Raphaël G. Git Repositories - youtubedl/blob - 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
  16     def _real_extract(self,url):
  17         mobj = re.match(self._VALID_URL, url)
  18         if mobj is None:
  19             raise ExtractorError(u'Invalid URL: %s' % url)
  20         video_id = mobj.group(1)
  21
  22         redirect_page, urlh = self._download_webpage_handle(url, video_id)
  23         new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
  24         redirect_url = urlh.geturl() + new_location
  25         webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
  26
  27         title = self._html_search_regex(r'<title>(.*)</title>',
  28             webpage, u'title').split('/')[0].strip()
  29
  30         ext = "flv"
  31         info_url = "http://vbox7.com/play/magare.do"
  32         data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id})
  33         info_request = compat_urllib_request.Request(info_url, data)
  34         info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  35         info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage')
  36         if info_response is None:
  37             raise ExtractorError(u'Unable to extract the media url')
  38         (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
  39
  40         return [{
  41             'id':        video_id,
  42             'url':       final_url,
  43             'ext':       ext,
  44             'title':     title,
  45             'thumbnail': thumbnail_url,
  46         }]