title: //div[@id='main-article-info']//h1
body: //div[@id='article-wrapper']
date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate]
strip: //div[contains(@class, 'email-subscription')]
author: //li[@class='byline']
prune: no
tidy: no
test_url: http://www.guardian.co.uk/business/2011/oct/06/quantitative-easing-75bn-bank-of-england
test_url: http://www.guardian.co.uk/world/2013/jul/10/nsa-duckduckgo-gabriel-weinberg-prism