1 date: //meta[@name='DC.date.issued']/@content
2 date: //span[@class='post-meta the-date']
4 title: //meta[@property='og:title']/@content
6 author: //meta[@name='DC.creator']/@content
8 body: //div[contains(@class, 'post-sub-head') or starts-with(@id, 'post-content-')]
10 find_string: id="content"
11 replace_string: id="content-ignore"
13 strip_id_or_class: sharedaddy
17 test_url: http://gigaom.com/2011/10/24/groupon-google-lawsuit/