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 (
   6     compat_urllib_parse,
   7     compat_urlparse,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11     sanitized_Request,
  12 )
  13
  14
  15 class Vbox7IE(InfoExtractor):
  16     _VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
  17     _TEST = {
  18         'url': 'http://vbox7.com/play:249bb972c2',
  19         'md5': '99f65c0c9ef9b682b97313e052734c3f',
  20         'info_dict': {
  21             'id': '249bb972c2',
  22             'ext': 'mp4',
  23             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
  24         },
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29
  30         # need to get the page 3 times for the correct jsSecretToken cookie
  31         # which is necessary for the correct title
  32         def get_session_id():
  33             redirect_page = self._download_webpage(url, video_id)
  34             session_id_url = self._search_regex(
  35                 r'var\s*url\s*=\s*\'([^\']+)\';', redirect_page,
  36                 'session id url')
  37             self._download_webpage(
  38                 compat_urlparse.urljoin(url, session_id_url), video_id,
  39                 'Getting session id')
  40
  41         get_session_id()
  42         get_session_id()
  43
  44         webpage = self._download_webpage(url, video_id,
  45                                          'Downloading redirect page')
  46
  47         title = self._html_search_regex(r'<title>(.*)</title>',
  48                                         webpage, 'title').split('/')[0].strip()
  49
  50         info_url = "http://vbox7.com/play/magare.do"
  51         data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
  52         info_request = sanitized_Request(info_url, data)
  53         info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  54         info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
  55         if info_response is None:
  56             raise ExtractorError('Unable to extract the media url')
  57         (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
  58
  59         return {
  60             'id': video_id,
  61             'url': final_url,
  62             'title': title,
  63             'thumbnail': thumbnail_url,
  64         }