youtube_dl/extractor/canalc2.py

   1 # coding: utf-8
   2 import re
   3
   4 from .common import InfoExtractor
   5
   6
   7 class Canalc2IE(InfoExtractor):
   8     IE_NAME = 'canalc2.tv'
   9     _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
  10
  11     _TEST = {
  12         u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
  13         u'file': u'12163.mp4',
  14         u'md5': u'060158428b650f896c542dfbb3d6487f',
  15         u'info_dict': {
  16             u'title': u'Terrasses du Numérique'
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = re.match(self._VALID_URL, url).group('id')
  22         # We need to set the voir field for getting the file name
  23         url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
  24         webpage = self._download_webpage(url, video_id)
  25         file_name = self._search_regex(
  26             r"so\.addVariable\('file','(.*?)'\);",
  27             webpage, 'file name')
  28         video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
  29
  30         title = self._html_search_regex(
  31             r'class="evenement8">(.*?)</a>', webpage, u'title')
  32
  33         return {'id': video_id,
  34                 'ext': 'mp4',
  35                 'url': video_url,
  36                 'title': title,
  37                 }