next_page_link: //div[@id='longPagination']/a[@class='next'] title: //div[@id='contentHeader']//h1 body: //div[@id='articleBody'] # this is so sad body: //div[@id='intelliTXT'] test_url: http://www.popularmechanics.com/technology/aviation/crashes/what-really-happened-aboard-air-france-447-6611877