_ Git - youtube-dl/blob - 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'md5:104892c71bd48e55d70b902736b81bbf',
  15         },
  16     }
  17
  18     def _real_extract(self, url):
  19         video_id = re.match(self._VALID_URL, url).group(1)
  20         webpage = self._download_webpage(url, video_id)
  21         width = re.search(r'width: "(\d*?)",', webpage).group(1)
  22         height = re.search(r'height: "(\d*?)",', webpage).group(1)
  23         files = re.findall(r'file: "(.*?)"', webpage)
  24         video_url = 'http://vod-flash.u-strasbg.fr:8080'
  25         formats = [{
  26             'format_id': 'SD',
  27             'url': video_url + files[0],
  28             'ext': 'mp4',
  29             'resolution': width + 'x' + height
  30             }]
  31         if files[1] != files[0]:
  32             formats.append({
  33             'format_id': 'HD',
  34             'url': video_url + files[1],
  35             'ext': 'mp4'
  36             })
  37         title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title')
  38
  39         return {'id': video_id,
  40                 'title': title,
  41                 'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL),
  42                 'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'),
  43                 'formats': formats
  44                 }