Merge e4759fdffe7e0cfa204fb83324552ab31503d597 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/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

@@ -736,6 +736,7 @@ from .mtv import (
     MTVJapanIE,
 )
 from .muenchentv import MuenchenTVIE
+from .mujrozhlas import MujRozhlasIE
 from .mwave import MwaveIE, MwaveMeetGreetIE
 from .mychannels import MyChannelsIE
 from .myspace import MySpaceIE, MySpaceAlbumIE

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/mujrozhlas.py

@@ -0,0 +1,63 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    clean_html,
+    parse_iso8601
+)
+
+
+class MujRozhlasIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?mujrozhlas\.cz/(?P<id>[a-zA-Z0-9/-]+)'
+    _TESTS = [{
+        'url': 'https://www.mujrozhlas.cz/meteor/meteor-o-nejvetsim-matematikovi-nekonecnem-vesmiru-skakajicim-pavoukovi-hrani-surikat',
+        'info_dict': {
+            'id': 'meteor/meteor-o-nejvetsim-matematikovi-nekonecnem-vesmiru-skakajicim-pavoukovi-hrani-surikat',
+            'ext': 'mp3',
+            'title': 'Meteor o největším matematikovi, nekonečném vesmíru, skákajícím pavoukovi a hraní surikat',
+            'description': 'Poslechněte si:01:00 Vymírající pták roku07:57 Největší experimentátor všech dob14:06 Největší matematik 20. století27:40 Jak si představit nekonečný vesmír?35:12 Pavouk, který skáče bunjee jumping41:34 Jak si hrají surikaty?Hovoří ornitolog Zdeněk Vermouzek, matematik Václav Chvátal nebo astronom Norbert Werner. Rubriku Stalo se tento den připravil ing. František Houdek.\xa0Z knihy\xa0Pozoruhodné objevy ze světa zvířat čte Zuzana Slavíková.\nPetr Sobotka',
+            'timestamp': 1647272701,
+            'upload_date': '20220314',
+        }
+    }, {
+        'url': 'https://www.mujrozhlas.cz/podcast-vinohradska-12/its-humanitarian-disaster-mariupol-we-want-help-says-msfs-alex-wade',
+        'info_dict': {
+            'id': 'podcast-vinohradska-12/its-humanitarian-disaster-mariupol-we-want-help-says-msfs-alex-wade',
+            'ext': 'mp3',
+            'title': 'It\'s a humanitarian disaster in Mariupol. We want to help, says MSF‘s Alex Wade',
+            'description': 'It is a humanitarian catastrophe. People in the southeast of Ukraine are dying in the streets and their neighbors have to bury them in the gardens. Those who are still alive, dont have food, water or medicine. I spoke to Alex Wade, an emergency coordinator for Doctors without Borders, who is in Dnipro. He is doing his best to help Ukrainians who are fleeing the war or staying to fight back.\nMatěj Skalický\n\nEdited by: Kateřina Pospíšilová\nSound design: Tomáš Černý\nResearched by:\xa0Alžběta Jurčová\nMusic:\xa0Martin Hůla',
+            'timestamp': 1647442501,
+            'upload_date': '20220316',
+        }
+    }]
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, audio_id)
+
+        content_id = self._html_search_regex(r'"contentId":"(.+?)"', webpage, 'content_id')
+        content_url = 'https://api.mujrozhlas.cz/episodes/' + content_id
+
+        content = self._download_json(content_url, content_id)
+        attrs = content['data']['attributes']
+        title = attrs['title']
+        audio_url = content['data']['attributes']['audioLinks'][0]['url']
+        audio_info = content['data']['attributes']['audioLinks'][0]
+        duration = audio_info.get('duration')
+        description = clean_html(attrs.get('description'))
+        thumbnail = self._og_search_thumbnail(webpage)
+        timestamp = parse_iso8601(self._og_search_property('updated_time', webpage, fatal=False))
+
+        return {
+            'id': audio_id,
+            'url': audio_url,
+            'title': title,
+            'description': description,
+            'duration': int_or_none(duration),
+            'vcodec': 'none',
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+        }

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',