youtube_dl/extractor/franceinter.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 class FranceInterIE(InfoExtractor):
   5
   6     _VALID_URL=r'http://www.franceinter.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
   7     IE_NAME='FranceInter'
   8     _TEST={
   9            u'url':u'http://www.franceinter.fr/player/reecouter?play=793962',
  10            u'file':u'793962.mp3'
  11
  12
  13            }
  14
  15     #Easier to use python string matching than regex for a simple match
  16     def get_download_url(self,webpage):
  17
  18         start=webpage.index('&urlAOD=')+8
  19         end=webpage.index('&startTime')
  20         return u'http://www.franceinter.fr/%s'%webpage[start:end]
  21
  22     def get_title(self,webpage):
  23         start=webpage.index('<span class="title diffusion">')+30
  24         end=webpage.index('</span> dans')
  25
  26         return webpage[start:end]
  27     def _real_extract(self,url):
  28
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31
  32         webpage=self._download_webpage(url,video_id)
  33
  34         title=self.get_title(webpage)
  35
  36         video_url=self.get_download_url(webpage)
  37
  38         return{'id': video_id,u'url': video_url,u'title': title}
  39
  40