.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 2020.11.18. 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 Issues with outdated version will be REJECTED.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 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2020.11.18**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.17**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.11.18
+ [debug] youtube-dl version 2020.11.17
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.18. 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 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2020.11.18**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.17**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.18. 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 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.11.18**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.17**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.18. 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 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2020.11.18**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.17**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] youtube-dl version 2020.11.18
+ [debug] youtube-dl version 2020.11.17
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.18. 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 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2020.11.18**
+- [ ] I've verified that I'm running youtube-dl version **2020.11.17**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

ChangeLog

@@ -1,19 +1,3 @@
-version 2020.11.18
-
-Extractors
-* [spiegel] Fix extraction (#24206, #24767)
-* [youtube] Improve extraction
-    + Add support for --no-playlist (#27009)
-    * Improve playlist and mix extraction (#26390, #26509, #26534, #27011)
-    + Extract playlist uploader data
-* [youtube:tab] Fix view count extraction (#27051)
-* [malltv] Fix extraction (#27035)
-+ [bandcamp] Extract playlist description (#22684)
-* [urplay] Fix extraction (#26828)
-* [youtube:tab] Fix playlist title extraction (#27015)
-* [youtube] Fix chapters extraction (#26005)
-
-
 version 2020.11.17
 
 Core

docs/supportedsites.md

@@ -824,6 +824,8 @@
  - **SpankBangPlaylist**
  - **Spankwire**
  - **Spiegel**
+ - **Spiegel:Article**: Articles on spiegel.de
+ - **Spiegeltv**
  - **sport.francetvinfo.fr**
  - **Sport5**
  - **SportBox**

test/test_all_urls.py

@@ -31,17 +31,16 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_youtube_playlist_matching(self):
         assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
-        assertTab = lambda url: self.assertMatch(url, ['youtube:tab'])
         assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
         assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q')  # 585
         assertPlaylist('PL63F0C78739B09958')
-        assertTab('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
+        # assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
         assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        assertTab('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
+        # assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        assertTab('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')  # 668
+        assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')  # 668
         self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
         # Top tracks
-        assertTab('https://www.youtube.com/playlist?list=MCUS.20142101')
+        # assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
 
     def test_youtube_matching(self):
         self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))

youtube_dl/extractor/extractors.py

@@ -1054,7 +1054,8 @@ from .spankbang import (
     SpankBangPlaylistIE,
 )
 from .spankwire import SpankwireIE
-from .spiegel import SpiegelIE
+from .spiegel import SpiegelIE, SpiegelArticleIE
+from .spiegeltv import SpiegeltvIE
 from .spike import (
     BellatorIE,
     ParamountNetworkIE,

youtube_dl/extractor/malltv.py

@@ -1,16 +1,10 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
-from ..utils import (
+from ..utils import merge_dicts
-    clean_html,
-    dict_get,
-    float_or_none,
-    int_or_none,
-    merge_dicts,
-    parse_duration,
-    try_get,
-)
 
 
 class MallTVIE(InfoExtractor):
@@ -23,7 +17,7 @@ class MallTVIE(InfoExtractor):
             'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
             'ext': 'mp4',
             'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
-            'description': 'md5:db7d5744a4bd4043d9d98324aa72ab35',
+            'description': 'md5:25fc0ec42a72ba602b602c683fa29deb',
             'duration': 216,
             'timestamp': 1538870400,
             'upload_date': '20181007',
@@ -43,46 +37,20 @@ class MallTVIE(InfoExtractor):
         webpage = self._download_webpage(
             url, display_id, headers=self.geo_verification_headers())
 
-        video = self._parse_json(self._search_regex(
+        SOURCE_RE = r'(<source[^>]+\bsrc=(?:(["\'])(?:(?!\2).)+|[^\s]+)/(?P<id>[\da-z]+)/index)\b'
-            r'videoObject\s*=\s*JSON\.parse\(JSON\.stringify\(({.+?})\)\);',
-            webpage, 'video object'), display_id)
-        video_source = video['VideoSource']
         video_id = self._search_regex(
-            r'/([\da-z]+)/index\b', video_source, 'video id')
+            SOURCE_RE, webpage, 'video id', group='id')
 
