yt-dlp/youtube_dl/extractor/vbox7.py

56 lines
2.0 KiB
Python
Raw Normal View History

2014-02-04 15:02:53 -07:00
# encoding: utf-8
from __future__ import unicode_literals
2013-06-23 14:25:46 -06:00
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
compat_urllib_request,
ExtractorError,
)
class Vbox7IE(InfoExtractor):
2014-02-04 15:02:53 -07:00
_VALID_URL = r'http://(www\.)?vbox7\.com/play:(?P<id>[^/]+)'
2013-06-27 12:46:46 -06:00
_TEST = {
2014-02-04 15:02:53 -07:00
'url': 'http://vbox7.com/play:249bb972c2',
'md5': '99f65c0c9ef9b682b97313e052734c3f',
'info_dict': {
'id': '249bb972c2',
'ext': 'mp4',
2014-02-04 15:02:53 -07:00
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
},
2013-06-27 12:46:46 -06:00
}
2013-06-23 14:25:46 -06:00
2014-02-04 15:02:53 -07:00
def _real_extract(self, url):
2013-06-23 14:25:46 -06:00
mobj = re.match(self._VALID_URL, url)
2014-02-04 15:02:53 -07:00
video_id = mobj.group('id')
2013-06-23 14:25:46 -06:00
redirect_page, urlh = self._download_webpage_handle(url, video_id)
2014-02-04 15:02:53 -07:00
new_location = self._search_regex(r'window\.location = \'(.*)\';',
2014-11-23 13:39:15 -07:00
redirect_page, 'redirect location')
2013-06-23 14:25:46 -06:00
redirect_url = urlh.geturl() + new_location
2014-02-04 15:02:53 -07:00
webpage = self._download_webpage(redirect_url, video_id,
2014-11-23 13:39:15 -07:00
'Downloading redirect page')
2013-06-23 14:25:46 -06:00
title = self._html_search_regex(r'<title>(.*)</title>',
2014-11-23 13:39:15 -07:00
webpage, 'title').split('/')[0].strip()
2013-06-23 14:25:46 -06:00
info_url = "http://vbox7.com/play/magare.do"
2014-02-04 15:02:53 -07:00
data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
2013-06-23 14:25:46 -06:00
info_request = compat_urllib_request.Request(info_url, data)
info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
2014-02-04 15:02:53 -07:00
info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
2013-06-23 14:25:46 -06:00
if info_response is None:
2014-02-04 15:02:53 -07:00
raise ExtractorError('Unable to extract the media url')
2013-06-23 14:25:46 -06:00
(final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
2014-02-04 15:02:53 -07:00
return {
'id': video_id,
'url': final_url,
'title': title,
2013-06-23 14:25:46 -06:00
'thumbnail': thumbnail_url,
2014-02-04 15:02:53 -07:00
}