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'
                }