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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8 )
   9
  10
  11 class SlutloadIE(InfoExtractor):
  12     _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
  13     _TEST = {
  14         'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
  15         'md5': '0cf531ae8006b530bd9df947a6a0df77',
  16         'info_dict': {
  17             'id': 'TD73btpBqSxc',
  18             'ext': 'mp4',
  19             "title": "virginie baisee en cam",
  20             "age_limit": 18,
  21             'thumbnail': 're:https?://.*?\.jpg'
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         video_id = mobj.group('id')
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
  32             webpage, 'title').strip()
  33
  34         video_url = self._html_search_regex(
  35             r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
  36             webpage, 'video URL')
  37         thumbnail = self._html_search_regex(
  38             r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
  39             webpage, 'thumbnail', fatal=False)
  40
  41         return {
  42             'id': video_id,
  43             'url': video_url,
  44             'title': video_title,
  45             'thumbnail': thumbnail,
  46             'age_limit': 18
  47         }