- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- url_title = mobj.group('url_title')
- webpage = self._download_webpage(url, url_title)
-
- video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
- webpage, u'video id')
-
- self.report_extraction(video_id)
-
- data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
- data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
-
- video_url = self._html_search_regex(r'<file [^>]*type="high".*?>(.*?)</file>',
- data, u'video URL')
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': 'mp4',
- 'title': self._og_search_title(webpage),
- 'thumbnail': self._og_search_thumbnail(webpage),
- 'description': self._og_search_description(webpage),
- }]
+
+ display_id = mobj.group('display_id')
+ webpage = self._download_webpage(url, display_id)
+
+ video_id = mobj.group('video_id')
+ if not video_id:
+ video_id = self._html_search_regex(
+ self._VIDEO_ID_REGEXES, webpage, 'video id')
+
+ data = preload = None
+ preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage)
+ if preloads:
+ preload = max([(len(p), p) for p in preloads])[1]
+
+ if not preload:
+ preload = ''.join(re.findall(r'this\.push\("([^"]+)"\);', webpage))
+
+ if not preload:
+ preload = self._html_search_regex([
+ r'player,\[?"([^"]+)"\]?', r'player.init\(\[?"([^"]+)"\]?\)'
+ ], webpage.replace('","', ''), 'preload data', default=None)
+
+ if not preload:
+ preload_codes = self._html_search_regex(
+ r'(function.+)setTimeout\(function\(\)\{playlist',
+ webpage, 'preload codes')
+ base64_fragments = re.findall(r'"([a-zA-z0-9+/=]+)"', preload_codes)
+ base64_fragments.remove('init')
+ for i in range(len(base64_fragments)):
+ cur_sequence = (''.join(base64_fragments[i:] + base64_fragments[:i])).encode('ascii')
+ try:
+ raw_data = base64.b64decode(cur_sequence)
+ except (TypeError, binascii.Error):
+ continue
+ if compat_ord(raw_data[0]) == compat_ord('{'):
+ data = self._parse_json(raw_data.decode('utf-8'), video_id, fatal=False)
+
+ if not preload and not data:
+ raise ExtractorError(
+ 'Preload information could not be extracted', expected=True)
+
+ if not data:
+ data = self._parse_json(
+ base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id)
+
+ formats = []
+ get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
+ for filed in data['files']:
+ if filed['type'] == 'hls':
+ formats.extend(self._extract_m3u8_formats(
+ filed['url'], video_id, ext='mp4'))
+ else:
+ m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
+ if m_format is not None:
+ format_id = m_format.group(1)
+ else:
+ format_id = filed['bitrate']
+ tbr = (
+ int(filed['bitrate'])
+ if filed['bitrate'].isdigit()
+ else None)
+
+ formats.append({
+ 'url': filed['url'],
+ 'ext': 'mp4',
+ 'tbr': tbr,
+ 'format_id': format_id,
+ 'quality': get_quality(format_id),
+ })
+
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'formats': formats,
+ 'title': data['title'],
+ 'thumbnail': data.get('thumb', {}).get('href'),
+ 'description': data.get('teaser'),
+ 'duration': data.get('duration'),
+ 'age_limit': self._family_friendly_search(webpage),
+ }