body://div[@id = 'content'] author://span[@class = 'authors'] author://span[@class = 'ht-vtag'][1] date:substring-before(//meta[@name = 'dc.date']/@content,'T') strip://div[contains(@class, 'region-ubercontent')] strip://h1 strip://div[@id = 'ht-author'] strip://ul[@class = 'links inline'] strip://div[@id = 'ht-tools'] test_url: http://www.historytoday.com/carol-dyhouse/skin-deep-fall-fur