-        formats = self._extract_m3u8_formats(
+        media = self._parse_html5_media_entries(
-            video_source + '.m3u8', video_id, 'mp4', 'm3u8_native')
+            url, re.sub(SOURCE_RE, r'\1.m3u8', webpage), video_id,
-        self._sort_formats(formats)
+            m3u8_id='hls', m3u8_entry_protocol='m3u8_native')[0]
-
-        subtitles = {}
-        for s in (video.get('Subtitles') or {}):
-            s_url = s.get('Url')
-            if not s_url:
-                continue
-            subtitles.setdefault(s.get('Language') or 'cz', []).append({
-                'url': s_url,
-            })
-
-        entity_counts = video.get('EntityCounts') or {}
-
-        def get_count(k):
-            v = entity_counts.get(k + 's') or {}
-            return int_or_none(dict_get(v, ('Count', 'StrCount')))
 
         info = self._search_json_ld(webpage, video_id, default={})
 
-        return merge_dicts({
+        return merge_dicts(media, info, {
             'id': video_id,
             'display_id': display_id,
-            'title': video.get('Title'),
+            'title': self._og_search_title(webpage, default=None) or display_id,
-            'description': clean_html(video.get('Description')),
+            'description': self._og_search_description(webpage, default=None),
-            'thumbnail': video.get('ThumbnailUrl'),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
-            'formats': formats,
+        })
-            'subtitles': subtitles,
-            'duration': int_or_none(video.get('DurationSeconds')) or parse_duration(video.get('Duration')),
-            'view_count': get_count('View'),
-            'like_count': get_count('Like'),
-            'dislike_count': get_count('Dislike'),
-            'average_rating': float_or_none(try_get(video, lambda x: x['EntityRating']['AvarageRate'])),
-            'comment_count': get_count('Comment'),
-        }, info)

youtube_dl/extractor/spiegel.py

@@ -1,54 +1,159 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
-from .jwplatform import JWPlatformIE
+from .nexx import (
+    NexxIE,
+    NexxEmbedIE,
+)
+from .spiegeltv import SpiegeltvIE
+from ..compat import compat_urlparse
+from ..utils import (
+    parse_duration,
+    strip_or_none,
+    unified_timestamp,
+)
 
