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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class UstreamIE(InfoExtractor):
   7     _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
   8     IE_NAME = u'ustream'
   9     _TEST = {
  10         u'url': u'http://www.ustream.tv/recorded/20274954',
  11         u'file': u'20274954.flv',
  12         u'md5': u'088f151799e8f572f84eb62f17d73e5c',
  13         u'info_dict': {
  14             u"uploader": u"Young Americans for Liberty",
  15             u"title": u"Young Americans for Liberty February 7, 2012 2:28 AM"
  16         }
  17     }
  18
  19     def _real_extract(self, url):
  20         m = re.match(self._VALID_URL, url)
  21         video_id = m.group('videoID')
  22
  23         video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
  24         webpage = self._download_webpage(url, video_id)
  25
  26         self.report_extraction(video_id)
  27
  28         video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
  29             webpage, u'title')
  30
  31         uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
  32             webpage, u'uploader', fatal=False, flags=re.DOTALL)
  33
  34         thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
  35             webpage, u'thumbnail', fatal=False)
  36
  37         info = {
  38                 'id': video_id,
  39                 'url': video_url,
  40                 'ext': 'flv',
  41                 'title': video_title,
  42                 'uploader': uploader,
  43                 'thumbnail': thumbnail,
  44                }
  45         return info