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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class KeekIE(InfoExtractor):
   7     _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
   8     IE_NAME = u'keek'
   9     _TEST = {
  10         u'url': u'http://www.keek.com/ytdl/keeks/NODfbab',
  11         u'file': u'NODfbab.mp4',
  12         u'md5': u'9b0636f8c0f7614afa4ea5e4c6e57e83',
  13         u'info_dict': {
  14             u"uploader": u"ytdl",
  15             u"title": u"test chars: \"'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
  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://cdn.keek.com/keek/video/%s' % video_id
  24         thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
  25         webpage = self._download_webpage(url, video_id)
  26
  27         video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
  28             webpage, u'title')
  29
  30         uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
  31             webpage, u'uploader', fatal=False)
  32
  33         info = {
  34                 'id': video_id,
  35                 'url': video_url,
  36                 'ext': 'mp4',
  37                 'title': video_title,
  38                 'thumbnail': thumbnail,
  39                 'uploader': uploader
  40         }
  41         return [info]