title: //meta[@property="og:title"]/@content date: //meta[@property="article:published_time"]/@content date: //header[@id="article_header"]//div[@class="pub-date"] body: //div[@itemprop="mainEntityOfPage"] body: //article//section[contains(@class, 'content')] strip: //aside[contains(@class, 'in-article-recirc')] #strip: //dl #strip: //p[em/a[contains(@href, 'facebook.com')]] prune: no # Use img in