youtube_dl/extractor/hentaistigma.py

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