1 body: //div[@id='articlebody']
3 author: //p[@id='by']//a
5 next_page_link: //span[@class='next']/a
6 # Not the same as below!
11 # Annoying 'next' links plainly inside the article body
12 strip: //*[text()[contains(.,'Next: ')]]
14 test_url: http://psychology.about.com/od/theoriesofpersonality/ss/defensemech.htm