From ecb3e676a52a0b478511751ca84da74188972b39 Mon Sep 17 00:00:00 2001 From: "M.Yasoob Khalid" Date: Sat, 8 Jun 2013 12:44:38 +0500 Subject: [PATCH] Added Vbox7 Infoextractor --- test/tests.json | 9 +++++++++ youtube_dl/InfoExtractors.py | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) diff --git a/test/tests.json b/test/tests.json index c39d1d9c1..04be912ce 100644 --- a/test/tests.json +++ b/test/tests.json @@ -500,5 +500,14 @@ "info_dict":{ "title":"TAME" } + }, + { + "name": "Vbox7", + "url": "http://vbox7.com/play:249bb972c2", + "file": "249bb972c2.flv", + "md5": "9c70d6d956f888bdc08c124acc120cfe", + "info_dict":{ + "title":"Смях! Чудо - чист за секунди - Скрита камера" + } } ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index b40edf5fb..8535a3e9a 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -4534,6 +4534,39 @@ 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] + + return [{ + 'id': video_id, + 'url': final_url, + 'ext': ext, + 'title': title, + }] def gen_extractors(): """ Return a list of an instance of every supported extractor. @@ -4598,6 +4631,7 @@ def gen_extractors(): TeamcocoIE(), XHamsterIE(), HypemIE(), + Vbox7IE(), GenericIE() ]