inc/3rdparty/site_config/standard/newsmill.se.txt

   1 title: //h1
   2 body: (//div[@class='articleImg']//img)[1] | //p[contains(@class, 'commentTextArticle') or contains(@class, 'articlePublished')] | //div[@id='articleLeftContent']
   3 author: //div[@class='byline']//a[contains(@href, '/user/')]
   4
   5 strip_id_or_class: facts
   6 strip_id_or_class: articleBlogsHolder
   7 strip_id_or_class: byline
   8
   9 prune: no
  10 tidy: no
  11
  12 test_url: http://www.newsmill.se/artikel/2012/05/06/medielogiken-v-ger-tyngre-n-reportrarnas-sikter