Merge ca76f4e8eb9c853577e407d3689c10bb12e17674 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

@@ -1065,7 +1065,13 @@ from .rtl2 import (
 )
 from .rtp import RTPIE
 from .rts import RTSIE
-from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
+from .rtve import (
+        RTVEALaCartaIE,
+        RTVELiveIE,
+        RTVEAudioIE,
+        RTVEInfantilIE,
+        RTVETelevisionIE,
+)
 from .rtvnh import RTVNHIE
 from .rtvs import RTVSIE
 from .ruhd import RUHDIE

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/rtve.py

@@ -179,6 +179,87 @@ class RTVEALaCartaIE(InfoExtractor):
             for s in subs)
 
 
+class RTVEAudioIE(RTVEALaCartaIE):
+    IE_NAME = 'rtve.es:audio'
+    IE_DESC = 'RTVE audio'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/(alacarta|play)/audios/[^/]+/[^/]+/(?P<id>[0-9]+)/'
+
+    _TESTS = [{
+        'url': 'https://www.rtve.es/alacarta/audios/a-hombros-de-gigantes/palabra-ingeniero-codigos-informaticos-27-04-21/5889192/',
+        'md5': 'ae06d27bff945c4e87a50f89f6ce48ce',
+        'info_dict': {
+            'id': '5889192',
+            'ext': 'mp3',
+            'title': 'Códigos informáticos',
+            'thumbnail': r're:https?://.+/1598856591583.jpg',
+            'duration': 349.440,
+        },
+    }, {
+        'url': 'https://www.rtve.es/play/audios/en-radio-3/ignatius-farray/5791165/',
+        'md5': '072855ab89a9450e0ba314c717fa5ebc',
+        'info_dict': {
+            'id': '5791165',
+            'ext': 'mp3',
+            'title': 'Ignatius Farray',
+            'thumbnail': r're:https?://.+/1613243011863.jpg',
+            'duration': 3559.559,
+        },
+    }, {
+        'url': 'https://www.rtve.es/play/audios/frankenstein-o-el-moderno-prometeo/capitulo-26-ultimo-muerte-victor-juan-jose-plans-mary-shelley/6082623/',
+        'md5': '0eadab248cc8dd193fa5765712e84d5c',
+        'info_dict': {
+            'id': '6082623',
+            'ext': 'mp3',
+            'title': 'Capítulo 26 y último: La muerte de Victor',
+            'thumbnail': r're:https?://.+/1632147445707.jpg',
+            'duration': 3174.086,
+        },
+    }]
+
+    def _extract_png_formats(self, audio_id):
+        png = self._download_webpage(
+            'http://www.rtve.es/ztnr/movil/thumbnail/%s/audios/%s.png' %
+            (self._manager, audio_id),
+            audio_id, 'Downloading url information', query={'q': 'v2'})
+        q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
+        formats = []
+        for quality, audio_url in self._decrypt_url(png):
+            ext = determine_ext(audio_url)
+            print(quality, audio_url, ext)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    audio_url, audio_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    audio_url, audio_id, 'dash', fatal=False))
+            else:
+                formats.append({
+                    'format_id': quality,
+                    'quality': q(quality),
+                    'url': audio_url,
+                })
+        self._sort_formats(formats)
+        return formats
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+        info = self._download_json(
+            'https://www.rtve.es/api/audios/%s.json' % audio_id,
+            audio_id)['page']['items'][0]
+        title = info['title'].strip()
+        formats = self._extract_png_formats(audio_id)
+
+        return {
+            'id': audio_id,
+            'title': title,
+            'thumbnail': info.get('thumbnail'),
+            'duration': float_or_none(info.get('duration'), 1000),
+            'series': info.get('programInfo').get('title'),
+            'formats': formats,
+        }
+
+
 class RTVEInfantilIE(RTVEALaCartaIE):
     IE_NAME = 'rtve.es:infantil'
     IE_DESC = 'RTVE infantil'

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: