inc/3rdparty/site_config/standard/fnal.gov.txt

   1 title: normalize(//h1)
   2
   3 author: //td/p[position()=last()]/em
   4
   5 # I swear, this is really the best way to do this
   6 date: normalize(//td[contains(@style, "color: #ffffff")])
   7
   8 # my god, it's full of tables
   9 body: /table/tbody/tr[5]//table/tbody//table/tbody/tr/td
  10 strip: //h1
  11
  12 # the following two lines strip the byline at the end of the article (the byline is a <p> that consists of an em dash and then some text in an <em>). I have no idea why I can't just strip //p[position()=last()], but trying to do so includes a bunch of other crap in the output.
  13 strip: //p[position()=last()]/em
  14 strip: //p[position()=last()]/child::text()
  15 test_url: http://www.fnal.gov/pub/today/archive_2011/today11-11-09_MuonDepartmentReadMore.html