title: //*[@id='Content']/span[1] author: substring-after(substring-before(//*[@id='Content']/span[2], ')'), '(') date: substring-before(substring-after(//*[@id='Content']/span[2], 'Updated: '), 'Counter') strip: //*[@id='Content']/span[1] strip: //*[@id='Content']/span[2] body: //*[@id='Content'] test_url: http://www.chinamining.org/News/2011-07-22/1311319069d48087.html