Merge 44f73880fed2cd1f4095fb1af7641bf82563ab4a 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/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/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

@@ -157,7 +157,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
 
         description = strip_or_none(xpath_text(itemdoc, 'description'))
 
-        timestamp = timeconvert(xpath_text(itemdoc, 'pubDate'))
+        timestamp = timeconvert(xpath_text(itemdoc, 'pubDate') or xpath_text(itemdoc, 'airDate'))
 
         title_el = None
         if title_el is None:
@@ -290,7 +290,17 @@ 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']
+            if video_player:
+                mgid = video_player['props']['media']['video']['config']['uri']
+            else:
+                flex_wrapper = self._extract_child_with_type(ab_testing or main_container, 'FlexWrapper')
+                auth_suite_wrapper = self._extract_child_with_type(flex_wrapper, 'AuthSuiteWrapper')
+                player = self._extract_child_with_type(auth_suite_wrapper or flex_wrapper, 'Player')
+                if player:
+                    mgid = player['props']['videoDetail']['mgid']
+
+        if not mgid:
+            raise ExtractorError('Could not extract mgid')
 
         return mgid
 

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/extractor/southpark.py

@@ -6,19 +6,19 @@ from .mtv import MTVServicesInfoExtractor
 
 class SouthParkIE(MTVServicesInfoExtractor):
     IE_NAME = 'southpark.cc.com'
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark(?:\.cc|studios)\.com/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark(?:\.cc|studios)\.com/((?:video-)?clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))'
 
     _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
 
     _TESTS = [{
-        'url': 'http://southpark.cc.com/clips/104437/bat-daded#tab=featured',
+        'url': 'https://southpark.cc.com/video-clips/d7wr06/south-park-you-all-agreed-to-counseling',
         'info_dict': {
-            'id': 'a7bff6c2-ed00-11e0-aca6-0026b9414f30',
+            'id': '31929ad5-8269-11eb-8774-70df2f866ace',
             'ext': 'mp4',
-            'title': 'South Park|Bat Daded',
+            'title': 'You All Agreed to Counseling',
-            'description': 'Randy disqualifies South Park by getting into a fight with Bat Dad.',
+            'description': 'Kenny, Cartman, Stan, and Kyle visit Mr. Mackey and ask for his help getting Mrs. Nelson to come back. Mr. Mackey reveals the only way to get things back to normal is to get the teachers vaccinated.',
-            'timestamp': 1112760000,
+            'timestamp': 1615377600,
-            'upload_date': '20050406',
+            'upload_date': '20210310',
         },
     }, {
         'url': 'http://southpark.cc.com/collections/7758/fan-favorites/1',
@@ -40,11 +40,11 @@ class SouthParkIE(MTVServicesInfoExtractor):
 
 class SouthParkEsIE(SouthParkIE):
     IE_NAME = 'southpark.cc.com:español'
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/episodios-en-espanol/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/es/episodios/(?P<id>.+?)(\?|#|$))'
     _LANG = 'es'
 
     _TESTS = [{
-        'url': 'http://southpark.cc.com/episodios-en-espanol/s01e01-cartman-consigue-una-sonda-anal#source=351c1323-0b96-402d-a8b9-40d01b2e9bde&position=1&sort=!airdate',
+        'url': 'http://southpark.cc.com/es/episodios/s01e01-cartman-consigue-una-sonda-anal#source=351c1323-0b96-402d-a8b9-40d01b2e9bde&position=1&sort=!airdate',
         'info_dict': {
             'title': 'Cartman Consigue Una Sonda Anal',
             'description': 'Cartman Consigue Una Sonda Anal',
@@ -69,6 +69,7 @@ class SouthParkDeIE(SouthParkIE):
             'timestamp': 1380160800,
             'upload_date': '20130926',
         },
+        'skip': 'Geo-restricted',
     }, {
         # non-ASCII characters in initial URL
         'url': 'http://www.southpark.de/alle-episoden/s18e09-hashtag-aufwärmen',
@@ -77,6 +78,7 @@ class SouthParkDeIE(SouthParkIE):
             'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.',
         },
         'playlist_count': 3,
+        'skip': 'Geo-restricted',
     }, {
         # non-ASCII characters in redirect URL
         'url': 'http://www.southpark.de/alle-episoden/s18e09',
@@ -85,6 +87,7 @@ class SouthParkDeIE(SouthParkIE):
             'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.',
         },
         'playlist_count': 3,
+        'skip': 'Geo-restricted',
     }, {
         'url': 'http://www.southpark.de/collections/2476/superhero-showdown/1',
         'only_matching': True,
@@ -103,6 +106,7 @@ class SouthParkNlIE(SouthParkIE):
             'description': 'Stan is addicted to the new Terrance and Phillip mobile game.',
         },
         'playlist_mincount': 3,
+        'skip': 'Geo-restricted',
     }]
 
 
@@ -118,6 +122,7 @@ class SouthParkDkIE(SouthParkIE):
             'description': 'Butters is convinced he\'s living in a virtual reality.',
         },
         'playlist_mincount': 3,
+        'skip': 'Geo-restricted',
     }, {
         'url': 'http://www.southparkstudios.dk/collections/2476/superhero-showdown/1',
         'only_matching': True,

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:

youtube_dl/utils.py

@@ -2079,7 +2079,7 @@ def timeconvert(timestr):
     timetuple = email.utils.parsedate_tz(timestr)
     if timetuple is not None:
         timestamp = email.utils.mktime_tz(timetuple)
-    return timestamp
+    return int(timestamp) if timestamp is not None else timestamp
 
 
 def sanitize_filename(s, restricted=False, is_id=False):