Merge b8f7389a712f0962a17927b8ce9557d50fb6a3ca into 4e714f9df1ed2cccd51df60d45ff5504abe827b7

* 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/chelseafc.py

@@ -0,0 +1,83 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    traverse_obj,
+    unified_timestamp,
+    url_or_none,
+)
+
+
+class ChelseafcIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?chelseafc\.com(?:/[a-z]+)?/video/(?P<id>[a-z0-9]+(?:-[a-z0-9]+)*)'
+    _TESTS = [{
+        'url': 'https://www.chelseafc.com/en/video/full-match-chelsea-2-2-everton',
+        'md5': '2fda617911b7148a2a19bec55b75d30a',
+        'info_dict': {
+            'id': 'full-match-chelsea-2-2-everton',
+            'ext': 'mp4',
+            'title': 'Full Match: Chelsea 2-2 Everton',
+            'description': 'Full match highlights from Chelsea\'s 2-2 Premier League draw with Everton at Stamford Bridge.',
+            'duration': 2842.0,
+            'timestamp': 1679184000,
+            'tags': ['Premier League', 'Everton', 'Video and article choice'],
+            'upload_date': '20230319',
+            'thumbnail': r're:https?://.*\.png'
+        }
+    },
+        {
+        'url': 'https://www.chelseafc.com/en/video/manchester-city-vs-chelsea-2-0-or-highlights-or-efl-cup',
+        'md5': '2905365c3c9cf4612f303fbb99c2f4ca',
+        'info_dict': {
+            'id': 'manchester-city-vs-chelsea-2-0-or-highlights-or-efl-cup',
+            'ext': 'mp4',
+            'title': 'Manchester City 2-0 Chelsea | Highlights | EFL Cup',
+            'description': 'Highlights from our EFL Cup match against Man City.',
+            'duration': 120.0,
+            'timestamp': 1668042000,
+            'upload_date': '20221110',
+            'tags': ['Highlights', 'League Cup', 'Manchester City'],
+            'thumbnail': r're:https?://.*\.jpg'
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_details_div = self._search_regex(
+            r'(<div\s[^>]*\bdata-component\s*=\s*(?:"|\')\s*VideoDetails\s*(?:"|\')[^>]*>)',
+            webpage,
+            'div'
+        )
+        raw_data = self._html_search_regex(
+            r'<div[^>]*\sdata-props\s*=\s*(?:"|\')\s*([^"\']*)\s*(?:"|\')[^>]*>',
+            video_details_div,
+            'data'
+        )
+
+        data = self._parse_json(raw_data, video_id)
+        manifest_url = data['videoDetail']['signedUrl']
+
+        data = data['videoDetail']
+
+        title = data['title']
+
+        formats = self._extract_m3u8_formats(manifest_url, video_id, 'mp4')
+        self._sort_formats(formats)
+
+        txt_or_none = lambda x: x.strip() or None
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': txt_or_none(data.get('description')),
+            'formats': formats,
+            'duration': parse_duration(data.get('duration')),
+            'timestamp': unified_timestamp(data.get('releaseDate')),
+            'tags': traverse_obj(data, ('tags', Ellipsis, 'title'), expected_type=txt_or_none),
+            'thumbnail': traverse_obj(data, ('image', 'file', 'url'), expected_type=url_or_none),
+        }

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

@@ -215,6 +215,7 @@ from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .charlierose import CharlieRoseIE
 from .chaturbate import ChaturbateIE
+from .chelseafc import ChelseafcIE
 from .chilloutzone import ChilloutzoneIE
 from .chirbit import (
     ChirbitIE,
@@ -989,6 +990,10 @@ from .puhutv import (
     PuhuTVIE,
     PuhuTVSerieIE,
 )
+from .pr0gramm import (
+    Pr0grammIE,
+    Pr0grammStaticIE,
+)
 from .presstv import PressTVIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .puls4 import Puls4IE

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',