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

   1 title: //h1
   2
   3 # We can have multiple authors
   4 author: //a[@class='auteur']
   5
   6 # Last edition date (if any)
   7 date: //time[@itemprop='dateModified']/@datetime
   8 # Publication date
   9 date: //time[@itemprop='datePublished']/@datetime
  10
  11
  12 body: //div[@id='articleBody']
  13 #Shoot the insane "conjugaison.lemonde.fr" links :
  14 #strip: //a[contains(@class, 'conjug')]
  15
  16 prune: no
  17
  18 test_url: http://www.lemonde.fr/economie/article/2011/07/05/moody-s-abaisse-la-note-du-portugal-de-quatre-crans_1545237_3234.html