Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xnxx.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6
   7     ExtractorError,
   8 )
   9
  10
  11 class XNXXIE(InfoExtractor):
  12     _VALID_URL = r'^(?:https?://)?(?:video|www)\.xnxx\.com/video([0-9]+)/(.*)'
  13     VIDEO_URL_RE = r'flv_url=(.*?)&amp;'
  14     VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
  15     VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
  16     _TEST = {
  17         u'url': u'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
  18         u'file': u'1135332.flv',
  19         u'md5': u'0831677e2b4761795f68d417e0b7b445',
  20         u'info_dict': {
  21             u"title": u"lida \u00bb Naked Funny Actress  (5)",
  22             u"age_limit": 18,
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         if mobj is None:
  29             raise ExtractorError(u'Invalid URL: %s' % url)
  30         video_id = mobj.group(1)
  31
  32         # Get webpage content
  33         webpage = self._download_webpage(url, video_id)
  34
  35         video_url = self._search_regex(self.VIDEO_URL_RE,
  36             webpage, u'video URL')
  37         video_url = compat_urllib_parse.unquote(video_url)
  38
  39         video_title = self._html_search_regex(self.VIDEO_TITLE_RE,
  40             webpage, u'title')
  41
  42         video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE,
  43             webpage, u'thumbnail', fatal=False)
  44
  45         return [{
  46             'id': video_id,
  47             'url': video_url,
  48             'uploader': None,
  49             'upload_date': None,
  50             'title': video_title,
  51             'ext': 'flv',
  52             'thumbnail': video_thumbnail,
  53             'description': None,
  54             'age_limit': 18,
  55         }]