X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvbox7.py;h=455b6d9da62f221cf0854655f707d5963546840f;hb=9e1a5b845586a0a5431fb72467142046d8571e6f;hp=2f3ce46e86a880fa5058c6ebcb2fce28ad913c82;hpb=01c10ca26ed5e5df0b975a3421f1186e5b94d925;p=youtube-dl diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py index 2f3ce46e8..455b6d9da 100644 --- a/youtube_dl/extractor/vbox7.py +++ b/youtube_dl/extractor/vbox7.py @@ -1,3 +1,6 @@ +# encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -10,37 +13,43 @@ from ..utils import ( class Vbox7IE(InfoExtractor): - """Information Extractor for Vbox7""" - _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)' - - def _real_extract(self,url): + _VALID_URL = r'http://(www\.)?vbox7\.com/play:(?P[^/]+)' + _TEST = { + 'url': 'http://vbox7.com/play:249bb972c2', + 'md5': '99f65c0c9ef9b682b97313e052734c3f', + 'info_dict': { + 'id': '249bb972c2', + 'ext': 'mp4', + 'title': 'Смях! Чудо - чист за секунди - Скрита камера', + }, + } + + 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) + video_id = mobj.group('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 - 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'(.*)', - webpage, u'title').split('/')[0].strip() + webpage, 'title').split('/')[0].strip() - ext = "flv" 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.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: - 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('&')) - return [{ - 'id': video_id, - 'url': final_url, - 'ext': ext, - 'title': title, + return { + 'id': video_id, + 'url': final_url, + 'title': title, 'thumbnail': thumbnail_url, - }] + }