inc/3rdparty/site_config/standard/lemonde.fr.txt

   1 title: //h1
   2
   3 # they have a single component containing both author and date
   4 #author: //p[@class='source']
   5 #date: //p[@class='source']
   6
   7 body: //div[@class='contenu_article']
   8 #Shoot the insane "conjugaison.lemonde.fr" links :
   9 strip: //a[contains(@class, 'listLink')]
  10
  11 prune: no
  12
  13 test_url: http://www.lemonde.fr/economie/article/2011/07/05/moody-s-abaisse-la-note-du-portugal-de-quatre-crans_1545237_3234.html