X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxhamster.py;h=361619694980d3260ff81aeed2d0d07294739a0e;hb=a8c6b2415535054862235a7286ac03db474c95a0;hp=0fd0775834fe607cfe08259bda3d78b74c73fe3a;hpb=53b0f3e4e290016ccc0a905ec8a18efb5bd9af8a;p=youtube-dl diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 0fd077583..361619694 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -4,14 +4,15 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, unescapeHTML, + determine_ext, ExtractorError, ) class XHamsterIE(InfoExtractor): """Information Extractor for xHamster""" - _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P[0-9]+)/.*\.html' - _TEST = { + _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.+?)\.html(?:\?.*)?' + _TESTS = [{ u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', u'file': u'1509445.flv', u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa', @@ -20,13 +21,24 @@ class XHamsterIE(InfoExtractor): u"uploader_id": u"Ruseful2011", u"title": u"FemaleAgent Shy beauty takes the bait" } - } + }, + { + u'url': u'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', + u'file': u'2221348.flv', + u'md5': u'e767b9475de189320f691f49c679c4c7', + u'info_dict': { + u"upload_date": u"20130914", + u"uploader_id": u"jojo747400", + u"title": u"Britney Spears Sexy Booty" + } + }] def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id + seo = mobj.group('seo') + mrss_url = 'http://xhamster.com/movies/%s/%s.html?hd' % (video_id, seo) webpage = self._download_webpage(mrss_url, video_id) mobj = re.search(r'\'srv\': \'(?P[^\']*)\',\s*\'file\': \'(?P[^\']+)\',', webpage) @@ -36,7 +48,6 @@ class XHamsterIE(InfoExtractor): video_url = compat_urllib_parse.unquote(mobj.group('file')) else: video_url = mobj.group('server')+'/key='+mobj.group('file') - video_extension = video_url.split('.')[-1].split('?')[0] video_title = self._html_search_regex(r'(?P<title>.+?) - xHamster\.com', webpage, u'title') @@ -64,7 +75,7 @@ class XHamsterIE(InfoExtractor): return [{ 'id': video_id, 'url': video_url, - 'ext': video_extension, + 'ext': determine_ext(video_url), 'title': video_title, 'description': video_description, 'upload_date': video_upload_date,