title: //meta[@property="og:title"]/@content body: //div[img[starts-with(@id, 'img_caption')]] | //div[@class="big_photo"] | //div[contains(@class, 'entry_body_text')] date: //meta[@name="publish_date"]/@content author: //a[@rel="author"] author: //meta[@name="author"]/@content prune: no tidy: no strip: //footer strip_id_or_class: ps-slideshow strip_id_or_class: fs-slideshow strip: //p[contains(., 'Related on HuffPost:')] # end early replace_string(