]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tf1.py
   2 from __future__ 
import unicode_literals
 
   4 from .common 
import InfoExtractor
 
   7 class TF1IE(InfoExtractor
): 
   8     """TF1 uses the wat.tv player.""" 
   9     _VALID_URL 
= r
'https?://(?:(?:videos|www|lci)\.tf1|(?:www\.)?(?:tfou|ushuaiatv|histoire|tvbreizh))\.fr/(?:[^/]+/)*(?P<id>[^/?#.]+)' 
  11         'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', 
  15             'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle', 
  16             'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.', 
  19             # Sometimes wat serves the whole file with the --test option 
  20             'skip_download': True, 
  23         'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html', 
  25             'id': 'le-grand-mysterioso-chuggington-7085291-739', 
  27             'title': 'Le grand Mystérioso - Chuggington', 
  28             'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.', 
  29             'upload_date': '20150103', 
  32             # Sometimes wat serves the whole file with the --test option 
  33             'skip_download': True, 
  35         'skip': 'HTTP Error 410: Gone', 
  37         'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html', 
  38         'only_matching': True, 
  40         'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html', 
  41         'only_matching': True, 
  43         'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html', 
  44         'only_matching': True, 
  47     def _real_extract(self
, url
): 
  48         video_id 
= self
._match
_id
(url
) 
  49         webpage 
= self
._download
_webpage
(url
, video_id
) 
  50         wat_id 
= self
._html
_search
_regex
( 
  51             r
'(["\'])(?
:https?
:)?
//www\
.wat\
.tv
/embedframe
/.*?
(?P
<id>\d{8}
)\
1', 
  52             webpage, 'wat 
id', group='id') 
  53         return self.url_result('wat
:%s' % wat_id, 'Wat
')