From: Pierre Rudloff Date: Tue, 17 Sep 2013 20:13:40 +0000 (+0200) Subject: Extractor for websurg.com X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=d79a0e233a329e543797478a2eeb377e469c0f3f;p=youtube-dl Extractor for websurg.com --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 761575062..19ded18f1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -109,6 +109,7 @@ from .videofyme import VideofyMeIE from .vimeo import VimeoIE, VimeoChannelIE from .vine import VineIE from .wat import WatIE +from .websurg import WeBSurgIE from .weibo import WeiboIE from .wimp import WimpIE from .worldstarhiphop import WorldStarHipHopIE diff --git a/youtube_dl/extractor/websurg.py b/youtube_dl/extractor/websurg.py new file mode 100644 index 000000000..953bc9831 --- /dev/null +++ b/youtube_dl/extractor/websurg.py @@ -0,0 +1,67 @@ +# coding: utf-8 + +import re + +from ..utils import ( + compat_urllib_request, + compat_urllib_parse +) + +from .common import InfoExtractor + +class WeBSurgIE(InfoExtractor): + IE_NAME = u'websurg.com' + _VALID_URL = r'http://.*?\.websurg\.com/MEDIA/\?noheader=1&doi=(.*)' + + _TEST = { + u'url': u'http://www.websurg.com/MEDIA/?noheader=1&doi=vd01en4012', + u'file': u'vd01en4012.mp4', + u'params': { + u'skip_download': True, + } + } + + _LOGIN_URL = 'http://www.websurg.com/inc/login/login_div.ajax.php?login=1' + + def _real_extract(self, url): + + login_form = { + 'username': self._downloader.params['username'], + 'password': self._downloader.params['password'], + 'Submit': 1 + } + + request = compat_urllib_request.Request( + self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) + request.add_header( + 'Content-Type', 'application/x-www-form-urlencoded;charset=utf-8') + login_results = compat_urllib_request.urlopen(request).info() + + sessid = re.match(r'PHPSESSID=(.*);', + login_results['Set-Cookie']).group(1) + request = compat_urllib_request.Request( + url, compat_urllib_parse.urlencode(login_form), + {'Cookie': 'PHPSESSID=' + sessid + ';'}) + webpage = compat_urllib_request.urlopen(request).read() + + video_id = re.match(self._VALID_URL, url).group(1) + + url_info = re.search(r'streamer="(.*?)" src="(.*?)"', webpage) + + if url_info is None: + self._downloader.report_warning( + u'Unable to log in: bad username/password') + return + + return {'id': video_id, + 'title' : re.search( + r'property="og:title" content="(.*?)" />' + , webpage).group(1), + 'description': re.search( + r'name="description" content="(.*?)" />', webpage).group(1), + 'ext' : 'mp4', + 'url' : url_info.group(1) + '/' + url_info.group(2), + 'thumbnail': re.search( + r'property="og:image" content="(.*?)" />', webpage + ).group(1) + }