1 title: //meta[@property='og:title']/@content
2 body: //img[contains(@class, 'FirstImage')] | //div[contains(@class, 'articleContent')]
3 date: //meta[@property='article:published_time']/@content
4 author: //div[@id='main']//div[@class='byline']//span[@class='authorName']
6 strip_id_or_class: RelatedArtTag
8 strip: //h5[contains(., 'READ MORE:')]
9 strip: //h5[contains(., 'Read more:')]
12 test_url: http://www.independent.co.uk/news/world/middle-east/syria-could-face-human-rights-probe-2274326.html
13 test_url: http://www.independent.co.uk/voices/comment/robert-fisk-on-the-cia-torture-report-once-again-language-is-distorted-in-order-to-hide-us-state-wrongdoing-9924501.html
14 test_contains: Thank God for Noam Chomsky.
16 test_url: http://www.independent.co.uk/news/uk/rss