Merge f2a095884c293ebffd2363dc5b24c644bf6f4837 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/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/xvideos.py

@@ -10,6 +10,8 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     parse_duration,
+    str_to_int,
+    urljoin,
 )
 
 
@@ -25,14 +27,21 @@ class XVideosIE(InfoExtractor):
                         (?P<id>[0-9]+)
                     '''
     _TESTS = [{
-        'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
-        'md5': '14cea69fcb84db54293b1e971466c2e1',
+        'url': 'https://www.xvideos.com/video50011247/when_girls_play_-_adriana_chechik_abella_danger_-_tradimento_-_twistys',
+        'md5': 'aa54f96311768b3a8bfe54b8c8fda070',
         'info_dict': {
-            'id': '4588838',
+            'id': '50011247',
             'ext': 'mp4',
-            'title': 'Biker Takes his Girl',
-            'duration': 108,
+            'title': 'When Girls Play - (Adriana Chechik, Abella Danger) - Betrayal - Twistys',
+            'duration': 720,
             'age_limit': 18,
+            'tags': ['lesbian', 'teen', 'hardcore', 'latina', 'rough', 'squirt', 'big-ass', 'cheater', 'twistys', 'cheat', 'ass-play', 'when-girls-play'],
+            'creator': 'Twistys',
+            'uploader': 'Twistys',
+            'uploader_id': 'Twistys',
+            'uploader_url': '/channels/twistys1',
+            'actors': [{'given_name': 'Adriana Chechik', 'url': 'https://www.xvideos.com/pornstars/adriana-chechik'}, {'given_name': 'Abella Danger', 'url': 'https://www.xvideos.com/pornstars/abella-danger'}],
+            'view_count': int,
         }
     }, {
         'url': 'https://flashservice.xvideos.com/embedframe/4588838',
@@ -137,6 +146,25 @@ class XVideosIE(InfoExtractor):
 
         self._sort_formats(formats)
 
+        tags = self._search_regex(r'<meta name="keywords" content="xvideos,xvideos\.com, x videos,x video,porn,video,videos,(?P<tag>.+?)"', webpage, 'tags', group='tag', default='').split(',')
+
+        creator_data = re.findall(r'<a href="(?P<creator_url>.+?)" class="btn btn-default label main uploader-tag hover-name"><span class="name">(?P<creator>.+?)<', webpage)
+        creator = None
+        uploader_url = None
+        if creator_data != []:
+            uploader_url, creator = creator_data[0][0:2]
+
+        actors_data = re.findall(r'href="(?P<actor_url>/pornstars/.+?)" class="btn btn-default label profile hover-name"><span class="name">(?P<actor_name>.+?)</span>', webpage)
+        actors = []
+        if actors_data != []:
+            for actor_tuple in actors_data:
+                actors.append({
+                    'given_name': actor_tuple[1],
+                    'url': urljoin(url, actor_tuple[0]),
+                })
+
+        views = self._search_regex(r'<strong class="mobile-hide">(?P<views>.+?)<', webpage, 'views', group='views', default=None)
+
         return {
             'id': video_id,
             'formats': formats,
@@ -144,4 +172,11 @@ class XVideosIE(InfoExtractor):
             'duration': duration,
             'thumbnails': thumbnails,
             'age_limit': 18,
+            'tags': tags,
+            'creator': creator,
+            'uploader': creator,
+            'uploader_id': creator,
+            'uploader_url': uploader_url,
+            'actors': actors,
+            'view_count': str_to_int(views),
         }

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: