Raphaël G. Git Repositories - youtubedl/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 compat_urlparse
   6 from ..utils import (
   7     ExtractorError,
   8     sanitized_Request,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class Vbox7IE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
  15     _TEST = {
  16         'url': 'http://vbox7.com/play:249bb972c2',
  17         'md5': '99f65c0c9ef9b682b97313e052734c3f',
  18         'info_dict': {
  19             'id': '249bb972c2',
  20             'ext': 'mp4',
  21             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
  22         },
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27
  28         # need to get the page 3 times for the correct jsSecretToken cookie
  29         # which is necessary for the correct title
  30         def get_session_id():
  31             redirect_page = self._download_webpage(url, video_id)
  32             session_id_url = self._search_regex(
  33                 r'var\s*url\s*=\s*\'([^\']+)\';', redirect_page,
  34                 'session id url')
  35             self._download_webpage(
  36                 compat_urlparse.urljoin(url, session_id_url), video_id,
  37                 'Getting session id')
  38
  39         get_session_id()
  40         get_session_id()
  41
  42         webpage = self._download_webpage(url, video_id,
  43                                          'Downloading redirect page')
  44
  45         title = self._html_search_regex(r'<title>(.*)</title>',
  46                                         webpage, 'title').split('/')[0].strip()
  47
  48         info_url = 'http://vbox7.com/play/magare.do'
  49         data = urlencode_postdata({'as3': '1', 'vid': video_id})
  50         info_request = sanitized_Request(info_url, data)
  51         info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  52         info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
  53         if info_response is None:
  54             raise ExtractorError('Unable to extract the media url')
  55         (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
  56
  57         return {
  58             'id': video_id,
  59             'url': final_url,
  60             'title': title,
  61             'thumbnail': thumbnail_url,
  62         }