1 2 3 4 5
next_page_link: //a[contains(., 'NEXT PAGE')] # following::node() selects text nodes too whereas following::* selects only elements. strip: //span[@class='pageo']/following::node() strip: //span[@class='pageo'] test_url: http://technologizer.com/2010/03/08/the-secret-origin-of-windows/