youtube_dl/extractor/youjizz.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class YouJizzIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]+)?-(?P<id>[0-9]+)\.html(?:$|[?#])'
   8     _TESTS = [{
   9         'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
  10         'md5': '78fc1901148284c69af12640e01c6310',
  11         'info_dict': {
  12             'id': '2189178',
  13             'ext': 'mp4',
  14             'title': 'Zeichentrick 1',
  15             'age_limit': 18,
  16         }
  17     }, {
  18         'url': 'http://www.youjizz.com/videos/-2189178.html',
  19         'only_matching': True,
  20     }]
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24         webpage = self._download_webpage(url, video_id)
  25         # YouJizz's HTML5 player has invalid HTML
  26         webpage = webpage.replace('"controls', '" controls')
  27         age_limit = self._rta_search(webpage)
  28         video_title = self._html_search_regex(
  29             r'<title>\s*(.*)\s*</title>', webpage, 'title')
  30
  31         info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
  32
  33         info_dict.update({
  34             'id': video_id,
  35             'title': video_title,
  36             'age_limit': age_limit,
  37         })
  38
  39         return info_dict