1 title: //div[@class='printbody']/h1
2 body: //div[@class='printbody']
5 strip: //div[@class='printbody']/a[@href='http://www.truthdig.com/']
6 strip: //table[@class='footer']
7 strip: //h6[contains(., 'http://')]
9 single_page_link: //a[contains(@href, '/print/')]
11 test_url: http://www.truthdig.com/report/item/the_election_march_of_the_trolls_20110829/
12 test_url: http://www.truthdig.com/dig/item/the_death_of_truth_20130505/