author: //article//a[@itemprop="author"]
date: //article//time[@itemprop="datePublished"]/@content
body: //div[contains(@class, 'article-body-wrap')]

# pull quotes
strip: //aside

test_url: https://newrepublic.com/article/120178/problem-international-development-and-plan-fix-it
test_contains: It seemed like such a good idea at the time
test_url: http://www.newrepublic.com/article/112731/moocs-will-online-education-ruin-university-experience