 
 class SpiegelIE(InfoExtractor):
-    _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$'
-    _VALID_URL = r'https?://(?:www\.)?(?:spiegel|manager-magazin)\.de(?:/[^/]+)+/[^/]*-(?P<id>[0-9]+|%s)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' % _UUID_RE
     _TESTS = [{
         'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
-        'md5': '50c7948883ec85a3e431a0a44b7ad1d6',
+        'md5': 'b57399839d055fccfeb9a0455c439868',
         'info_dict': {
-            'id': 'II0BUyxY',
+            'id': '563747',
-            'display_id': '1259285',
             'ext': 'mp4',
-            'title': 'Vulkan Tungurahua in Ecuador ist wieder aktiv - DER SPIEGEL - Wissenschaft',
+            'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv',
             'description': 'md5:8029d8310232196eb235d27575a8b9f4',
-            'duration': 48.0,
+            'duration': 49,
             'upload_date': '20130311',
-            'timestamp': 1362997920,
+            'timestamp': 1362994320,
         },
     }, {
         'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
+        'md5': '5b6c2f4add9d62912ed5fc78a1faed80',
+        'info_dict': {
+            'id': '580988',
+            'ext': 'mp4',
+            'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
+            'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
+            'duration': 983,
+            'upload_date': '20131115',
+            'timestamp': 1384546642,
+        },
+    }, {
+        'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
+        'md5': '97b91083a672d72976faa8433430afb9',
+        'info_dict': {
+            'id': '601883',
+            'ext': 'mp4',
+            'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.',
+            'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
+            'upload_date': '20140904',
+            'timestamp': 1409834160,
+        }
+    }, {
+        'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
         'only_matching': True,
     }, {
-        'url': 'https://www.spiegel.de/video/eifel-zoo-aufregung-um-ausgebrochene-raubtiere-video-99018031.html',
+        # nexx video
-        'only_matching': True,
-    }, {
-        'url': 'https://www.spiegel.de/panorama/urteile-im-goldmuenzenprozess-haftstrafen-fuer-clanmitglieder-a-aae8df48-43c1-4c61-867d-23f0a2d254b7',
-        'only_matching': True,
-    }, {
         'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html',
         'only_matching': True,
-    }, {
-        'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
-        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        metadata_url = 'http://www.spiegel.de/video/metadata/video-%s.json' % video_id
-        media_id = self._html_search_regex(
+        handle = self._request_webpage(metadata_url, video_id)
-            r'(&#34;|["\'])mediaId\1\s*:\s*(&#34;|["\'])(?P<id>(?:(?!\2).)+)\2',
+
-            webpage, 'media id', group='id')
+        # 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html
+        if SpiegeltvIE.suitable(handle.geturl()):
+            return self.url_result(handle.geturl(), 'Spiegeltv')
+
+        video_data = self._parse_json(self._webpage_read_content(
+            handle, metadata_url, video_id), video_id)
+        title = video_data['title']
+        nexx_id = video_data['nexxOmniaId']
+        domain_id = video_data.get('nexxOmniaDomain') or '748'
+
         return {
             '_type': 'url_transparent',
             'id': video_id,
-            'display_id': video_id,
+            'url': 'nexx:%s:%s' % (domain_id, nexx_id),
-            'url': 'jwplatform:%s' % media_id,
+            'title': title,
-            'title': self._og_search_title(webpage, default=None),
+            'description': strip_or_none(video_data.get('teaser')),
-            'ie_key': JWPlatformIE.ie_key(),
+            'duration': parse_duration(video_data.get('duration')),
+            'timestamp': unified_timestamp(video_data.get('datum')),
+            'ie_key': NexxIE.ie_key(),
         }
+
+
+class SpiegelArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
+    IE_NAME = 'Spiegel:Article'
+    IE_DESC = 'Articles on spiegel.de'
+    _TESTS = [{
+        'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
+        'info_dict': {
+            'id': '1516455',
+            'ext': 'mp4',
+            'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
+            'description': 're:^Patrick Kämnitz gehört.{100,}',
+            'upload_date': '20140825',
+        },
+    }, {
+        'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html',
+        'info_dict': {
+
+        },
+        'playlist_count': 6,
+    }, {
+        # Nexx iFrame embed
+        'url': 'http://www.spiegel.de/sptv/spiegeltv/spiegel-tv-ueber-schnellste-katapult-achterbahn-der-welt-taron-a-1137884.html',
+        'info_dict': {
+            'id': '161464',
+            'ext': 'mp4',
+            'title': 'Nervenkitzel Achterbahn',
+            'alt_title': 'Karussellbauer in Deutschland',
+            'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
+            'release_year': 2005,
+            'creator': 'SPIEGEL TV',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 2761,
+            'timestamp': 1394021479,
+            'upload_date': '20140305',
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        # Single video on top of the page
+        video_link = self._search_regex(
+            r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
+            'video page URL', default=None)
+        if video_link:
+            video_url = compat_urlparse.urljoin(
+                self.http_scheme() + '//spiegel.de/', video_link)
+            return self.url_result(video_url)
+
+        # Multiple embedded videos
+        embeds = re.findall(
+            r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"',
+            webpage)
+        entries = [
+            self.url_result(compat_urlparse.urljoin(
+                self.http_scheme() + '//spiegel.de/', embed_path))
+            for embed_path in embeds]
+        if embeds:
+            return self.playlist_result(entries)
+
+        return self.playlist_from_matches(
+            NexxEmbedIE._extract_urls(webpage), ie=NexxEmbedIE.ie_key())

youtube_dl/extractor/spiegeltv.py

@@ -0,0 +1,17 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .nexx import NexxIE
+
+
+class SpiegeltvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/videos/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.spiegel.tv/videos/161681-flug-mh370/',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        return self.url_result(
+            'https://api.nexx.cloud/v3/748/videos/byid/%s'
+            % self._match_id(url), ie=NexxIE.ie_key())

youtube_dl/extractor/youtube.py

@@ -45,7 +45,6 @@ from ..utils import (
     unescapeHTML,
     unified_strdate,
     unsmuggle_url,
-    update_url_query,
     uppercase_escape,
     url_or_none,
     urlencode_postdata,
@@ -66,7 +65,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
     # If True it will raise an error if no login info is provided
     _LOGIN_REQUIRED = False
 
-    _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM)'
+    _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',
@@ -975,6 +974,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'sJL6WA-aGkQ',
             'only_matching': True,
         },
+        {
+            'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
+            'only_matching': True,
+        },
         {
             'url': 'https://invidio.us/watch?v=BaW_jenozKc',
             'only_matching': True,
@@ -2348,7 +2351,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
 class YoutubeTabIE(YoutubeBaseInfoExtractor):
     IE_DESC = 'YouTube.com tab'
-    _VALID_URL = r'https?://(?:\w+\.)?(?:youtube(?:kids)?\.com|invidio\.us)/(?:(?:channel|c|user)/|(?:playlist|watch)\?.*?\blist=)(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:\w+\.)?(?:youtube(?:kids)?\.com|invidio\.us)/(?:(?:channel|c|user)/|playlist\?.*?\blist=)(?P<id>[^/?#&]+)'
     IE_NAME = 'youtube:tab'
 
     _TESTS = [{
@@ -2358,7 +2361,6 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'id': 'UCqj7Cz7revf5maW9g5pgNcg',
             'title': 'Игорь Клейнер - Playlists',
-            'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
         },
     }, {
         # playlists, multipage, different order
@@ -2367,16 +2369,14 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'id': 'UCqj7Cz7revf5maW9g5pgNcg',
             'title': 'Игорь Клейнер - Playlists',
-            'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
         },
     }, {
         # playlists, singlepage
         'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
         'playlist_mincount': 4,
         'info_dict': {
-            'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
+            'id': 'ThirstForScience',
-            'title': 'ThirstForScience - Playlists',
+            'title': 'ThirstForScience',
-            'description': 'md5:609399d937ea957b0f53cbffb747a14c',
         }
     }, {
         'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
@@ -2407,7 +2407,6 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
             'title': 'lex will - Home',
-            'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
         },
         'playlist_mincount': 2,
     }, {
@@ -2416,7 +2415,6 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
             'title': 'lex will - Videos',
-            'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
         },
         'playlist_mincount': 975,
     }, {
@@ -2425,7 +2423,6 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
             'title': 'lex will - Videos',
-            'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
         },
         'playlist_mincount': 199,
     }, {
@@ -2434,7 +2431,6 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
             'title': 'lex will - Playlists',
-            'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
         },
         'playlist_mincount': 17,
     }, {
@@ -2443,7 +2439,6 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
             'title': 'lex will - Community',
-            'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
         },
         'playlist_mincount': 18,
     }, {
@@ -2452,7 +2447,6 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
             'title': 'lex will - Channels',
-            'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
         },
         'playlist_mincount': 138,
     }, {
@@ -2471,7 +2465,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             'title': '29C3: Not my department',
             'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
             'uploader': 'Christiaan008',
-            'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
+            'uploader_id': 'ChRiStIaAn008',
         },
         'playlist_count': 96,
     }, {
@@ -2481,7 +2475,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             'title': 'Uploads from Cauchemar',
             'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
             'uploader': 'Cauchemar',
-            'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
+            'uploader_id': 'Cauchemar89',
         },
         'playlist_mincount': 1123,
     }, {
@@ -2495,7 +2489,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             'title': 'Uploads from Interstellar Movie',
             'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
             'uploader': 'Interstellar Movie',
-            'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
+            'uploader_id': 'InterstellarMovie1',
         },
         'playlist_mincount': 21,
     }, {
@@ -2504,43 +2498,13 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'title': 'Data Analysis with Dr Mike Pound',
             'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
-            'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
+            'uploader_id': 'Computerphile',
             'uploader': 'Computerphile',
         },
         'playlist_mincount': 11,
     }, {
         'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
         'only_matching': True,
-    }, {
-        # Playlist URL that does not actually serve a playlist
-        'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
-        'info_dict': {
-            'id': 'FqZTN594JQw',
-            'ext': 'webm',
-            'title': "Smiley's People 01 detective, Adventure Series, Action",
-            'uploader': 'STREEM',
-            'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
-            'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
-            'upload_date': '20150526',
-            'license': 'Standard YouTube License',
-            'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
-            'categories': ['People & Blogs'],
-            'tags': list,
-            'view_count': int,
-            'like_count': int,
-            'dislike_count': int,
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'skip': 'This video is not available.',
-        'add_ie': [YoutubeIE.ie_key()],
-    }, {
-        'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
-        'only_matching': True,
     }]
 
     @classmethod
@@ -2571,9 +2535,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
     def _extract_video(self, renderer):
         video_id = renderer.get('videoId')
         title = try_get(
-            renderer,
+            renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
-            (lambda x: x['title']['runs'][0]['text'],
-             lambda x: x['title']['simpleText']), compat_str)
         description = try_get(
             renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
             compat_str)
@@ -2581,8 +2543,8 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             renderer, lambda x: x['lengthText']['simpleText'], compat_str))
         view_count_text = try_get(
             renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
-        view_count = str_to_int(self._search_regex(
+        view_count = int_or_none(self._search_regex(
-            r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
+            r'^(\d+)', re.sub(r'\s', '', view_count_text),
             'view count', default=None))
         uploader = try_get(
             renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
@@ -2653,7 +2615,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         for content in video_list_renderer['contents']:
             if not isinstance(content, dict):
                 continue
-            renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
+            renderer = content.get('playlistVideoRenderer')
             if not isinstance(renderer, dict):
                 continue
             video_id = renderer.get('videoId')
@@ -2753,7 +2715,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
 
     def _entries(self, tab, identity_token):
         continuation = None
-        slr_contents = try_get(tab, lambda x: x['sectionListRenderer']['contents'], list) or []
+        slr_contents = tab['sectionListRenderer']['contents']
         for slr_content in slr_contents:
             if not isinstance(slr_content, dict):
                 continue
@@ -2862,30 +2824,13 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         else:
             raise ExtractorError('Unable to find selected tab')
 
-    @staticmethod
+    def _real_extract(self, url):
-    def _extract_uploader(data):
+        item_id = self._match_id(url)
-        uploader = {}
+        url = compat_urlparse.urlunparse(
-        sidebar_renderer = try_get(
+            compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
-            data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list)
+        webpage = self._download_webpage(url, item_id)
-        if sidebar_renderer:
+        data = self._extract_yt_initial_data(item_id, webpage)
-            for item in sidebar_renderer:
+        tabs = data['contents']['twoColumnBrowseResultsRenderer']['tabs']
-                if not isinstance(item, dict):
-                    continue
-                renderer = item.get('playlistSidebarSecondaryInfoRenderer')
-                if not isinstance(renderer, dict):
-                    continue
-                owner = try_get(
-                    renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
-                if owner:
-                    uploader['uploader'] = owner.get('text')
-                    uploader['uploader_id'] = try_get(
-                        owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
-                    uploader['uploader_url'] = urljoin(
-                        'https://www.youtube.com/',
-                        try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
-        return uploader
-
-    def _extract_from_tabs(self, item_id, webpage, data, tabs, identity_token):
         selected_tab = self._extract_selected_tab(tabs)
         renderer = try_get(
             data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
@@ -2903,69 +2848,42 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             title = renderer.get('title')
             description = None
             playlist_id = item_id
-        playlist = self.playlist_result(
-            self._entries(selected_tab['content'], identity_token),
-            playlist_id=playlist_id, playlist_title=title,
-            playlist_description=description)
-        playlist.update(self._extract_uploader(data))
-        return playlist
-
-    def _extract_from_playlist(self, item_id, data, playlist):
-        title = playlist.get('title') or try_get(
-            data, lambda x: x['titleText']['simpleText'], compat_str)
-        playlist_id = playlist.get('playlistId') or item_id
-        return self.playlist_result(
-            self._playlist_entries(playlist), playlist_id=playlist_id,
-            playlist_title=title)
-
-    def _real_extract(self, url):
-        item_id = self._match_id(url)
-        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)
-        video_id = qs.get('v', [None])[0]
-        playlist_id = qs.get('list', [None])[0]
-        if video_id and playlist_id:
-            if self._downloader.params.get('noplaylist'):
-                self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
-                return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
-            self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
-        webpage = self._download_webpage(url, item_id)
         identity_token = self._search_regex(
             r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
             'identity token', default=None)
-        data = self._extract_yt_initial_data(item_id, webpage)
+        return self.playlist_result(
-        tabs = try_get(
+            self._entries(selected_tab['content'], identity_token),
-            data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
+            playlist_id=playlist_id, playlist_title=title,
-        if tabs:
+            playlist_description=description)
-            return self._extract_from_tabs(item_id, webpage, data, tabs, identity_token)
-        playlist = try_get(
-            data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
-        if playlist:
-            return self._extract_from_playlist(item_id, data, playlist)
-        # Fallback to video extraction if no playlist alike page is recognized
-        if video_id:
-            return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
-        # Failed to recognize
-        raise ExtractorError('Unable to recognize tab page')
 
 
 class YoutubePlaylistIE(InfoExtractor):
     IE_DESC = 'YouTube.com playlists'
-    _VALID_URL = r'''(?x)(?:
+    _VALID_URL = r"""(?x)(?:
                         (?:https?://)?
                         (?:\w+\.)?
                         (?:
                             (?:
                                 youtube(?:kids)?\.com|
-                                invidio\.us|
+                                invidio\.us
-                                youtu\.be
                             )
-                            /.*?\?.*?\blist=
+                            /
-                        )?
+                            (?:
-                        (?P<id>%(playlist_id)s)
+                               (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
-                     )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
+                               \? (?:.*?[&;])*? (?:p|a|list)=
+                            |  p/
+                            )|
+                            youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
+                        )
+                        (
+                            (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,}
+                            # Top tracks, they can also include dots
+                            |(?:MC)[\w\.]*
+                        )
+                        .*
+                     |
+                        (%(playlist_id)s)
+                     )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
     IE_NAME = 'youtube:playlist'
     _TESTS = [{
         'note': 'issue #673',
@@ -2974,7 +2892,7 @@ class YoutubePlaylistIE(InfoExtractor):
             'title': '[OLD]Team Fortress 2 (Class-based LP)',
             'id': 'PLBB231211A4F62143',
             'uploader': 'Wickydoo',
-            'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
+            'uploader_id': 'Wickydoo',
         },
         'playlist_mincount': 29,
     }, {
@@ -3002,8 +2920,41 @@ class YoutubePlaylistIE(InfoExtractor):
             'title': '2018 Chinese New Singles (11/6 updated)',
             'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
             'uploader': 'LBK',
-            'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
+            'uploader_id': 'sdragonfang',
         }
+    }, {
+        'note': 'Embedded SWF player',
+        'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
+        'playlist_count': 4,
+        'info_dict': {
+            'title': 'JODA7',
+            'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
+        },
+        'skip': 'This playlist does not exist',
+    }, {
+        # Playlist URL that does not actually serve a playlist
+        'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
+        'info_dict': {
+            'id': 'FqZTN594JQw',
+            'ext': 'webm',
+            'title': "Smiley's People 01 detective, Adventure Series, Action",
+            'uploader': 'STREEM',
+            'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
+            'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
+            'upload_date': '20150526',
+            'license': 'Standard YouTube License',
+            'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
+            'categories': ['People & Blogs'],
+            'tags': list,
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'skip': 'This video is not available.',
+        'add_ie': [YoutubeIE.ie_key()],
     }, {
         'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
         'info_dict': {
@@ -3034,6 +2985,9 @@ class YoutubePlaylistIE(InfoExtractor):
         # music album playlist
         'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
         'only_matching': True,
+    }, {
+        'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
+        'only_matching': True,
     }]
 
     @classmethod
@@ -3042,12 +2996,13 @@ class YoutubePlaylistIE(InfoExtractor):
             YoutubePlaylistIE, cls).suitable(url)
 
     def _real_extract(self, url):
-        playlist_id = self._match_id(url)
+        # Extract playlist id
-        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+        mobj = re.match(self._VALID_URL, url)
-        if not qs:
+        if mobj is None:
-            qs = {'list': playlist_id}
+            raise ExtractorError('Invalid URL: %s' % url)
+        playlist_id = mobj.group(1) or mobj.group(2)
         return self.url_result(
-            update_url_query('https://www.youtube.com/playlist', qs),
+            'https://www.youtube.com/playlist?list=%s' % playlist_id,
             ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
 
 
@@ -3295,13 +3250,13 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
 class YoutubeWatchLaterIE(InfoExtractor):
     IE_NAME = 'youtube:watchlater'
     IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
-    _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/watch_later|:ytwatchlater'
+    _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
 
     _TESTS = [{
-        'url': 'https://www.youtube.com/feed/watch_later',
+        'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
         'only_matching': True,
     }, {
-        'url': ':ytwatchlater',
+        'url': 'https://www.youtube.com/feed/watch_later',
         'only_matching': True,
     }]
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2020.11.18'
+__version__ = '2020.11.17'