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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import compat_urllib_parse
   5
   6 class PornHdIE(InfoExtractor):
   7     _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
   8     _TEST = {
   9         u'id': u'1962',
  10         u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  11         u'md5': u'4fe06e5108e8b524c35896f4c54c7155',
  12         u'info_dict': {
  13             u"title": u"sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
  14             u"age_limit": 18,
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         mobj = re.match(self._VALID_URL, url)
  20
  21         video_id = mobj.group('video_id')
  22         video_title = mobj.group('video_title')
  23         video_extension = 'flv'
  24
  25         webpage = self._download_webpage(url, video_id)
  26
  27
  28         self.report_extraction(video_id)
  29
  30         video_url = self._html_search_regex(
  31             r'&hd=(http.+?)&', webpage, u'video URL')
  32         video_url = compat_urllib_parse.unquote(video_url)
  33
  34         age_limit = 18
  35
  36         return {
  37             'id':        video_id,
  38             'url':       video_url,
  39             'ext':       video_extension,
  40             'title':     video_title,
  41             'age_limit': age_limit,
  42         }