Merge fe02a15b1c35aad2463dfc6ff160e50cd8c2a04c 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

@@ -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 +1,95 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    js_to_json,
+)
+
+
+class MujRozhlasIE(InfoExtractor):
+    IE_NAME = 'mujRozhlas'
+    IE_DESC = 'https://www.mujrozhlas.cz/'
+    _VALID_URL = r'https?://www\.mujrozhlas\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [
+        {
+            'url': 'https://www.mujrozhlas.cz/vinohradska-12/zadne-dalsi-pusy-konec-prchala-spol-muze-znamenat-babisuv-odchod-z-politiky-tipuje',
+            'md5': '34ecaa47f64079a63d6b80498c280e9d',
+            'info_dict': {
+                'id': '0c54ba72-93dd-3a29-b567-910d3d8c71a8',
+                'ext': 'mp3',
+                'title': 'Žádné další pusy. Konec Prchala a spol. může znamenat Babišův odchod z politiky, tipuje politolog',
+                'description': 'md5:ec0610bdb1f591061dbd224d2dd9c19e',
+            },
+        },
+        {
+            'url': 'https://www.mujrozhlas.cz/kazki/princi-ta-zliy-drakon',
+            'md5': 'cbad6f68db6dc4d6d798d69b5d258aa5',
+            'info_dict': {
+                'id': 'ec5f53b2-3910-448e-8e7f-d6d1a19f4926',
+                'ext': 'm4a',
+                'title': 'Принці та злий дракон',
+                'description': 'md5:b21701e09c2b509c4451194af7ac271b',
+            },
+            'params': {
+                'format': 'hls-128',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        player_data = self._search_regex(
+            r'\bvar dl = ({[^\n]+});',
+            webpage, 'player data', default=None)
+        if not player_data:
+            raise ExtractorError('Could not find player data')
+
+        player_data = self._parse_json(player_data, display_id, js_to_json)
+        audio_id = player_data['contentId']
+        bundle = player_data['siteEntityBundle']
+        if bundle not in ('episode', 'serialPart'):
+            raise ExtractorError('Unsupported entity: {0}'.format(bundle))
+
+        url = 'https://api.mujrozhlas.cz/episodes/{0}'.format(player_data['contentId'])
+        webpage = self._download_webpage(url, audio_id)
+        attr = self._parse_json(webpage, audio_id)['data']['attributes']
+
+        formats = []
+        for link in attr['audioLinks']:
+            variant = link['variant']
+            if variant == 'hls':
+                formats.extend(self._extract_m3u8_formats(
+                    link['url'], audio_id, 'm4a', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif variant == 'dash':
+                formats.extend(self._extract_mpd_formats(
+                    link['url'], audio_id, mpd_id='dash', fatal=False))
+            elif variant == 'mp3':
+                url = link['url']
+                m = re.search(
+                    r'(?P<proto>[^:]+):(?:.*/)*(?P<id>[^.]+)\.(?P<ext>[^/.]+)$',
+                    url)
+                bitrate = link['bitrate']
+                formats.append({
+                    'url': link['url'],
+                    'protocol': m.group('proto'),
+                    'ext': m.group('ext'),
+                    'format_id': '-'.join(('mp3', str(bitrate))),
+                    'vcodec': 'none',
+                    'abr': bitrate,
+                    'tbr': bitrate,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': audio_id,
+            'title': attr['title'],
+            'description': clean_html(attr['description']),
+            'formats': formats,
+        }

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: