Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vbox7.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10
  11     ExtractorError,
  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         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         redirect_page, urlh = self._download_webpage_handle(url, video_id)
  32         new_location = self._search_regex(r'window\.location = \'(.*)\';',
  33             redirect_page, 'redirect location')
  34         redirect_url = urlh.geturl() + new_location
  35         webpage = self._download_webpage(redirect_url, video_id,
  36             'Downloading redirect page')
  37
  38         title = self._html_search_regex(r'<title>(.*)</title>',
  39             webpage, 'title').split('/')[0].strip()
  40
  41         info_url = "http://vbox7.com/play/magare.do"
  42         data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
  43         info_request = compat_urllib_request.Request(info_url, data)
  44         info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  45         info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
  46         if info_response is None:
  47             raise ExtractorError('Unable to extract the media url')
  48         (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
  49
  50         return {
  51             'id': video_id,
  52             'url': final_url,
  53             'title': title,
  54             'thumbnail': thumbnail_url,
  55         }