Raphaël G. Git Repositories - youtubedl/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 (
   6     compat_urllib_parse,
   7 )
   8
   9
  10 class XNXXIE(InfoExtractor):
  11     _VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P<id>[0-9]+)/(.*)'
  12     _TEST = {
  13         'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
  14         'md5': '0831677e2b4761795f68d417e0b7b445',
  15         'info_dict': {
  16             'id': '1135332',
  17             'ext': 'flv',
  18             'title': 'lida » Naked Funny Actress  (5)',
  19             'age_limit': 18,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(url, video_id)
  26
  27         video_url = self._search_regex(r'flv_url=(.*?)&amp;',
  28                                        webpage, 'video URL')
  29         video_url = compat_urllib_parse.unquote(video_url)
  30
  31         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
  32                                               webpage, 'title')
  33
  34         video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
  35                                              webpage, 'thumbnail', fatal=False)
  36
  37         return {
  38             'id': video_id,
  39             'url': video_url,
  40             'title': video_title,
  41             'ext': 'flv',
  42             'thumbnail': video_thumbnail,
  43             'age_limit': 18,
  44         }