1 2 3 4 5
title: //div[contains(@class, 'headline')]/h1 author: //h5[contains(@class, 'byline')] date: substring-after(//h4[contains(@class, 'posted')], 'Posted: ') body: //div[@id="storyboard"] test_url: http://www.cbc.ca/news/world/story/2012/01/16/cruise-ship-monday.html