Merge 517af8b6e01654d70340509922f85869e9950741 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/vimeo.py

@@ -390,6 +390,29 @@ class VimeoIE(VimeoBaseInfoExtractor):
             },
             'expected_warnings': ['Unable to download JSON metadata'],
         },
+        {
+            'url': 'https://vimeo.com/channels/bestofstaffpicks/543188947',
+            'note': 'channel video with no data-config-url',
+            'info_dict': {
+                'id': '543188947',
+                'ext': 'mp4',
+                'title': "THE CHEMICAL BROTHERS 'THE DARKNESS THAT YOU FEAR' - OFFICIAL VIDEO",
+                'description': 'md5:a3949dd6e4a3dc5161871d195ee46cf0',
+                'uploader_url': r're:https?://(?:www\.)?vimeo\.com/ruffmercy',
+                'uploader_id': 'ruffmercy',
+                'uploader': 'RUFFMERCY',
+                'channel_id': 'bestofstaffpicks',
+                'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/bestofstaffpicks',
+                'timestamp': 1619693770,
+                'upload_date': '20210429',
+                'duration': 237,
+            },
+            'params': {
+                # avoid selecting DASH/HLS which only send 1 fragment and fail expected size check
+                'format': 'best[protocol=https]',
+            },
+            'expected_warnings': ['Unable to download JSON metadata'],
+        },
         {
             'url': 'http://vimeo.com/76979871',
             'note': 'Video with subtitles',
@@ -704,14 +727,18 @@ class VimeoIE(VimeoBaseInfoExtractor):
         channel_id = self._search_regex(
             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
         if channel_id:
+            # look for data-config-url=, but it may not be present
             config_url = self._html_search_regex(
-                r'\bdata-config-url="([^"]+)"', webpage, 'config URL')
+                r'\bdata-config-url\s*=\s*("|\')(?P<config_url>[^"\']+)\1',
+                webpage, 'config URL', group='config_url', default=None)
             video_description = clean_html(get_element_by_class('description', webpage))
             info_dict.update({
                 'channel_id': channel_id,
                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
             })
         else:
+            config_url = None
+        if not config_url:
             page_config = self._parse_json(self._search_regex(
                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
                 webpage, 'page config', default='{}'), video_id, fatal=False)
@@ -721,8 +748,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
             cc_license = page_config.get('cc_license')
             clip = page_config.get('clip') or {}
             timestamp = clip.get('uploaded_on')
-            video_description = clean_html(
+            if not video_description:
-                clip.get('description') or page_config.get('description_html_escaped'))
+                video_description = clean_html(
+                    clip.get('description') or page_config.get('description_html_escaped'))
         config = self._download_json(config_url, video_id)
         video = config.get('video') or {}
         vod = video.get('vod') or {}

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: