youtube_dl/extractor/hentaistigma.py

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