+# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import base64
'ext': 'mp4',
'title': 'Conan Becomes A Mary Kay Beauty Consultant',
'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.',
+ 'duration': 504,
'age_limit': 0,
}
}, {
'ext': 'mp4',
'description': 'Louis C.K. got starstruck by George W. Bush, so what? Part one.',
'title': 'Louis C.K. Interview Pt. 1 11/3/11',
+ 'duration': 288,
'age_limit': 0,
}
+ }, {
+ 'url': 'http://teamcoco.com/video/timothy-olyphant-drinking-whiskey',
+ 'info_dict': {
+ 'id': '88748',
+ 'ext': 'mp4',
+ 'title': 'Timothy Olyphant Raises A Toast To “Justified”',
+ 'description': 'md5:15501f23f020e793aeca761205e42c24',
+ },
+ 'params': {
+ 'skip_download': True, # m3u8 downloads
+ }
}
]
_VIDEO_ID_REGEXES = (
video_id = self._html_search_regex(
self._VIDEO_ID_REGEXES, webpage, 'video id')
+ preload = None
preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage)
- if not preloads:
- raise ExtractorError('Preload information could not be extracted')
- preload = max([(len(p), p) for p in preloads])[1]
+ 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:
+ raise ExtractorError(
+ 'Preload information could not be extracted', expected=True)
+
data = self._parse_json(
base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id)
'title': data['title'],
'thumbnail': data.get('thumb', {}).get('href'),
'description': data.get('teaser'),
+ 'duration': data.get('duration'),
'age_limit': self._family_friendly_search(webpage),
}