[vbox7] simplify

This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-04 23:02:53 +01:00
parent 9bc70948e1
commit 50451f2a18
1 changed files with 27 additions and 25 deletions

View File

@ -1,3 +1,6 @@
# encoding: utf-8
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -10,45 +13,44 @@ from ..utils import (
class Vbox7IE(InfoExtractor): class Vbox7IE(InfoExtractor):
"""Information Extractor for Vbox7""" _VALID_URL = r'http://(www\.)?vbox7\.com/play:(?P<id>[^/]+)'
_VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
_TEST = { _TEST = {
u'url': u'http://vbox7.com/play:249bb972c2', 'url': 'http://vbox7.com/play:249bb972c2',
u'file': u'249bb972c2.flv', 'md5': '99f65c0c9ef9b682b97313e052734c3f',
u'md5': u'99f65c0c9ef9b682b97313e052734c3f', 'info_dict': {
u'info_dict': { 'id': '249bb972c2',
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" 'ext': 'flv',
} 'title': 'Смях! Чудо - чист за секунди - Скрита камера',
},
} }
def _real_extract(self,url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: video_id = mobj.group('id')
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
redirect_page, urlh = self._download_webpage_handle(url, video_id) redirect_page, urlh = self._download_webpage_handle(url, video_id)
new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location') new_location = self._search_regex(r'window\.location = \'(.*)\';',
redirect_page, 'redirect location')
redirect_url = urlh.geturl() + new_location redirect_url = urlh.geturl() + new_location
webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page') webpage = self._download_webpage(redirect_url, video_id,
'Downloading redirect page')
title = self._html_search_regex(r'<title>(.*)</title>', title = self._html_search_regex(r'<title>(.*)</title>',
webpage, u'title').split('/')[0].strip() webpage, 'title').split('/')[0].strip()
ext = "flv"
info_url = "http://vbox7.com/play/magare.do" info_url = "http://vbox7.com/play/magare.do"
data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id}) data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
info_request = compat_urllib_request.Request(info_url, data) info_request = compat_urllib_request.Request(info_url, data)
info_request.add_header('Content-Type', 'application/x-www-form-urlencoded') info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage') info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
if info_response is None: if info_response is None:
raise ExtractorError(u'Unable to extract the media url') raise ExtractorError('Unable to extract the media url')
(final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&')) (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
return [{ return {
'id': video_id, 'id': video_id,
'url': final_url, 'url': final_url,
'ext': ext, 'ext': 'flv',
'title': title, 'title': title,
'thumbnail': thumbnail_url, 'thumbnail': thumbnail_url,
}] }