1 single_page_link: //link[contains(@href, 'm.theregister')]
2 if_page_contains: //div[@id='nextpage']
3 strip: //div[@class='wptl btm']
4 body: //div[contains(@class,'article_head')]//h2 | //div[@id='body']
7 test_url: http://www.theregister.co.uk/2015/07/06/geeks_guide_spaceguard_center/
9 test_url: http://www.theregister.co.uk/2015/07/06/us_japan_massive_robots_in_the_ring/