Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ina.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class InaIE(InfoExtractor):
   7     """Information Extractor for Ina.fr"""
   8     _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I?[A-F0-9]+)/.*'
   9     _TEST = {
  10         u'url': u'www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
  11         u'file': u'I12055569.mp4',
  12         u'md5': u'a667021bf2b41f8dc6049479d9bb38a3',
  13         u'info_dict': {
  14             u"title": u"Fran\u00e7ois Hollande \"Je crois que c'est clair\""
  15         }
  16     }
  17
  18     def _real_extract(self,url):
  19         mobj = re.match(self._VALID_URL, url)
  20
  21         video_id = mobj.group('id')
  22         mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
  23         video_extension = 'mp4'
  24         webpage = self._download_webpage(mrss_url, video_id)
  25
  26         self.report_extraction(video_id)
  27
  28         video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
  29             webpage, u'video URL')
  30
  31         video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
  32             webpage, u'title')
  33
  34         return [{
  35             'id':       video_id,
  36             'url':      video_url,
  37             'ext':      video_extension,
  38             'title':    video_title,
  39         }]