yt-dlc/youtube_dlc/extractor/kankan.py

49 lines
1.7 KiB
Python
Raw Normal View History

2014-01-17 03:21:22 +00:00
from __future__ import unicode_literals
import re
import hashlib
from .common import InfoExtractor
_md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
2014-01-17 03:21:22 +00:00
class KankanIE(InfoExtractor):
_VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
2014-11-23 19:41:03 +00:00
_TEST = {
2014-01-17 03:21:22 +00:00
'url': 'http://yinyue.kankan.com/vod/48/48863.shtml',
'md5': '29aca1e47ae68fc28804aca89f29507e',
'info_dict': {
2015-02-01 14:03:55 +00:00
'id': '48863',
'ext': 'flv',
2014-01-17 03:21:22 +00:00
'title': 'Ready To Go',
},
2014-01-17 03:21:54 +00:00
'skip': 'Only available from China',
}
def _real_extract(self, url):
2015-02-01 14:03:55 +00:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2014-01-17 03:21:22 +00:00
title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')
surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
2016-02-14 09:37:17 +00:00
gcids = re.findall(r'http://.+?/.+?/(.+?)/', surls)
gcid = gcids[-1]
2014-01-17 03:21:22 +00:00
info_url = 'http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid
video_info_page = self._download_webpage(
info_url, video_id, 'Downloading video url info')
ip = self._search_regex(r'ip:"(.+?)"', video_info_page, 'video url ip')
path = self._search_regex(r'path:"(.+?)"', video_info_page, 'video url path')
param1 = self._search_regex(r'param1:(\d+)', video_info_page, 'param1')
param2 = self._search_regex(r'param2:(\d+)', video_info_page, 'param2')
key = _md5('xl_mp43651' + param1 + param2)
video_url = 'http://%s%s?key=%s&key1=%s' % (ip, path, key, param2)
2014-01-17 03:21:22 +00:00
return {
'id': video_id,
'title': title,
'url': video_url,
}