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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6 )
   7
   8
   9 class XVideosIE(InfoExtractor):
  10     _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
  11     _TEST = {
  12         u'url': u'http://www.xvideos.com/video939581/funny_porns_by_s_-1',
  13         u'file': u'939581.flv',
  14         u'md5': u'1d0c835822f0a71a7bf011855db929d0',
  15         u'info_dict': {
  16             u"title": u"Funny Porns By >>>>S<<<<<< -1"
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22         video_id = mobj.group(1)
  23
  24         webpage = self._download_webpage(url, video_id)
  25
  26         self.report_extraction(video_id)
  27
  28         # Extract video URL
  29         video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
  30             webpage, u'video URL'))
  31
  32         # Extract title
  33         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
  34             webpage, u'title')
  35
  36         # Extract video thumbnail
  37         video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
  38             webpage, u'thumbnail', fatal=False)
  39
  40         info = {
  41             'id': video_id,
  42             'url': video_url,
  43             'uploader': None,
  44             'upload_date': None,
  45             'title': video_title,
  46             'ext': 'flv',
  47             'thumbnail': video_thumbnail,
  48             'description': None,
  49         }
  50
  51         return [info]