Merge 5860937e17a249d80739efd07629dacd2392eba2 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/extractors.py

@@ -1430,6 +1430,7 @@ from .dlive import (
 from .umg import UMGDeIE
 from .unistra import UnistraIE
 from .unity import UnityIE
+from .uno import UNOIE
 from .uol import UOLIE
 from .uplynk import (
     UplynkIE,

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/uno.py

@@ -0,0 +1,64 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    unified_timestamp,
+    url_or_none,
+)
+
+
+class UNOIE(InfoExtractor):
+    _VALID_URL = r'https?://media\.un\.org/(?:\w+/)+(?P<id>k\d[\w]+)'
+    _TESTS = [{
+        'url': 'https://media.un.org/en/asset/k1r/k1r3vy9ikk',
+        'md5': '981c41cb283227f079d1e5059fd0d30c',
+        'info_dict': {
+            'id': '1_r3vy9ikk',
+            'ext': 'mp4',
+            'title': 'md5:abde2a46d396051535e5e6fd6f627a19',
+            'description': 'md5:2cba11ee153ae3e6ae2c629e7c4e39b0',
+            'thumbnail': 're:https?://.+/thumbnail/.+',
+            'duration': 5768,
+            'timestamp': 1625216872,
+            'upload_date': '20210702',
+            'uploader_id': 'UNWebTV_New_York',
+        }
+    }, {
+        'url': 'https://media.un.org/en/asset/k12/k12gpkg3qx',
+        'md5': '5978503ca886a922a0f00cf5a7e82395',
+        'info_dict': {
+            'id': '1_vohfjqkj',
+            'ext': 'mp4',
+            'title': '1851st Meeting, 81st session Committee on the Elimination of Discrimination Against Women (CEDAW)',
+            'description': 'Informal meeting with NGOs and human rights institutions - 1851st Meeting, 81st session CEDAW',
+            'thumbnail': 're:https?://.+/thumbnail/.+',
+            'duration': 3502,
+            'timestamp': 1644235332,
+            'upload_date': '20220207',
+            'uploader_id': 'nathalie.minard@un.org',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        partner_id = self._search_regex(r'partnerId\s*:\s*(\d+)\b', webpage, 'Partner ID')
+        video_id = self._search_regex(r'/p/%s(?:/\w+)+?/entry_id/(\w+)/' % (partner_id, ), webpage, 'Kaltura ID')
+        title = (
+            self._html_search_meta(('title', 'og:title'), webpage)
+            or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title\b', webpage, 'title').rsplit('|', 1)[0]).strip()
+        result = self.url_result(
+            'kaltura:%s:%s' % (partner_id, video_id), 'Kaltura',
+            video_title=title,
+            video_id=video_id)
+        if result:
+            result.update({
+                '_type': 'url_transparent',
+                'description': self._html_search_meta(('description', 'og:description'), webpage, 'description'),
+                'creator': self._html_search_meta('author', webpage),
+                'upoader_id': self._html_search_meta('publisher', webpage),
+                'thumbnail': url_or_none(self._og_search_thumbnail(webpage)),
+                'timestamp': unified_timestamp(self._og_search_property('updated_time', webpage)),
+            })
+        return result

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: