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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_unquote
   6
   7
   8 class XNXXIE(InfoExtractor):
   9     _VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video-?(?P<id>[0-9a-z]+)/(.*)'
  10     _TESTS = [{
  11         'url': 'http://www.xnxx.com/video-6gqggeb/hd_star-581_sam',
  12         'md5': '6a2a6aff3f10467d94e572edb7b7deb6',
  13         'info_dict': {
  14             'id': '6gqggeb',
  15             'ext': 'flv',
  16             'title': 'HD STAR-581 sam',
  17             'age_limit': 18,
  18         },
  19     }, {
  20         'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
  21         'only_matching': True,
  22     }]
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         video_url = self._search_regex(r'flv_url=(.*?)&amp;',
  29                                        webpage, 'video URL')
  30         video_url = compat_urllib_parse_unquote(video_url)
  31
  32         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
  33                                               webpage, 'title')
  34
  35         video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
  36                                              webpage, 'thumbnail', fatal=False)
  37
  38         return {
  39             'id': video_id,
  40             'url': video_url,
  41             'title': video_title,
  42             'ext': 'flv',
  43             'thumbnail': video_thumbnail,
  44             'age_limit': 18,
  45         }