_ Git - youtube-dl/blob - youtube_dl/extractor/vbox7.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     compat_urllib_request,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11 )
  12
  13
  14 class Vbox7IE(InfoExtractor):
  15     _VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
  16     _TEST = {
  17         'url': 'http://vbox7.com/play:249bb972c2',
  18         'md5': '99f65c0c9ef9b682b97313e052734c3f',
  19         'info_dict': {
  20             'id': '249bb972c2',
  21             'ext': 'mp4',
  22             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         redirect_page, urlh = self._download_webpage_handle(url, video_id)
  30         new_location = self._search_regex(r'window\.location = \'(.*)\';',
  31                                           redirect_page, 'redirect location')
  32         redirect_url = urlh.geturl() + new_location
  33         webpage = self._download_webpage(redirect_url, video_id,
  34                                          'Downloading redirect page')
  35
  36         title = self._html_search_regex(r'<title>(.*)</title>',
  37                                         webpage, 'title').split('/')[0].strip()
  38
  39         info_url = "http://vbox7.com/play/magare.do"
  40         data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
  41         info_request = compat_urllib_request.Request(info_url, data)
  42         info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  43         info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
  44         if info_response is None:
  45             raise ExtractorError('Unable to extract the media url')
  46         (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
  47
  48         return {
  49             'id': video_id,
  50             'url': final_url,
  51             'title': title,
  52             'thumbnail': thumbnail_url,
  53         }