# This filter is tested on: # http://www.lifeweek.com.cn/2012/1211/39439.shtml # http://www.lifeweek.com.cn/2013/0308/40213.shtml title:substring-before(//h1, '(') title://h1 date://ul[@class='authorbox']/li author: substring-after(//ul[@class='authorbox']/li/following-sibling::li, '作者:') next_page_link: //div[@class='pageturn_list']/a[@class='pagedown'] body: //div[@class='original '] strip://h1 strip://ul[@class='authorbox'] strip://span[@class='app_p'] strip://div[@style='text-align:right;'] strip://div[@class='pageturn_list'] strip://div[@class='lifespeaks'] strip://div[@class='vright fr'] strip://div[@class='copyrt mg20'] strip://div[@class='keyabout mg20'] strip://ul[@class='readabout mg20'] test_url: http://www.lifeweek.com.cn/2013/0308/40213.shtml