From: Jaime Marquínez Ferrándiz Date: Sat, 8 Jun 2013 08:47:52 +0000 (+0200) Subject: Merge pull request #878 from yasoob/master X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=cd453d38bbd038076c1b301396c2f996e77e261f;p=youtube-dl Merge pull request #878 from yasoob/master Added Vbox7.com InfoExtractor and tests. --- cd453d38bbd038076c1b301396c2f996e77e261f diff --cc youtube_dl/InfoExtractors.py index b40edf5fb,8535a3e9a..11fcd6adc --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@@ -4534,6 -4534,39 +4534,40 @@@ class HypemIE(InfoExtractor) 'artist': artist, }] + 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) + redirect_url = urlh.geturl() + re.search(r'window\.location = \'(.*)\';', redirect_page).group(1) + webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page') + + title = re.search(r'(.*)', webpage) + title = (title.group(1)).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 = (info_response.split('&')[0]).split('=')[1] ++ (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&')) + + return [{ - 'id': video_id, - 'url': final_url, - 'ext': ext, - 'title': title, ++ 'id': video_id, ++ 'url': final_url, ++ 'ext': ext, ++ 'title': title, ++ 'thumbnail': thumbnail_url, + }] def gen_extractors(): """ Return a list of an instance of every supported extractor.