R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

XHamsterIE: Fix support for new HD video url format and add test (closes PR #1443)

Browse Source
This commit is contained in:
rzhxeo 2013-09-17 06:24:20 +02:00 committed by Jaime Marquínez Ferrándiz
parent 5d13df79a5
commit 1237c9a3a5
1 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/xhamster.py
View File

@ -11,8 +11,8 @@ from ..utils import (
class XHamsterIE(InfoExtractor): class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster""" """Information Extractor for xHamster"""
_VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html' _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
_TEST = { _TESTS = [{
u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
u'file': u'1509445.flv', u'file': u'1509445.flv',
u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa', u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
@ -21,13 +21,24 @@ class XHamsterIE(InfoExtractor):
u"uploader_id": u"Ruseful2011", u"uploader_id": u"Ruseful2011",
u"title": u"FemaleAgent Shy beauty takes the bait" 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): def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
mrss_url = 'http://xhamster.com/movies/%s/.html?hd' % 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) webpage = self._download_webpage(mrss_url, video_id)
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage) mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)