body: //div[@id='content-content']//div[@class='content'] title: //h1[@class='title'] date: substring-after(//*[@class='submitted'],'Submitted on') tidy: no strip: //div[@class='terms terms-inline'] strip: //div[@class='more'] strip: //div[@class='share-links'] strip: //table[@id='attachments'] test_url: http://www.laquadrature.net/en/finalization-of-eu-parliaments-weak-net-neutrality-resolution