title: //meta[@property="og:title"]/@content author: //meta[@name='Author']/@content date: //meta[@name='DisplayDate']/@content body: //div[@data-testid="ArticlePageChunks"] body: //div[contains(@class, 'article__chunks') or contains(@class, 'content-header__dek')] body: (//article[contains(@class, 'body-copy')])[1] body: (//article[contains(@class, 'article-body-component')])[1] body: //div[contains(concat(' ',normalize-space(@class),' '),' entry ')] strip: //p[contains(., 'Pages:') and contains(., 'View All')] strip: //p[@class='caption'] strip: //div[@class='desc' or @class='slide' or @id='slide-info'] strip: //div[contains(@class, 'RecircMostPopularWrapper')] strip_id_or_class: full-bleed-ad strip_id_or_class: layout__aside #strip_id_or_class: callout strip: //*[contains(concat(' ',normalize-space(@class),' '),' callout ')] strip_id_or_class: pullquote strip_id_or_class: left_rail strip_id_or_class: related-container strip_id_or_class: radvert-caption-wrap strip_id_or_class: related strip_id_or_class: article-tags strip_id_or_class: visually-hidden strip_id_or_class: inset-left-component strip_id_or_class: recirc-most-popular strip_id_or_class: callout--has-top-border strip_id_or_class: newsletter-subscribe-form strip_id_or_class: iframe-embed strip: //div[@id="social"] strip: //img[contains(@alt, 'capital letter')] # Trick to easily strip the bottom related stories section strip: (//hr)[last()]/following::* find_string: replace_string: # Remove gallery? strip_id_or_class: wpgallery #strip: //text()[contains(., 'nextpage')] prune: no # 2017-07-27 No longer used it seems # single_page_link: //a[.='View All' and contains(@href, '/all/')] test_url: https://www.wired.com/story/telltale-heart-fitbit-murder/ test_contains: twiddling his thumbs in her direction test_url: https://www.wired.com/2017/07/inside-cubas-diy-internet-revolution/ test_contains: I should call the hostess once I know test_url: http://www.wired.com/cloudline/2011/10/meet-arms-cortex-a15-the-future-of-the-ipad-and-possibly-the-macbook-air/ test_url: http://www.wired.com/wiredenterprise/2013/09/docker/ test_url: http://www.wired.com/threatlevel/2012/05/ff_counterfeiter/all/ test_url: http://www.wired.com/2015/11/i-turned-off-javascript-for-a-whole-week-and-it-was-glorious/