1 title: substring-before(//title,'| /Film')
2 date: substring-before(substring-after(//p[@class='post-info'],'Posted on '),'by')
3 strip: //div[@class='pm-left']
4 strip: //div[@class='pm-right']
6 next_page_link: //h2/strong/a
8 strip: //p[contains(text(),'we have to split this post over')]
9 strip: //p[@class='post-info']
11 strip: //img[contains(@src,'siteimages/authors')]
12 strip: //div[@id='header']
13 strip: //div[@class='topad-right']
14 strip: //strong[contains(text(),'Cool Posts From Around the Web:')]
15 test_url: http://www.slashfilm.com/superhero-bits-206/