yt_dlp/extractor/behindkink.py

   1 from .common import InfoExtractor
   2 from ..utils import url_basename
   3
   4
   5 class BehindKinkIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
   7     _TEST = {
   8         'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
   9         'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
  10         'info_dict': {
  11             'id': '37127',
  12             'ext': 'mp4',
  13             'title': 'What are you passionate about – Marley Blaze',
  14             'description': 'md5:aee8e9611b4ff70186f752975d9b94b4',
  15             'upload_date': '20141205',
  16             'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
  17             'age_limit': 18,
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = self._match_valid_url(url)
  23         display_id = mobj.group('id')
  24
  25         webpage = self._download_webpage(url, display_id)
  26
  27         video_url = self._search_regex(
  28             r'<source src="([^"]+)"', webpage, 'video URL')
  29         video_id = url_basename(video_url).split('_')[0]
  30         upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day')
  31
  32         return {
  33             'id': video_id,
  34             'display_id': display_id,
  35             'url': video_url,
  36             'title': self._og_search_title(webpage),
  37             'thumbnail': self._og_search_thumbnail(webpage),
  38             'description': self._og_search_description(webpage),
  39             'upload_date': upload_date,
  40             'age_limit': 18,
  41         }