Merge 666a963046e89f51d29e99ac349b845ff963674a 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/slideslive.py

@@ -3,9 +3,13 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     bool_or_none,
+    extract_attributes,
+    int_or_none,
     smuggle_url,
     try_get,
+    unified_timestamp,
     url_or_none,
 )
 
@@ -23,17 +27,20 @@ class SlidesLiveIE(InfoExtractor):
             'description': 'Watch full version of this video at https://slideslive.com/38902413.',
             'uploader': 'SlidesLive Videos - A',
             'uploader_id': 'UC62SdArr41t_-_fX40QCLRw',
-            'timestamp': 1597615266,
+            'timestamp': 1618809663,
             'upload_date': '20170925',
         }
     }, {
         # video_service_name = yoda
         'url': 'https://slideslive.com/38935785',
-        'md5': '575cd7a6c0acc6e28422fe76dd4bcb1a',
+        'md5': '575cd7a6c0acc6e28422fe76dd4bcb1a',  # d735b130beb40013a839de1c58a74689
         'info_dict': {
-            'id': 'RMraDYN5ozA_',
+            'id': 'F31OTzeGyDK_',
+            'display_id': '38935785',
             'ext': 'mp4',
             'title': 'Offline Reinforcement Learning: From Algorithms to Practical Challenges',
+            'upload_date': '20210220',
+            'timestamp': 1613785940,
         },
         'params': {
             'format': 'bestvideo',
@@ -54,8 +61,17 @@ class SlidesLiveIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        player = self._search_regex(
+            r'<div\s[^>]*?id\s*=\s*(?P<q>\'|"|\b)player(?P=q)(?:\s[^>]*)?>.*?</div>',
+            webpage, 'player div', fatal=False, group=0)
+        player = (player and extract_attributes(player)) or {}
+        token = player.get('data-player-token')
+        if not token:
+            raise ExtractorError('Unable to get player token', expected=True)
         video_data = self._download_json(
-            'https://ben.slideslive.com/player/' + video_id, video_id)
+            'https://ben.slideslive.com/player/' + video_id, video_id,
+            query={'player_token': token, })
         service_name = video_data['video_service_name'].lower()
         assert service_name in ('url', 'yoda', 'vimeo', 'youtube')
         service_id = video_data['video_service_id']
@@ -72,12 +88,23 @@ class SlidesLiveIE(InfoExtractor):
             })
         info = {
             'id': video_id,
-            'thumbnail': video_data.get('thumbnail'),
+            'thumbnail': video_data.get(
+                'thumbnail',
+                self._html_search_meta(('thumbnailUrl', 'thumbnailURL'), webpage)),
             'is_live': bool_or_none(video_data.get('is_live')),
             'subtitles': subtitles,
+            'timestamp': (
+                int_or_none(video_data.get('updated_at'))
+                or unified_timestamp(
+                    self._html_search_meta('uploadDate', webpage))),
+            'creator': self._og_search_property('author', webpage, fatal=False),
         }
+        title = (
+            video_data.get('title')
+            or self._html_search_meta('name', webpage, display_name='meta title')
+            or self._og_search_title(webpage, fatal=False))
         if service_name in ('url', 'yoda'):
-            info['title'] = video_data['title']
+            info['title'] = title or video_data['title']
             if service_name == 'url':
                 info['url'] = service_id
             else:
@@ -93,6 +120,7 @@ class SlidesLiveIE(InfoExtractor):
                 self._sort_formats(formats)
                 info.update({
                     'id': service_id,
+                    'display_id': video_id,
                     'formats': formats,
                 })
         else:
@@ -100,7 +128,7 @@ class SlidesLiveIE(InfoExtractor):
                 '_type': 'url_transparent',
                 'url': service_id,
                 'ie_key': service_name.capitalize(),
-                'title': video_data.get('title'),
+                'title': title,
             })
             if service_name == 'vimeo':
                 info['url'] = smuggle_url(

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: