Merge 67d578b0761b2b8b2ae1acbc445191b551c4e6ef 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/extractors.py

@@ -1172,6 +1172,7 @@ from .soundgasm import (
 from .southpark import (
     SouthParkIE,
     SouthParkDeIE,
+    SouthParkDeEnIE,
     SouthParkDkIE,
     SouthParkEsIE,
     SouthParkNlIE

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

@@ -140,6 +140,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
             mediagen_url += '&' if '?' in mediagen_url else '?'
             mediagen_url += 'acceptMethods='
             mediagen_url += 'hls' if use_hls else 'fms'
+        if (self._LANG):
+            mediagen_url += '&' if '?' in mediagen_url else '?'
+            mediagen_url += 'lang=' + self._LANG
 
         mediagen_doc = self._download_xml(
             mediagen_url, video_id, 'Downloading video urls', fatal=False)

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

@@ -54,42 +54,77 @@ class SouthParkEsIE(SouthParkIE):
     }]
 
 
-class SouthParkDeIE(SouthParkIE):
+class SouthParkDeIE(MTVServicesInfoExtractor):
     IE_NAME = 'southpark.de'
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:clips|alle-episoden|collections)/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:videoclip|folgen|collections)/(?P<id>.+?)(\?|#|$))'
-    _FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'
+    _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
+    _LANG = 'de'
 
     _TESTS = [{
-        'url': 'http://www.southpark.de/clips/uygssh/the-government-wont-respect-my-privacy#tab=featured',
+        # clip
+        'url': 'https://www.southpark.de/videoclip/ct46op/south-park-zahnfee-cartman',
         'info_dict': {
-            'id': '85487c96-b3b9-4e39-9127-ad88583d9bf2',
+            'id': 'e99d45ea-ed00-11e0-aca6-0026b9414f30',
             'ext': 'mp4',
-            'title': 'South Park|The Government Won\'t Respect My Privacy',
+            'title': 'Zahnfee Cartman',
-            'description': 'Cartman explains the benefits of "Shitter" to Stan, Kyle and Craig.',
+            'description': 'Cartman verkleidet sich als Zahnfee, um Butters unter dem Kissen liegenden Zahn zu stehlen. Cartman bekommt 4$ für diesen Zahn, was das Streben nach mehr Zähnen nährt'
-            'timestamp': 1380160800,
-            'upload_date': '20130926',
         },
     }, {
-        # non-ASCII characters in initial URL
+        # episode
-        'url': 'http://www.southpark.de/alle-episoden/s18e09-hashtag-aufwärmen',
+        'url': 'https://www.southpark.de/folgen/242csn/south-park-her-mit-dem-hirn-staffel-1-ep-7',
         'info_dict': {
-            'title': 'Hashtag „Aufwärmen“',
+            'id': '607115f3-496f-40c3-8647-2b0bcff486c0',
-            '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.',
+            'ext': 'mp4',
+            'title': 'South Park | Pink Eye | E 0107 | HDSS0107X deu | Version: 634312 | Comedy Central S1',
         },
-        'playlist_count': 3,
-    }, {
-        # non-ASCII characters in redirect URL
-        'url': 'http://www.southpark.de/alle-episoden/s18e09',
-        'info_dict': {
-            'title': 'Hashtag „Aufwärmen“',
-            '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,
-    }, {
-        'url': 'http://www.southpark.de/collections/2476/superhero-showdown/1',
-        'only_matching': True,
     }]
 
+    def _get_feed_query(self, uri):
+        return {
+            'accountOverride': 'intl.mtvi.com',
+            'arcEp': 'shared.southpark.gsa.de',
+            'ep': '50c78199',
+            'imageEp': 'shared.southpark.gsa.de',
+            'clusterName': 'EMEAA',
+            'mgid': uri,
+        }
+
+
+class SouthParkDeEnIE(SouthParkIE):
+    IE_NAME = 'southpark.de:en'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/en/(?:video-clips|episodes|collections)/(?P<id>.+?)(\?|#|$))'
+    _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
+
+    _TESTS = [{
+        # clip
+        'url': 'https://www.southpark.de/en/video-clips/ct46op/south-park-tooth-fairy-cartman',
+        'info_dict': {
+            'id': 'e99d45ea-ed00-11e0-aca6-0026b9414f30',
+            'ext': 'mp4',
+            'title': 'Tooth Fairy Cartman',
+            'description': 'Cartman dresses up as the Tooth Fairy to steal Butters\' tooth from underneath his pillow. Cartman gets $4 for this tooth, feeding the drive for more teeth.',
+        },
+    }, {
+        # episode
+        'url': 'https://www.southpark.de/en/episodes/yy0vjs/south-park-the-pandemic-special-season-24-ep-1',
+        'info_dict': {
+            'id': 'f5fbd823-04bc-11eb-9b1b-0e40cf2fc285',
+            'ext': 'mp4',
+            'title': 'South Park',
+            'description': 'Randy comes to terms with his role in the COVID-19 outbreak as the on-going pandemic presents continued challenges to the citizens of South Park.',
+        },
+    }]
+
+    def _get_feed_query(self, uri):
+        return {
+            'accountOverride': 'intl.mtvi.com',
+            'arcEp': 'shared.southpark.gsa.en',
+            'ep': '20476225',
+            'imageEp': 'shared.southpark.gsa.en',
+            'clusterName': 'EMEAA',
+            'mgid': uri,
+        }
+
 
 class SouthParkNlIE(SouthParkIE):
     IE_NAME = 'southpark.nl'

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: