Merge 08202a62a7251f2a471660bc83a1c2c8340ce52b into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

youtube_dl/extractor/bokecc.py

@@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    _IE_DESC = 'CC视频'
+    IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

youtube_dl/extractor/cloudy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    _IE_DESC = 'cloudy.ec'
+    IE_DESC = 'cloudy.ec'
     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',

youtube_dl/extractor/comedycentral.py

@@ -1,15 +1,22 @@
 from __future__ import unicode_literals
 
+import re
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
+from ..utils import urljoin
+
 from .mtv import MTVServicesInfoExtractor
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?)/(?P<id>[0-9a-z]{6})'
+    _VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?|collection-playlist/[0-9a-z]+/[^/]+)/(?P<id>[0-9a-z]{6})'
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
     _TESTS = [{
         'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
-        'md5': 'b8acb347177c680ff18a292aa2166f80',
+        'md5': '58e7caf5c7c0c865d9d79f7d151e5090',
         'info_dict': {
             'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025',
             'ext': 'mp4',
@@ -18,13 +25,29 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
             'timestamp': 1598670000,
             'upload_date': '20200829',
         },
+        'params': {
+            'hls_prefer_native': False,
+        },
     }, {
         'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314',
         'only_matching': True,
     }, {
         'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
         'only_matching': True,
-    }]
+    }, {
+        'url': 'https://www.cc.com/collection-playlist/8b7hw5/the-daily-shows-summer-exclusives/o2qny3',
+        'info_dict': {
+            'id': '2f56e756-91ec-4d68-8799-e3b710e360e4',
+            'ext': 'mp4',
+            'title': 'The Daily Show with Trevor Noah|August 4, 2021|26|NO-EPISODE#|Hottest Take - The Olympics',
+            'description': 'md5:104484314a4cba36d8c62b094523efc8',
+            'timestamp': 1628125200,
+            'upload_date': '20210805',
+        },
+        'params': {
+            'hls_prefer_native': False,
+        },
+    }, ]
 
 
 class ComedyCentralTVIE(MTVServicesInfoExtractor):
@@ -49,3 +72,99 @@ class ComedyCentralTVIE(MTVServicesInfoExtractor):
             'imageEp': 'web.cc.tv',
             'mgid': uri,
         }
+
+
+class ComedyCentralCollectionIE(ComedyCentralIE):
+    _VALID_URL = r'https?://(?:www\.)?cc\.com/collections/(?P<id>[0-9a-z]{6})(?:/[^/]*)?'
+    _TESTS = [{
+        'url': 'https://www.cc.com/collections/8b7hw5/the-daily-show-s-summer-exclusives',
+        'info_dict': {
+            'id': '8b7hw5',
+            'title': "The Daily Show's Summer Exclusives",
+            'description': 'md5:ae65028fcf8438e65f1c98099119fe6d',
+        },
+        'playlist_mincount': 11,
+    }, ]
+    _CLIP_IE = 'ComedyCentral'
+
+    # we need to know the redirected URL, so stash it in the extractor
+    # strange that this hasn't been a general requirement
+    def _request_webpage(self, url_or_request, video_id,
+                         note=None, errnote=None, fatal=True, data=None,
+                         headers={}, query={}, expected_status=None):
+        urlh = super(ComedyCentralCollectionIE, self)._request_webpage(
+            url_or_request, video_id, note, errnote, fatal,
+            data, headers, query, expected_status)
+        if urlh is not False:
+            self._url = urlh.geturl()
+        elif isinstance(url_or_request, compat_str):
+            self._url = url_or_request
+        else:
+            self._url = url_or_request.get_full_url()
+        return urlh
+
+    def _get_clip_id(self, url):
+        return None
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        url = self._url
+        clip_id = self._get_clip_id(url)
+        if clip_id:
+            url = url.rstrip(clip_id)
+        else:
+            url = url.replace('/collections/', '/collection-playlist/')
+        path = compat_urlparse.urlparse(url).path
+        if path.endswith('/'):
+            path = path[:-1]
+        clip_urls = re.finditer(
+            r'<a\s?[^>]*?href\s*=\s*"(?P<link>%s/(?P<id>[0-9a-z]{6}))"[^<]*>' % path,
+            webpage)
+        playlist_title = (self._html_search_meta('twitter:title', webpage, 'title')
+                          or self._og_search_title(webpage, display_name='title')
+                          or self._html_search_regex(r'<title\s?[^>]*>([^<]+)</',
+                                                     webpage, 'title', default=None))
+        playlist_desc = (self._html_search_meta(('description', 'twitter:description'), webpage)
+                         or self._og_search_description(webpage, display_name='description'))
+        pl = self.playlist_from_matches(clip_urls, playlist_id, playlist_title,
+                                        lambda m: urljoin(url, m.group('link')),
+                                        self._CLIP_IE)
+        if pl:
+            pl['description'] = playlist_desc
+            return pl
+
+
+class ComedyCentralPlaylistIE(ComedyCentralCollectionIE):
+    _VALID_URL = r'https?://(?:www\.)?cc\.com/playlists/(?P<id>[0-9a-z]{6})(?:/(?:[^/]+(?:/(?P<clip_id>[0-9a-z]{6})?)?)?)?'
+    _TESTS = [{
+        'url': 'https://www.cc.com/playlists/mym6e5/corporate-working-nine-to-five',
+        'info_dict': {
+            'id': 'mym6e5',
+            'title': 'Coffee Break - Corporate | Comedy Central US',
+            'description': 'md5:89bc6e8e983ad34ded85af84108f6ea8',
+        },
+        'playlist_mincount': 5,
+    }, {
+        'url': 'https://www.cc.com/playlists/mym6e5/corporate-working-nine-to-five/dm8ekc',
+        'only_matching': True,
+    }, ]
+
+    def _get_clip_id(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        return mobj.group('clip_id')
+
+    def _real_initialize(self):
+        self._CLIP_IE = self.IE_NAME
+
+    def _real_extract(self, url):
+        if self._get_clip_id(url):
+            return ComedyCentralIE._real_extract(self, url)
+        playlist_id = self._match_id(url)
+        if self._downloader.params.get('noplaylist', False):
+            _ = self._download_webpage(url, playlist_id)
+            if self._get_clip_id(self._url):
+                self.to_screen(
+                    'Downloading just the "now playing" clip because of --no-playlist')
+                return self.url_result(self._url, self._CLIP_IE, playlist_id)
+        return super(ComedyCentralPlaylistIE, self)._real_extract(url)

youtube_dl/extractor/common.py

@@ -422,6 +422,8 @@ class InfoExtractor(object):
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
+    # supply this in public subclasses: used in supported sites list, etc
+    # IE_DESC = 'short description of IE'
 
     def __init__(self, downloader=None):
         """Constructor. Receives an optional downloader."""

youtube_dl/extractor/extractors.py

@@ -251,6 +251,8 @@ from .coub import CoubIE
 from .comedycentral import (
     ComedyCentralIE,
     ComedyCentralTVIE,
+    ComedyCentralCollectionIE,
+    ComedyCentralPlaylistIE,
 )
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .commonprotocols import (

youtube_dl/extractor/generic.py

@@ -903,6 +903,9 @@ class GenericIE(InfoExtractor):
                 'timestamp': 1349922600,
                 'upload_date': '20121011',
             },
+            'params': {
+                'hls-prefer-native': False,
+            },
         },
         # YouTube embed via <data-embed-url="">
         {

youtube_dl/extractor/itv.py

@@ -35,15 +35,6 @@ from ..utils import (
 
 class ITVBaseIE(InfoExtractor):
 
-    def _search_nextjs_data(self, webpage, video_id, **kw):
-        transform_source = kw.pop('transform_source', None)
-        fatal = kw.pop('fatal', True)
-        return self._parse_json(
-            self._search_regex(
-                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
-                webpage, 'next.js data', group='js', fatal=fatal, **kw),
-            video_id, transform_source=transform_source, fatal=fatal)
-
     def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
         if errnote is False:
             return False
@@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
 
 class ITVIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
-    _IE_DESC = 'ITVX'
+    IE_DESC = 'ITVX'
+    _WORKING = False
+
     _TESTS = [{
         'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
         video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
         title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
         info = self._og_extract(webpage, require_title=not title)
@@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
 
 class ITVBTCCIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    IE_DESC = 'ITV articles: News, British Touring Car Championship'
     _TESTS = [{
         'note': 'British Touring Car Championship',
         'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

youtube_dl/extractor/mtv.py

@@ -229,6 +229,8 @@ class MTVServicesInfoExtractor(InfoExtractor):
             if info:
                 entries.append(info)
 
+        if len(entries) == 1:
+            return entries[0]
         return self.playlist_result(
             entries, playlist_title=title, playlist_description=description)
 
@@ -290,7 +292,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
             main_container = self._extract_child_with_type(data, 'MainContainer')
             ab_testing = self._extract_child_with_type(main_container, 'ABTesting')
             video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer')
-            mgid = video_player['props']['media']['video']['config']['uri']
+            mgid = try_get(video_player, lambda x: x['props']['media']['video']['config']['uri'])
 
         return mgid
 
@@ -298,7 +300,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
         title = url_basename(url)
         webpage = self._download_webpage(url, title)
         mgid = self._extract_mgid(webpage)
+        if not mgid:
+            raise ExtractorError('Unable to determine MTVServices ID (mgid)', expected=True)
         videos_info = self._get_videos_info(mgid)
+        if videos_info and videos_info.get('_type') != 'playlist':
+            videos_info['display_id'] = title
         return videos_info
 
 

youtube_dl/extractor/senateisvp.py

@@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
-    _IE_NAME = 'senate.gov'
+    IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

youtube_dl/jsinterp.py

@@ -686,6 +686,8 @@ class JSInterpreter(object):
             raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
     def _dump(self, obj, namespace):
+        if obj is JS_Undefined:
+            return 'undefined'
         try:
             return json.dumps(obj)
         except TypeError: