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
   7
   8 class SlutloadIE(InfoExtractor):
   9     _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
  10     _TESTS = [{
  11         'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
  12         'md5': '868309628ba00fd488cf516a113fd717',
  13         'info_dict': {
  14             'id': 'TD73btpBqSxc',
  15             'ext': 'mp4',
  16             'title': 'virginie baisee en cam',
  17             'age_limit': 18,
  18             'thumbnail': r're:https?://.*?\.jpg'
  19         }
  20     }, {
  21         # mobile site
  22         'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/',
  23         'only_matching': True,
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         desktop_url = re.sub(r'^(https?://)mobile\.', r'\1', url)
  30         webpage = self._download_webpage(desktop_url, video_id)
  31
  32         video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
  33                                               webpage, 'title').strip()
  34
  35         video_url = self._html_search_regex(
  36             r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
  37             webpage, 'video URL')
  38         thumbnail = self._html_search_regex(
  39             r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
  40             webpage, 'thumbnail', fatal=False)
  41
  42         return {
  43             'id': video_id,
  44             'url': video_url,
  45             'title': video_title,
  46             'thumbnail': thumbnail,
  47             'age_limit': 18
  48         }