Merge fb7755bb1ed7ac0cc7e430f609723d019ede5ce5 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/parliamentliveuk.py

@@ -2,6 +2,15 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 
+from ..compat import compat_str
+
+from ..utils import (
+    get_element_by_id,
+    int_or_none,
+    parse_iso8601,
+    try_get,
+)
+
 
 class ParliamentLiveUKIE(InfoExtractor):
     IE_NAME = 'parliamentlive.tv'
@@ -11,12 +20,15 @@ class ParliamentLiveUKIE(InfoExtractor):
     _TESTS = [{
         'url': 'http://parliamentlive.tv/Event/Index/c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
         'info_dict': {
-            'id': '1_af9nv9ym',
+            'id': 'c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
             'ext': 'mp4',
             'title': 'Home Affairs Committee',
-            'uploader_id': 'FFMPEG-01',
-            'timestamp': 1422696664,
-            'upload_date': '20150131',
+            'timestamp': 1622916432,
+            'upload_date': '20210605',
+            'description': 'Tue, 18 Mar 2014 14:44:32 GMT',
+        },
+        'params': {
+            'format': 'bestvideo/best',
         },
     }, {
         'url': 'http://parliamentlive.tv/event/index/3f24936f-130f-40bf-9a5d-b3d6479da6a4',
@@ -25,6 +37,56 @@ class ParliamentLiveUKIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        video_data = self._download_json(
+            'https://exposure.api.redbee.live/v2/customer/UKParliament/businessunit/ParliamentLive/entitlement/%s/play?' % video_id,
+            video_id, fatal=False,
+            headers={'Authorization': 'Bearer 5qIxfu04iGfVXniravNWzlcxk|5qIxfu04iGfVXniravNWzlcxk|5qIxfu04iGfVXniravNWzlcxk|null|1639618587134|1642210587134|true|82293e3a-a0ea-fac9-385d-bfad5829b9c1|WEB||||YipgM4RjyCVP0UqxE29scVZio+L5yUzzCF0Xtp6ToMM=', })
+        if video_data:
+            webpage = self._download_webpage(url, video_id)
+            pub_id = try_get(video_data, 'publicationId', compat_str) or ('%s_0D62A9b' % video_id)
+            video_metadata = self._download_json(
+                'https://exposure.api.redbee.live/v1/customer/UKParliament/businessunit/ParliamentLive/content/asset/%s?fieldSet=ALL' % pub_id,
+                video_id, fatal=False, note='Downloading additional JSON metadata') or {}
+            title = (try_get(video_metadata, lambda x: x['localized'][0]['title'], compat_str)
+                     or self._html_search_regex(r'<title\b[^>]*>([^<]+)</', webpage, 'title'))
+            fmts = []
+            for f in try_get(video_data, lambda x: x['formats'], list):
+                fmt_url = try_get(f, lambda x: x['mediaLocator'], compat_str)
+                if not fmt_url:
+                    continue
+                if '.ism/Manifest' in fmt_url:
+                    fmts.extend(self._extract_ism_formats(
+                        fmt_url, video_id, ism_id='mss', fatal=False))
+                elif '.m3u8' in fmt_url:
+                    fmts.extend(self._extract_m3u8_formats(
+                        fmt_url, video_id, 'mp4', fatal=False))
+                elif '.mpd' in fmt_url:
+                    fmts.extend(self._extract_mpd_formats(
+                        fmt_url, video_id, mpd_id='dash', fatal=False))
+                else:
+                    fmts.append({
+                        'format_id': f.get('format'),
+                        'url': fmt_url,
+                    })
+            self._sort_formats(fmts)
+            thumbnail = try_get(
+                self._download_json(
+                    'http://parliamentlive.tv/Event/GetShareVideo/' + video_id, video_id, fatal=False,
+                    note='Downloading event JSON metadata'),
+                lambda x: x['thumbnailUrl'], compat_str)
+            return {
+                'id': video_id,
+                'title': title,
+                'description': (try_get(video_metadata, lambda x: x['localized'][0]['shortDescription'], compat_str)
+                                or (get_element_by_id('eventTitleContainer', webpage) or '').split(title)[-1]
+                                or self._og_search_description(webpage)),
+                'formats': fmts,
+                'isLive': try_get(video_data, lambda x: x['streamInfo']['live'], bool) or False,
+                'duration': int_or_none(video_data.get('durationInMs'), scale=1000),
+                'timestamp': parse_iso8601(try_get(video_metadata, lambda x: x['created'])),
+                'release_timestamp': parse_iso8601(try_get(video_metadata, lambda x: x['publications'][0]['publicationDate'])),
+                'thumbnail': thumbnail,
+            }
         webpage = self._download_webpage(
             'http://vodplayer.parliamentlive.tv/?mid=' + video_id, video_id)
         widget_config = self._parse_json(self._search_regex(

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: