_ Git - youtube-dl/blob - youtube_dl/extractor/canalc2.py

   1 # coding: utf-8
   2 """Extractor for canalc2.tv"""
   3 import re
   4 import lxml.html
   5
   6 from .common import InfoExtractor
   7
   8 class Canalc2IE(InfoExtractor):
   9     """Extractor for canalc2.tv"""
  10     _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui'
  11
  12     _TEST = {
  13         u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
  14         u'file': u'12163.mp4',
  15         u'md5': u'c00fa80517373764ff5c0b5eb5a58780',
  16         u'info_dict': {
  17             u'title': u'Terrasses du Numérique'
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = re.match(self._VALID_URL, url).group(1)
  23         webpage = self._download_webpage(url, video_id)
  24         file_name = re.search(r"so\.addVariable\('file','(.*?)'\);",
  25             webpage).group(1)
  26
  27         video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
  28
  29         html   = lxml.html.fromstring(webpage)
  30
  31         title = html.cssselect('.evenement8')[0].text_content()
  32
  33         return {'id': video_id,
  34                 'ext' : 'mp4',
  35                 'url' : video_url,
  36                 'title' : title
  37                 }