Merge 3033db0217e58b4c264683a49dc71660efea317a into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

youtube_dl/extractor/beeg.py

@@ -1,18 +1,28 @@
+# coding: utf-8
+
 from __future__ import unicode_literals
 
+import itertools
+
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
     compat_urlparse,
+    compat_zip as zip,
 )
 from ..utils import (
+    dict_get,
     int_or_none,
+    parse_iso8601,
+    str_or_none,
+    try_get,
     unified_timestamp,
+    urljoin,
 )
 
 
 class BeegIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/-?(?P<id>\d+)'
     _TESTS = [{
         # api/v6 v1
         'url': 'http://beeg.com/5416503',
@@ -27,7 +37,8 @@ class BeegIE(InfoExtractor):
             'duration': 383,
             'tags': list,
             'age_limit': 18,
-        }
+        },
+        'skip': 'no longer available',
     }, {
         # api/v6 v2
         'url': 'https://beeg.com/1941093077?t=911-1391',
@@ -42,13 +53,28 @@ class BeegIE(InfoExtractor):
     }, {
         'url': 'https://beeg.porn/5416503',
         'only_matching': True,
+    }, {
+        'url': 'https://beeg.com/-01882333214',
+        'md5': 'f8fd97a58a09bc6d2ac25b6bbc98c220',
+        'info_dict': {
+            'id': '1882333214',
+            'ext': 'mp4',
+            'title': 'Be mine',
+            'description': 'Lil cam dork living in Canada with 4 kitties',
+            'timestamp': 1628218803,
+            'upload_date': '20210806',
+            'duration': 559,
+            'tags': list,
+            'age_limit': 18,
+            'thumbnail': r're:https?://thumbs\.beeg\.com/videos/1882333214/\d+\.jpe?g',
+        },
+        'params': {
+            # ignore variable HLS file data
+            'skip_download': True,
+        },
     }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
+    def _old_real_extract(self, url, video_id, webpage):
         beeg_version = self._search_regex(
             r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
             default='1546225636701')
@@ -67,11 +93,14 @@ class BeegIE(InfoExtractor):
         else:
             query = {'v': 1}
 
-        for api_path in ('', 'api.'):
+        def reverse_enumerate(l):
+            return zip(reversed(next(zip(*enumerate(l)), [])), l)
+
+        for rcnt, api_path in reverse_enumerate(('', 'api.')):
             video = self._download_json(
                 'https://%sbeeg.com/api/v6/%s/video/%s'
                 % (api_path, beeg_version, video_id), video_id,
-                fatal=api_path == 'api.', query=query)
+                fatal=(rcnt == 0), query=query)
             if video:
                 break
 
@@ -114,3 +143,53 @@ class BeegIE(InfoExtractor):
             'formats': formats,
             'age_limit': self._rta_search(webpage),
         }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = []
+        # leading 0s stripped from ID by site, though full ID also works
+        video = self._download_json(
+            'https://store.externulls.com/facts/file/%d' % int(video_id),
+            video_id, fatal=False)
+        if video:
+            video_data = try_get(video, lambda x: x['file'], dict) or {}
+            video_data.update(video_data.get('stuff', {}))
+            video_data.update(try_get(video, lambda x: x['fc_facts'][0], dict))
+            for format_id, key in itertools.chain(
+                    try_get(video_data, lambda x: x['resources'].items()) or [],
+                    try_get(video_data, lambda x: x['hls_resources'].items()) or []):
+                if not format_id:
+                    continue
+                formats.append({
+                    'url': urljoin('https://video.beeg.com', key),
+                    'format_id': format_id,
+                    'height': int_or_none(format_id.rsplit('_', 1)[-1]),
+                })
+            if formats:
+                self._sort_formats(formats)
+                tags = try_get(video, lambda v: [tag['tg_slug'] for tag in v['tags'] if tag.get('tg_slug')])
+                result = {
+                    'id': str_or_none(video.get('fc_file_id')) or video_id,
+                    'title': video_data.get('sf_name') or 'Beeg video %s' % video_id,
+                    'description': video_data.get('sf_story'),
+                    'timestamp': parse_iso8601(video_data.get('fc_created')),
+                    'duration': int_or_none(dict_get(video_data, ('fl_duration', 'sf_duration'))),
+                    'tags': tags,
+                    'formats': formats,
+                    'age_limit': self._rta_search(webpage) or 18,
+                    'height': int_or_none(video_data.get('fl_height')),
+                    'width': int_or_none(video_data.get('fl_width')),
+                }
+                thumb_id = try_get(video_data, lambda x: x['fc_thumbs'][0], int)
+                if thumb_id is not None:
+                    set_id = video_data.get('resources', {}).get('set_id')
+                    result['thumbnail'] = (
+                        'https://thumbs.beeg.com/videos/%s/%d.jpg' % (result['id'], thumb_id)
+                        if set_id is None else
+                        'https://thumbs-015.externulls.com/sets/%s/thumbs/%s-%0.4d.jpg' % (set_id, set_id, thumb_id))
+                return result
+
+        return self._old_real_extract(url, video_id, webpage)

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/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: