Merge e1dc38319cb5974496b9877958d491cec157a3a0 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/erocast.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..utils import traverse_obj
+
+import re
+
+
+class ErocastIE(InfoExtractor):
+    IE_NAME = 'erocast'
+    _VALID_URL = r'https?://(?:www\.)?erocast\.me/track/(?P<id>[0-9]+)/(?P<display_id>[0-9a-zA-Z_-]+)'
+    _TESTS = [{
+        'url': 'https://erocast.me/track/6508/piano-sample-by-ytdl',
+        'md5': '6764726b2d19161e93c9cf3a9a69800a',
+        'info_dict': {
+            'id': '6508',
+            'ext': 'mp4',
+            'title': 'Piano sample by ytdl',
+            'uploader': 'ytdl',
+        }
+    }, {
+        'url': 'https://erocast.me/track/4254/intimate-morning-with-your-wife',
+        'md5': '45b06c21cf93612dd72a3d764c0bb362',
+        'info_dict': {
+            'id': '4254',
+            'ext': 'mp4',
+            'title': 'Intimate morning  with your wife',
+            'uploader': 'ZLOY_ASMR',
+        }
+    }, {
+        'url': 'https://erocast.me/playlist/2278/rough-hot-and-dirty',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        # The Song data is in a script tag with the following format:
+        # (see https://github.com/ytdl-org/youtube-dl/issues/31203#issuecomment-1259867716)
+        searchPattern = r'<script\b[^>]*>var\s+song_data_%s\s*=\s*(.+?)</script>' % re.escape(video_id)
+        jsonString = self._html_search_regex(searchPattern, webpage, 'song_data')
+
+        # The data is in JSON format, so we convert the JSON String to a python object
+        # and read the data from this json object
+        jsonObject = self._parse_json(jsonString, None, fatal=False)
+        audio_url = jsonObject['stream_url']
+        title = jsonObject['title']
+        user_name = traverse_obj(jsonObject, ('user', 'name'), expected_type=lambda x: x.strip() or None)
+
+        # The audio url is a m3u8 playlist, so we extract the audio url from this playlist
+        formats = self._extract_m3u8_formats(
+            audio_url, video_id, 'mp4', 'm3u8_native',
+            m3u8_id='hls', fatal=False)
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'uploader': user_name,
+        }
+
+
+class ErocastPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?erocast\.me/playlist/(?P<playlist_id>[0-9]+)/(?P<playlist_title>[0-9a-zA-Z_-]+)'
+    _TESTS = [{
+        'url': 'https://erocast.me/playlist/2278/rough-hot-and-dirty',
+        'info_dict': {
+            'id': '2278',
+            'title': 'rough-hot-and-dirty',
+        },
+        'playlist_mincount': 3,
+    }, {
+        'url': 'https://erocast.me/playlist/1841/dilf',
+        'info_dict': {
+            'id': '1841',
+            'title': 'dilf',
+        },
+        'playlist_mincount': 7,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('playlist_id')
+        title = mobj.group('playlist_title')
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        # Get URL for each track in the playlist
+        entries = [self.url_result(
+            'https://erocast.me/track/' + mobj.group('song_id') + '/' + mobj.group('track_url'),
+            ie=ErocastIE.ie_key(), video_id=mobj.group('song_id'))
+            for mobj in re.finditer(
+                r'<script\b[^>]*>var\s+song_data_(?P<song_id>[0-9]+)\s*=\s*.+?\\/track\\/[0-9]+\\/(?P<track_url>.+)\"\,\"stream_url.+?</script>', webpage)]
+
+        return self.playlist_result(entries, playlist_id, title)

youtube_dl/extractor/extractors.py

@@ -360,6 +360,10 @@ from .embedly import EmbedlyIE
 from .engadget import EngadgetIE
 from .epidemicsound import EpidemicSoundIE
 from .eporner import EpornerIE
+from .erocast import (
+    ErocastIE,
+    ErocastPlaylistIE,
+)
 from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
 from .espn 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/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: