tidy: no body: //div[@class='main'] author: substring-before(substring-after(//div[@class='meta-single'], 'erstellt von '), ' am') date: substring-before(substring-after(//div[@class='meta-single'], ' am '), ' | ') strip_id_or_class: pagelink strip_id_or_class: wp-polls next_page_link: //div[@class='post-page-next']/a test_url: http://www.designtagebuch.de/die-gefuehlte-lesbarkeit/