Merge 19ac5b7656f04e8ba8d1ec136d1791236aa2f052 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

@@ -465,6 +465,11 @@ from .globo import (
 from .go import GoIE
 from .godtube import GodTubeIE
 from .golem import GolemIE
+from .goodgame import (
+    GoodgameStreamIE,
+    GoodgameVideoIE,
+    GoodgameClipIE,
+)
 from .googledrive import GoogleDriveIE
 from .googlepodcasts import (
     GooglePodcastsIE,

youtube_dl/extractor/goodgame.py

@@ -0,0 +1,239 @@
+# coding=utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .youtube import YoutubeIE
+from ..utils import (
+    ExtractorError,
+    int_or_none
+)
+
+
+class GoodgameBaseIE(InfoExtractor):
+    _RTMP_SERVER = 'rtmp://46.61.227.158:1940/vod//'
+    _API_BASE = 'https://goodgame.ru/api'
+    _HLS_BASE = 'https://hls.goodgame.ru/hls'
+    _QUALITIES = {
+        'Source': '',
+        '240p': '_240',
+        '480p': '_480',
+        '720p': '_720',
+    }
+    _RE_UPLOADER = r'''(?x)
+                        <a[^>]+
+                        href=\"https?://(?:www\.)?goodgame\.ru/user/(?P<uploader_id>\d+)/\"
+                        [^>]*>
+                        (?P<uploader>[^<]+)
+                    '''
+    _RE_TIMESTAMP = r'utc-timestamp=\"(?P<timestamp>\d+)\"'
+
+    def _extract_uploader(self, webpage):
+        uploader_match = re.search(self._RE_UPLOADER, webpage)
+        if uploader_match:
+            uploader = uploader_match.group('uploader')
+            uploader_id = uploader_match.group('uploader_id')
+        else:
+            uploader, uploader_id = None, None
+
+        return uploader, uploader_id
+
+
+class GoodgameStreamIE(GoodgameBaseIE):
+    IE_NAME = 'goodgame:stream'
+    _VALID_URL = r'https?://(?:www\.)?goodgame\.ru/(?:channel/|player\?)(?P<id>[^/#?]+)'
+    _TESTS = [{
+        'url': 'https://goodgame.ru/channel/rutony',
+        'info_dict': {
+            'id': 'rutony',
+            'title': r're:^.*',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'ext': 'mp4',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://goodgame.ru/player?9418',
+        'info_dict': {
+            'id': 'Artist.the',
+            'title': r're:^.*',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'ext': 'mp4',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://goodgame.ru/channel/BRAT_OK/#autoplay',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+        stream_info = next(
+            _ for _ in self._download_json('%s/getchannelstatus?id=%s&fmt=json' % (self._API_BASE, channel_id),
+                                           channel_id,
+                                           note='Downloading stream JSON').values())
+
+        if stream_info.get('status') == 'Dead':
+            raise ExtractorError('%s is offline' % channel_id, expected=True)
+
+        # url with player and stream_id
+        if stream_info.get('key') == stream_info.get('stream_id'):
+            channel_id = self._download_json('%s/player?src=%s' % (self._API_BASE, channel_id),
+                                             channel_id,
+                                             note='Downloading streamer info JSON').get('streamer_name')
+
+        _id = self._search_regex(r'src=\"https://goodgame.ru/player\?(?P<id>.+)\"', stream_info.get('embed'), 'id')
+        thumbnail = stream_info.get('thumb')
+        # goodgame.ru host thumbnail image
+        if thumbnail.startswith('//'):
+            thumbnail = 'https:%s' % thumbnail
+        else:
+            thumbnail = None
+
+        formats = []
+        for quality, suffix in self._QUALITIES.items():
+            formats.append({
+                'format_id': quality,
+                'url': '%s/%s%s.m3u8' % (self._HLS_BASE, _id, suffix),
+                'ext': 'mp4',
+                'protocol': 'm3u8'
+            })
+        self._prefer_source(formats)
+        return {
+            'id': channel_id,
+            'title': stream_info['title'],
+            'view_count': int(stream_info.get('viewers')),
+            'thumbnail': thumbnail,
+            'is_live': True,
+            'formats': formats,
+        }
+
+    def _prefer_source(self, formats):
+        try:
+            source = next(f for f in formats if f['format_id'] == 'Source')
+            source['preference'] = 10
+        except StopIteration:
+            pass
+        self._sort_formats(formats)
+
+
+class GoodgameVideoIE(GoodgameBaseIE):
+    IE_NAME = 'goodgame:video'
+    _VALID_URL = r'https?://(?:www\.)?goodgame\.ru/video/(?P<id>\d+)'
+    _TEST = {
+        # Embedded youtube video
+        'url': 'https://goodgame.ru/video/49294/',
+        'add_ie': ['Youtube'],
+        'info_dict': {
+            'id': 'EihUN4ylsn4',
+            'title': 'Шахматы с Бонивуром | Осторожно, мат на стриме! [запись 25.09.17]',
+            'description': r're:^Большое спасибо за поддержку трансляций интеллектуального формата\..*',
+            'uploader': 'bonivur',
+            'uploader_id': '30',
+            'timestamp': 1506416377,
+            'upload_date': '20170925',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<div[^>]+class=([\"\'])[^\"\']*video-description[^\"\']*\1[^>]*>.*'
+            r'<div[^>]+class=\"title\"[^>]*>(?P<title>[^<]+)',
+            webpage, 'title', group='title', flags=re.DOTALL)
+        description = self._html_search_regex(r'<div[^>]+class=\"description\"[^>]*>(?P<info>[^\0]*?)</div>',
+                                              webpage, 'info', fatal=False, default=None)
+        timestamp = self._html_search_regex(self._RE_TIMESTAMP, webpage, 'timestamp', fatal=False, default=None)
+        uploader, uploader_id = self._extract_uploader(webpage)
+
+        embed_url = YoutubeIE._extract_url(webpage)
+        if embed_url:
+            return {
+                '_type': 'url_transparent',
+                'url': embed_url,
+                'title': title,
+                'description': description,
+                'timestamp': int_or_none(timestamp),
+                'uploader': uploader,
+                'uploader_id': uploader_id
+            }
+
+        file = self._html_search_regex(r'<param[^>]+name=\"flashvars\"[^>]+value=\"src=(?P<path>[^=\"]+)\"[^>]*>',
+                                       webpage, 'path', default=None)
+        if file:
+            rtmp_url = '%s%s' % (self._RTMP_SERVER, file)
+            formats = [{
+                'format_id': 'rtmp',
+                'url': rtmp_url,
+                'ext': 'flv',
+            }]
+
+            return {
+                'id': video_id,
+                'title': title,
+                'description': description,
+                'timestamp': int_or_none(timestamp),
+                'uploader': uploader,
+                'uploader_id': uploader_id,
+                'formats': formats,
+            }
+
+        raise ExtractorError('Video %s was deleted' % video_id, expected=True)
+
+
+class GoodgameClipIE(GoodgameBaseIE):
+    IE_NAME = 'goodgame:clip'
+    _VALID_URL = r'https?://(?:www\.)?goodgame\.ru/clip/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://goodgame.ru/clip/397722/',
+        'info_dict': {
+            'id': '397722',
+            'title': 'ЭТО ФИАСКО',
+            'uploader': '0x111BA6FA',
+            'uploader_id': '1035569',
+            'timestamp': 1506975639,
+            'upload_date': '20171002',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://goodgame.ru/clip/397155/?from=rec',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        timestamp = self._html_search_regex(self._RE_TIMESTAMP, webpage, 'timestamp')
+        uploader, uploader_id = self._extract_uploader(webpage)
+
+        formats = [{
+            'format_id': 'clip',
+            'url': self._og_search_video_url(webpage),
+            'ext': 'mp4',
+        }]
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'timestamp': int_or_none(timestamp),
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+        }

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: