body: //article[contains(concat(' ',normalize-space(@class),' '),' content-container__single ')] body: //article[contains(concat(' ',normalize-space(@class),' '),' content-container ')] strip: //aside strip: //header strip: //footer strip: //div[contains(concat(' ',normalize-space(@class),' '),' notice-header ')] # HTML5-PHP parsing issue? parser: libxml prune: no test_url: https://www.cityam.com/uk-to-reveal-social-media-ban-plans-for-under-16s-within-weeks/