4abf2778f4
It now requires two additional parameters, one is a timestamp we get from the getCdnresource_flv page and the other is a key, it seems to only work for a specific User-Agent. It seems to be valid for different videos.
41 lines
1.6 KiB
Python
41 lines
1.6 KiB
Python
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=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, u'video title')
|
|
surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
|
|
gcids = re.findall(r"http://.+?/.+?/(.+?)/", surls)
|
|
gcid = gcids[-1]
|
|
|
|
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?key=fb2dcb4b14401eae04986d42011ae4d4&key1=1383767293' % (ip, path)
|
|
|
|
return {'id': video_id,
|
|
'title': title,
|
|
'url': video_url,
|
|
'ext': determine_ext(video_url),
|
|
'user_agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36'
|
|
}
|