youtube_dl/extractor/vbox7.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6     compat_urllib_request,
   7
   8     ExtractorError,
   9 )
  10
  11
  12 class Vbox7IE(InfoExtractor):
  13     """Information Extractor for Vbox7"""
  14     _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
  15     _TEST = {
  16         u'url': u'http://vbox7.com/play:249bb972c2',
  17         u'file': u'249bb972c2.flv',
  18         u'md5': u'9c70d6d956f888bdc08c124acc120cfe',
  19         u'info_dict': {
  20             u"title": u"\u0421\u043c\u044f\u0445! \u0427\u0443\u0434\u043e - \u0447\u0438\u0441\u0442 \u0437\u0430 \u0441\u0435\u043a\u0443\u043d\u0434\u0438 - \u0421\u043a\u0440\u0438\u0442\u0430 \u043a\u0430\u043c\u0435\u0440\u0430"
  21         }
  22     }
  23
  24     def _real_extract(self,url):
  25         mobj = re.match(self._VALID_URL, url)
  26         if mobj is None:
  27             raise ExtractorError(u'Invalid URL: %s' % url)
  28         video_id = mobj.group(1)
  29
  30         redirect_page, urlh = self._download_webpage_handle(url, video_id)
  31         new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
  32         redirect_url = urlh.geturl() + new_location
  33         webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
  34
  35         title = self._html_search_regex(r'<title>(.*)</title>',
  36             webpage, u'title').split('/')[0].strip()
  37
  38         ext = "flv"
  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, u'Downloading info webpage')
  44         if info_response is None:
  45             raise ExtractorError(u'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             'ext':       ext,
  52             'title':     title,
  53             'thumbnail': thumbnail_url,
  54         }]