You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
youtube-dl/youtube_dl/extractor/vbox7.py

54 lines
2.0 KiB
Python

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