1 date: //meta[@name='dcterms.created']/@content
2 title: //meta[@property='og:title']/@content
3 author: //section[@class="post-meta"]//a[@rel="author"]
5 body: //div[starts-with(@id, 'post-content-')]
7 strip_id_or_class: sharedaddy
11 test_url: http://gigaom.com/2011/10/24/groupon-google-lawsuit/
12 test_url: http://gigaom.com/2012/12/26/snapchat-rises-why-pokes-decline-shows-facebooks-inability-to-invent/