youtube_dl/extractor/unistra.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 class UnistraIE(InfoExtractor):
   6     _VALID_URL = r'http://utv.unistra.fr/(?:index|video).php\?id_video\=(\d+)'
   7
   8     _TEST = {
   9         u'url': u'http://utv.unistra.fr/video.php?id_video=154',
  10         u'file': u'154.mp4',
  11         u'md5': u'736f605cfdc96724d55bb543ab3ced24',
  12         u'info_dict': {
  13             u'title': u'M!ss Yella',
  14             u'description': u'md5:75e8439a3e2981cd5d4b6db232e8fdfc',
  15         },
  16     }
  17
  18     def _real_extract(self, url):
  19         id = re.match(self._VALID_URL, url).group(1)
  20         webpage = self._download_webpage(url, id)
  21         file = re.search(r'file: "(.*?)",', webpage).group(1)
  22         title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title')
  23
  24         video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file
  25
  26         return {'id': id,
  27                 'title': title,
  28                 'ext': 'mp4',
  29                 'url': video_url,
  30                 'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL),
  31                 'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'),
  32                 }