diff --git a/youtube_dl/extractor/kankan.py b/youtube_dl/extractor/kankan.py index 50916f4a66..2707462ee0 100644 --- a/youtube_dl/extractor/kankan.py +++ b/youtube_dl/extractor/kankan.py @@ -1,20 +1,22 @@ +from __future__ import unicode_literals + import re import hashlib from .common import InfoExtractor -from ..utils import determine_ext _md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() + class KankanIE(InfoExtractor): _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P\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', + 'url': 'http://yinyue.kankan.com/vod/48/48863.shtml', + 'file': '48863.flv', + 'md5': '29aca1e47ae68fc28804aca89f29507e', + 'info_dict': { + 'title': 'Ready To Go', }, } @@ -23,22 +25,23 @@ def _real_extract(self, 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') + title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, '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') - param1 = self._search_regex(r'param1:(\d+)', video_info_page, u'param1') - param2 = self._search_regex(r'param2:(\d+)', video_info_page, u'param2') + 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) - return {'id': video_id, - 'title': title, - 'url': video_url, - 'ext': determine_ext(video_url), - } + return { + 'id': video_id, + 'title': title, + 'url': video_url, + }