author: substring-after(//div[@class='byline'], " by ") date: substring-before(//div[@class='byline'], " by ") # set body body: //div[@class='content'] # set title title: //h3 #strip: //div[@class='content']/h3 test_url: http://www.macrumors.com/2010/11/10/apple-debuts-new-apple-tv-and-itunes-movie-content-in-japan/