title: //div[contains(@class, 'articleHead')]//h1 body: //div[@itemprop='articleBody'] body: //div[@class='articleText'] body: //div[@class='articleContent'] body: //div[@id='article'] date: //*[contains(@class, 'date')] author: //div[@id='profile']//*[@class='authors']//a[1] author: //*[@class='author']/span prune: no strip: //div[@class='moreOnBoxWithImages'] strip: //p[contains(., 'This article available online at:')] strip: //p[contains(., 'This article available online at:')]/following::* strip: //div[@class='earthbox'] single_page_link: //div[contains(@class, 'article-tools')]//a[contains(@class, 'print')] native_ad_clue: //meta[@property="og:url" and contains(@content, '/sponsored/')] #multi-page article test_url: http://www.theatlantic.com/magazine/archive/2014/12/the-real-roots-of-midlife-crisis/382235/ test_contains: The curve tends to evince itself test_url: http://www.theatlantic.com/technology/archive/2011/04/want-to-see-how-crazy-a-bot-run-market-can-be/237773/ test_url: http://www.theatlantic.com/magazine/archive/2007/11/the-autumn-of-the-multitaskers/6342/ test_url: http://www.theatlantic.com/entertainment/archive/2012/04/30-rock-live-a-funny-reminder-of-why-sitcoms-arent-shot-live-anymore/256447/