# get past the cookie wall http_header(cookie): pws=functional|analytics|content_recommendation|targeted_advertising|social_media; pwv=1 # grab the author and date author: //a[@class='artstyle__byline__author'] date: //time[@class='artstyle__byline__datetime'] # grab article body body: //article[@class='artstyle fu--type-default artstyle--type-default'] # strip category header strip: //h4[@class='artstyle__labels'] # strip author, date and timestamp metadata strip: //section[@data-element-id='article-element-authors'] # strip the "Lees ook" part at the bottom strip: //aside[@class='artstyle__editorial-tips'] test_url: https://www.demorgen.be/nieuws/helft-belgische-moslims-is-fundamentalist~b2344ae6/ test_contains: Helft Belgische moslims is fundamentalist