1 title: //*[@class="article"]/h1
2 date: //*[@class="article"]/div[@class="date"]
4 # strip the title and date from the article text
5 strip: //*[@class="article"]/h1
6 strip: //*[@class="article"]/div[@class="date"]
8 # strip annoying <br> between metadata and article
9 strip: //*[@class="article"]/div[@class="date"]/following-sibling::br
10 test_url: http://minnesota.publicradio.org/display/web/2012/06/19/health/senators-want-health-care-ruling-on-tv/