Add an extractor for kankan.com (closes #1133)

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-07-29 23:13:12 +02:00
parent caeefc29eb
commit 8cda9241d1
2 changed files with 38 additions and 0 deletions

View file

@ -38,6 +38,7 @@ from .infoq import InfoQIE
from .instagram import InstagramIE from .instagram import InstagramIE
from .jukebox import JukeboxIE from .jukebox import JukeboxIE
from .justintv import JustinTVIE from .justintv import JustinTVIE
from .kankan import KankanIE
from .keek import KeekIE from .keek import KeekIE
from .liveleak import LiveLeakIE from .liveleak import LiveLeakIE
from .livestream import LivestreamIE from .livestream import LivestreamIE

View file

@ -0,0 +1,37 @@
import re
from .common import InfoExtractor
from ..utils import determine_ext
class KankanIE(InfoExtractor):
_VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
_TEST = {
u'url': u'http://yinyue.kankan.com/vod/48/48863.shtml',
u'file': u'48863.flv',
u'md5': u'29aca1e47ae68fc28804aca89f29507e',
u'info_dict': {
u'title': u'Ready To Go',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._search_regex(r'G_TITLE=[\'"](.+?)[\'"]', webpage, u'video title')
gcid = self._search_regex(r'lurl:[\'"]http://.+?/.+?/(.+?)/', webpage, u'gcid')
video_info_page = self._download_webpage('http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid,
video_id, u'Downloading video url info')
ip = self._search_regex(r'ip:"(.+?)"', video_info_page, u'video url ip')
path = self._search_regex(r'path:"(.+?)"', video_info_page, u'video url path')
video_url = 'http://%s%s' % (ip, path)
return {'id': video_id,
'title': title,
'url': video_url,
'ext': determine_ext(video_url),
}