,7 +2810,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         url = compat_urlparse.urlunparse(
             compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
         # Handle both video/playlist URLs
-        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+        qs = parse_qs(url)
         video_id = qs.get('v', [None])[0]
         playlist_id = qs.get('list', [None])[0]
         if video_id and playlist_id:
@@ -2860,12 +2906,19 @@ class YoutubePlaylistIE(InfoExtractor):
 
     @classmethod
     def suitable(cls, url):
-        return False if YoutubeTabIE.suitable(url) else super(
+        if YoutubeTabIE.suitable(url):
-            YoutubePlaylistIE, cls).suitable(url)
+            return False
+        # Hack for lazy extractors until more generic solution is implemented
+        # (see #28780)
+        from .youtube import parse_qs
+        qs = parse_qs(url)
+        if qs.get('v', [None])[0]:
+            return False
+        return super(YoutubePlaylistIE, cls).suitable(url)
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
-        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+        qs = parse_qs(url)
         if not qs:
             qs = {'list': playlist_id}
         return self.url_result(

youtube_dl/utils.py

@@ -39,6 +39,7 @@ import zlib
 from .compat import (
     compat_HTMLParseError,
     compat_HTMLParser,
+    compat_HTTPError,
     compat_basestring,
     compat_chr,
     compat_cookiejar,
@@ -2879,12 +2880,60 @@ class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
 
 
 class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
-    if sys.version_info[0] < 3:
+    """YoutubeDL redirect handler
-        def redirect_request(self, req, fp, code, msg, headers, newurl):
+
-            # On python 2 urlh.geturl() may sometimes return redirect URL
+    The code is based on HTTPRedirectHandler implementation from CPython [1].
-            # as byte string instead of unicode. This workaround allows
+
-            # to force it always return unicode.
+    This redirect handler solves two issues:
-            return compat_urllib_request.HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, headers, compat_str(newurl))
+     - ensures redirect URL is always unicode under python 2
+     - introduces support for experimental HTTP response status code
+       308 Permanent Redirect [2] used by some sites [3]
+
+    1. https://github.com/python/cpython/blob/master/Lib/urllib/request.py
+    2. https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/308
+    3. https://github.com/ytdl-org/youtube-dl/issues/28768
+    """
+
+    http_error_301 = http_error_303 = http_error_307 = http_error_308 = compat_urllib_request.HTTPRedirectHandler.http_error_302
+
+    def redirect_request(self, req, fp, code, msg, headers, newurl):
+        """Return a Request or None in response to a redirect.
+
+        This is called by the http_error_30x methods when a
+        redirection response is received.  If a redirection should
+        take place, return a new Request to allow http_error_30x to
+        perform the redirect.  Otherwise, raise HTTPError if no-one
+        else should try to handle this url.  Return None if you can't
+        but another Handler might.
+        """
+        m = req.get_method()
+        if (not (code in (301, 302, 303, 307, 308) and m in ("GET", "HEAD")
+                 or code in (301, 302, 303) and m == "POST")):
+            raise compat_HTTPError(req.full_url, code, msg, headers, fp)
+        # Strictly (according to RFC 2616), 301 or 302 in response to
+        # a POST MUST NOT cause a redirection without confirmation
+        # from the user (of urllib.request, in this case).  In practice,
+        # essentially all clients do redirect in this case, so we do
+        # the same.
+
+        # On python 2 urlh.geturl() may sometimes return redirect URL
+        # as byte string instead of unicode. This workaround allows
+        # to force it always return unicode.
+        if sys.version_info[0] < 3:
+            newurl = compat_str(newurl)
+
+        # Be conciliant with URIs containing a space.  This is mainly
+        # redundant with the more complete encoding done in http_error_302(),
+        # but it is kept for compatibility with other callers.
+        newurl = newurl.replace(' ', '%20')
+
+        CONTENT_HEADERS = ("content-length", "content-type")
+        # NB: don't use dict comprehension for python 2.6 compatibility
+        newheaders = dict((k, v) for k, v in req.headers.items()
+                          if k.lower() not in CONTENT_HEADERS)
+        return compat_urllib_request.Request(
+            newurl, headers=newheaders, origin_req_host=req.origin_req_host,
+            unverifiable=True)
 
 
 def extract_timezone(date_str):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2021.04.07'
+__version__ = '2021.04.26'