1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-22 22:42:52 +08:00
youtube-dl/youtube_dl/extractor/vbox7.py

47 lines
1.7 KiB
Python
Raw Normal View History

2013-06-24 04:25:46 +08:00
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
compat_urllib_request,
ExtractorError,
)
class Vbox7IE(InfoExtractor):
"""Information Extractor for Vbox7"""
_VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
redirect_page, urlh = self._download_webpage_handle(url, video_id)
new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
redirect_url = urlh.geturl() + new_location
webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
title = self._html_search_regex(r'<title>(.*)</title>',
webpage, u'title').split('/')[0].strip()
ext = "flv"
info_url = "http://vbox7.com/play/magare.do"
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')
info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage')
if info_response is None:
raise ExtractorError(u'Unable to extract the media url')
(final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
return [{
'id': video_id,
'url': final_url,
'ext': ext,
'title': title,
'thumbnail': thumbnail_url,
}]