1 title: //div[@id='pr']/h3
2 author: //div[@class='dateline']//a[contains(@href, '/author/')]
5 body: //div[@id='prbody']
7 body: //div[@id='pgbody']
9 # for multi-page articles
10 single_page_link: //div[@class='tipjar']//a[contains(@href, '/printerFriendly.php?')]
14 test_url: http://www.walrusmagazine.com/articles/2011.12-memoir-kidnapped