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
  10     def _real_extract(self, url):
  11         m = re.match(self._VALID_URL, url)
  12         video_id = m.group('videoID')
  13
  14         video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
  15         thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
  16         webpage = self._download_webpage(url, video_id)
  17
  18         video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
  19             webpage, u'title')
  20
  21         uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
  22             webpage, u'uploader', fatal=False)
  23
  24         info = {
  25                 'id': video_id,
  26                 'url': video_url,
  27                 'ext': 'mp4',
  28                 'title': video_title,
  29                 'thumbnail': thumbnail,
  30                 'uploader': uploader
  31         }
  32         return [info]