inc/3rdparty/site_config/standard/articles.courant.com.txt

   1 title: //div[@class="mod-courantarticleheader mod-articleheader"]/h1
   2 date: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[@class="pubdate"]
   3 author: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[3]
   4
   5 strip_id_or_class: mod-article-byline
   6 strip_id_or_class: mod-article-header
   7 strip_id_or_class: mod-article-subtitle
   8 #This leaves some crud after the article, but it's better than nothing.
   9 #It would be ideal if we could set the body to every element matching //div[contains(@class, "mod-articletext")]/p, but it seems like body only takes the first matching element.
  10
  11 test_url: http://articles.courant.com/2011-10-22/news/hc-green-drugsearch--1022-20111022_1_drugs-in-student-lockers-police-dogs-lockdown