_ Git - youtube-dl/blob - youtube_dl/extractor/hentaistigma.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 class HentaiStigmaIE(InfoExtractor):
   6     _VALID_URL = r'^https?://hentai\.animestigma\.com/(?P<videoid>[^/]+)'
   7     _TEST = {
   8         u'url': u'http://hentai.animestigma.com/inyouchuu-etsu-bonus/',
   9         u'file': u'inyouchuu-etsu-bonus.mp4',
  10         u'md5': u'4e3d07422a68a4cc363d8f57c8bf0d23',
  11         u'info_dict': {
  12             u"title": u"Inyouchuu Etsu Bonus",
  13             u"age_limit": 18,
  14         }
  15     }
  16
  17     def _real_extract(self, url):
  18         mobj = re.match(self._VALID_URL, url)
  19
  20         video_id = mobj.group('videoid')
  21
  22         # Get webpage content
  23         webpage = self._download_webpage(url, video_id)
  24
  25         # Get the video title
  26         video_title = self._html_search_regex(r'<h2 class="posttitle"><a[^>]*>([^<]+)</a>',
  27             webpage, u'title').strip()
  28
  29         # Get the wrapper url
  30         wrap_url = self._html_search_regex(r'<iframe src="([^"]+mp4)"', webpage, u'wrapper url')
  31
  32         # Get wrapper content
  33         wrap_webpage = self._download_webpage(wrap_url, video_id)
  34
  35         video_url = self._html_search_regex(r'clip:\s*{\s*url: "([^"]*)"', wrap_webpage, u'video url')
  36
  37         info = {'id': video_id,
  38                 'url': video_url,
  39                 'title': video_title,
  40                 'format': 'mp4',
  41                 'age_limit': 18}
  42
  43         return [info]