date: //meta[@name='DC.date.issued']/@content date: //span[@class='post-meta the-date'] title: //meta[@property='og:title']/@content author: //meta[@name='DC.creator']/@content body: //div[contains(@class, 'post-sub-head') or starts-with(@id, 'post-content-')] find_string: id="content" replace_string: id="content-ignore" strip_id_or_class: sharedaddy prune: no test_url: http://gigaom.com/2011/10/24/groupon-google-lawsuit/