Merge 86297d1acf9ad2420cfbbef9c0d45cac748bfecb 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

@@ -568,6 +568,10 @@ from .khanacademy import (
     KhanAcademyIE,
     KhanAcademyUnitIE,
 )
+from .khinsider import (
+    KhinsiderIE,
+    KhinsiderAlbumIE,
+)
 from .kickstarter import KickStarterIE
 from .kinja import KinjaEmbedIE
 from .kinopoisk import KinoPoiskIE

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/khinsider.py

@@ -0,0 +1,112 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+
+from .common import InfoExtractor
+from ..utils import (
+    get_element_by_id,
+    unified_strdate,
+    ExtractorError,
+    parse_duration)
+
+
+class KhinsiderIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?downloads\.khinsider\.com/game-soundtracks/album/(?P<album>.+?)/(?P<track>.+?)\.mp3'
+    _TESTS = [{
+        'url': 'https://downloads.khinsider.com/game-soundtracks/album/legend-of-zelda-the-breath-of-the-wild-sound-selection/01%2520-%2520Main%2520Theme.mp3',
+        'md5': 'ca2a50c45a0bb06d56ed48de4319d674',
+        'info_dict': {
+            'id': 'legend-of-zelda-the-breath-of-the-wild-sound-selection_01%2520-%2520Main%2520Theme',
+            'title': 'Main Theme',
+            'description': 'Download Main Theme - Legend of Zelda, The - Breath of the Wild Sound Selection soundtracks to your PC in MP3 format. Free Main Theme - Legend of Zelda, The - Breath of the Wild Sound Selection soundtracks, Main Theme - Legend of Zelda, The - Breath of the Wild Sound Selection MP3 downloads. Browse our great selection of Main Theme music. Unlimited free downloads of your favourite Legend of Zelda, The - Breath of the Wild Sound Selection albums.',
+            'ext': 'mp3',
+            'album': 'Legend of Zelda, The - Breath of the Wild Sound Selection',
+            'track': 'Main Theme'
+        }
+    }, {
+        'url': 'https://downloads.khinsider.com/game-soundtracks/album/doraemon-nobita-no-shin-makai-daibouken-ds-nintendo-ds/30.mp3',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._search_regex(
+            self._VALID_URL, url,
+            'album', group='album') + '_' + self._search_regex(self._VALID_URL, url, 'track', group='track')
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'Song name: <b>(.+?)</b>', webpage, 'title', default=video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta('description', webpage),
+            'url': url,
+            'ext': 'mp3',
+            'album': self._html_search_regex(r'Album name: <b>(.+?)</b>', webpage, 'album name', fatal=False),
+            'track': title
+        }
+
+
+class KhinsiderAlbumIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?downloads\.khinsider\.com/game-soundtracks/album/(?P<id>[\w,\-,0-9]+)'
+    _TESTS = [{
+        'url': 'https://downloads.khinsider.com/game-soundtracks/album/legend-of-zelda-the-breath-of-the-wild-sound-selection',
+        'info_dict': {
+            'id': 'legend-of-zelda-the-breath-of-the-wild-sound-selection',
+            'title': 'Legend of Zelda, The - Breath of the Wild Sound Selection MP3 - Download Legend of Zelda, The - Breath of the Wild Sound Selection Soundtracks for FREE!',
+            'description': 'Download Legend of Zelda, The - Breath of the Wild Sound Selection soundtracks to your PC in MP3 format. Free Legend of Zelda, The - Breath of the Wild Sound Selection soundtracks, Legend of Zelda, The - Breath of the Wild Sound Selection MP3 downloads. Browse our great selection of Legend of Zelda, The - Breath of the Wild Sound Selection music. Unlimitted free downloads of your favourite Legend of Zelda, The - Breath of the Wild Sound Selection albums.',
+        },
+        'playlist_mincount': 10
+    }, {
+        'url': 'https://downloads.khinsider.com/game-soundtracks/album/assassin-s-creed-3-the-tyranny-of-king-washington',
+        'info_dict': {
+            'id': 'assassin-s-creed-3-the-tyranny-of-king-washington',
+            'title': 'Assassin\'s Creed III: The Tyranny of King Washington DlC OST MP3 - Download Assassin\'s Creed III: The Tyranny of King Washington DlC OST Soundtracks for FREE!',
+            'description': 'Download Assassin\'s Creed III: The Tyranny of King Washington DlC OST soundtracks to your PC in MP3 format. Free Assassin\'s Creed III: The Tyranny of King Washington DlC OST soundtracks, Assassin\'s Creed III: The Tyranny of King Washington DlC OST MP3 downloads. Browse our great selection of Assassin\'s Creed III: The Tyranny of King Washington DlC OST music. Unlimitted free downloads of your favourite Assassin\'s Creed III: The Tyranny of King Washington DlC OST albums.',
+        },
+        'playlist_mincount': 20
+    }]
+
+    def _parse_playlist_entries(self, content, tb=None, ud=None):
+        r = re.compile(r'<td class=\"clickable-row\"><a href=\"(?P<track_url>.+?)\">(?P<track_title>.+?)</a></td>[^\S]+<td class=\"clickable-row\"[^>]+?><a href=\"(.+?)\"[^>]+?>(?P<duration>[0-9,:]+)</a></td>')
+        songs_info = [m.groupdict() for m in r.finditer(content)]
+
+        if len(songs_info) <= 0:
+            raise ExtractorError('No tracks found for this album.')
+
+        entries = []
+        for song_info in songs_info:
+            entries.append({
+                '_type': 'url_transparent',
+                'ie_key': KhinsiderIE.ie_key(),
+                'title': song_info.get('track_title'),
+                'url': 'https://downloads.khinsider.com' + song_info.get('track_url'),
+                'duration': parse_duration(song_info.get('duration')),
+                'thumbnail': tb,
+                'upload_date': unified_strdate(ud)
+            })
+
+        return entries
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<title>(.+?)[^\S]+?</title>', webpage, 'title', default=video_id)
+        upload_date = self._html_search_regex(r'Date added: <b>(.+?)</b>', webpage, 'upload date', fatal=False)
+        tb = self._html_search_regex(
+            r'<a href=\"(https://vgmsite.com/(.+?).jpg)\" target=\"_blank\">',
+            webpage, 'thumbnail', fatal=False) or self._html_search_regex(
+            r'<img src=\"(https://vgmsite.com/soundtracks/(.+?).jpg)\" border=\"0\">',
+            webpage, 'thumbnail', fatal=False)
+
+        songlist = get_element_by_id('songlist', webpage)
+        entries = self._parse_playlist_entries(songlist, tb=tb, ud=upload_date)
+
+        return self.playlist_result(
+            entries,
+            playlist_id=video_id,
+            playlist_title=title,
+            playlist_description=self._html_search_meta('description', webpage))

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: