- def _extract_video(self, webpage):
- description = self._html_search_regex([r'<div class="cne-video-description">(.+?)</div>',
- r'<div class="video-post-content">(.+?)</div>',
- ],
- webpage, u'description',
- fatal=False, flags=re.DOTALL)
- params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
- u'player params', flags=re.DOTALL)
- video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, u'video id')
- player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, u'player id')
- target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, u'target')
- data = compat_urllib_parse.urlencode({'videoId': video_id,
- 'playerId': player_id,
- 'target': target,
- })
- base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
- webpage, u'base info url',
- default='http://player.cnevids.com/player/loader.js?')
- info_url = base_info_url + data
- info_page = self._download_webpage(info_url, video_id,
- u'Downloading video info')
- video_info = self._search_regex(r'var video = ({.+?});', info_page, u'video info')
- video_info = json.loads(video_info)
-
- def _formats_sort_key(f):
- type_ord = 1 if f['type'] == 'video/mp4' else 0
- quality_ord = 1 if f['quality'] == 'high' else 0
- return (quality_ord, type_ord)
- best_format = sorted(video_info['sources'][0], key=_formats_sort_key)[-1]
-
- return {'id': video_id,
- 'url': best_format['src'],
- 'ext': best_format['type'].split('/')[-1],
- 'title': video_info['title'],
- 'thumbnail': video_info['poster_frame'],
- 'description': description,
- }
+ def _extract_video_params(self, webpage, display_id):
+ query = self._parse_json(
+ self._search_regex(
+ r'(?s)var\s+params\s*=\s*({.+?})[;,]', webpage, 'player params',
+ default='{}'),
+ display_id, transform_source=js_to_json, fatal=False)
+ if query:
+ query['videoId'] = self._search_regex(
+ r'(?:data-video-id=|currentVideoId\s*=\s*)["\']([\da-f]+)',
+ webpage, 'video id', default=None)
+ else:
+ params = extract_attributes(self._search_regex(
+ r'(<[^>]+data-js="video-player"[^>]+>)',
+ webpage, 'player params element'))
+ query.update({
+ 'videoId': params['data-video'],
+ 'playerId': params['data-player'],
+ 'target': params['id'],
+ })
+ return query
+
+ def _extract_video(self, params):
+ video_id = params['videoId']
+
+ video_info = None
+
+ # New API path
+ query = params.copy()
+ query['embedType'] = 'inline'
+ info_page = self._download_json(
+ 'http://player.cnevids.com/embed-api.json', video_id,
+ 'Downloading embed info', fatal=False, query=query)
+
+ # Old fallbacks
+ if not info_page:
+ if params.get('playerId'):
+ info_page = self._download_json(
+ 'http://player.cnevids.com/player/video.js', video_id,
+ 'Downloading video info', fatal=False, query=params)
+ if info_page:
+ video_info = info_page.get('video')
+ if not video_info:
+ info_page = self._download_webpage(
+ 'http://player.cnevids.com/player/loader.js',
+ video_id, 'Downloading loader info', query=params)
+ if not video_info:
+ info_page = self._download_webpage(
+ 'https://player.cnevids.com/inline/video/%s.js' % video_id,
+ video_id, 'Downloading inline info', query={
+ 'target': params.get('target', 'embedplayer')
+ })
+
+ if not video_info:
+ video_info = self._parse_json(
+ self._search_regex(
+ r'(?s)var\s+config\s*=\s*({.+?});', info_page, 'config'),
+ video_id, transform_source=js_to_json)['video']
+
+ title = video_info['title']
+
+ formats = []
+ for fdata in video_info['sources']:
+ src = fdata.get('src')
+ if not src:
+ continue
+ ext = mimetype2ext(fdata.get('type')) or determine_ext(src)
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ src, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ continue
+ quality = fdata.get('quality')
+ formats.append({
+ 'format_id': ext + ('-%s' % quality if quality else ''),
+ 'url': src,
+ 'ext': ext,
+ 'quality': 1 if quality == 'high' else 0,
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'formats': formats,
+ 'title': title,
+ 'thumbnail': video_info.get('poster_frame'),
+ 'uploader': video_info.get('brand'),
+ 'duration': int_or_none(video_info.get('duration')),
+ 'tags': video_info.get('tags'),
+ 'series': video_info.get('series_title'),
+ 'season': video_info.get('season_title'),
+ 'timestamp': parse_iso8601(video_info.get('premiere_date')),
+ 'categories': video_info.get('categories'),
+ }
Rapsys Git / youtubedl / blobdiff