Merge d81793ea564e44219aa06f806caa8d46a242d2f3 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

@@ -1068,6 +1068,7 @@ from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
 from .rtvnh import RTVNHIE
 from .rtvs import RTVSIE
+from .rtvslo import RTVSLO4DIE
 from .ruhd import RUHDIE
 from .rumble import RumbleEmbedIE
 from .rutube import (

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/rtvslo.py

@@ -0,0 +1,98 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    try_get,
+    unified_timestamp
+)
+
+
+class RTVSLO4DIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:4d\.rtvslo\.si/(?:arhiv/[^/]+|embed)|www\.rtvslo\.si/(?:4d/arhiv|mmr/prispevek))/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://4d.rtvslo.si/arhiv/seje-odbora-za-kmetijstvo-gozdarstvo-in-prehrano/174595438',
+        'md5': '37ab1181292a08e0d6b7952545e6ce8b',
+        'info_dict': {
+            'id': '174595438',
+            'ext': 'mp4',
+            'title': 'Krajčič o tatvini sendviča',
+            'thumbnail': r're:https://img.rtvslo.si/.+\.jpg',
+            'timestamp': 1549999614,
+            'upload_date': '20190212',
+            'duration': 85
+        },
+    }, {
+        'url': 'https://4d.rtvslo.si/arhiv/punto-e-a-capo/174752966',
+        'md5': 'a1ce903ee0a4051e417c9357e3d51c71',
+        'info_dict': {
+            'id': '174752966',
+            'ext': 'mp3',
+            'title': 'Dante divulgatore della scienza, con Gian Italo Bischi. E un ricordo di Federico Roncoroni',
+            'thumbnail': r're:https://img.rtvslo.si/.+\.jpg',
+            'timestamp': 1613033635,
+            'upload_date': '20210211',
+            'duration': 1740
+        },
+    }, {
+        'url': 'https://4d.rtvslo.si/arhiv/punto-e-a-capo/174752966',
+        'only_matching': True,
+    }, {
+        'url': 'https://4d.rtvslo.si/embed/174595438',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.rtvslo.si/4d/arhiv/174752597?s=tv_ita',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.rtvslo.si/mmr/prispevek/174752987',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+
+        media_info = self._download_json(
+            'https://api.rtvslo.si/ava/getRecording/' + media_id, media_id,
+            query={'client_id': '19cc0556a5ee31d0d52a0e30b0696b26'})['response']
+
+        if media_info['mediaType'] == 'video':
+            formats = []
+            for proto in ('hls_sec', 'hls',):
+                formats += self._extract_m3u8_formats(
+                    media_info['addaptiveMedia'][proto], media_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls')
+
+        elif media_info['mediaType'] == 'audio':
+            formats = [{
+                'format_id': file['mediaType'],
+                'url': file['streamers']['http'] + '/' + file['filename'],
+                'ext': determine_ext(file['filename']),
+                'tbr': int_or_none(file.get('bitrate')),
+                'filesize': int_or_none(file.get('filesize')),
+                'vcodec': 'none'
+            } for file in media_info['mediaFiles']]
+
+        self._sort_formats(formats)
+
+        return {
+            'id': media_id,
+            'title': media_info['title'],
+            'formats': formats,
+            'description': try_get(media_info, 'description'),
+            'thumbnail': media_info.get('thumbnail_sec'),
+            'timestamp': unified_timestamp(media_info.get('broadcastDate')),
+            'duration': media_info.get('duration'),
+            'subtitles': self.extract_subtitles(media_info)
+        }
+
+    def _get_subtitles(self, media_info):
+        subs = {}
+        for sub in media_info.get('subtitles', []):
+            subs[sub['language']] = [{
+                'ext': 'vtt',
+                'url': sub['file']
+            }]
+
+        return subs

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',