inc/3rdparty/site_config/standard/brookings.edu.txt

   1 title: //div[@id='contentheader']/h1
   2 author: //p[@class='attribution']/span[@class='author']/*
   3 # Is there a way to pull multiple authors? My XPath here is just grabbing the first
   4
   5 date: /html/head/meta[@name="date"]/@content
   6 body: //div[@class='main-content']
   7
   8 strip: //p[@class='byline']
   9 strip: //div[@class='img-gallery']
  10 strip: //div[@class='callout']
  11 strip: //div[@class='add-your-view']
  12 convert_double_br_tags: yes
  13 test_url: http://www.brookings.edu/opinions/2011/1018_cyberattack_libya_goldsmith.aspx