inc/3rdparty/site_config/standard/blogs.smithsonianmag.com.txt

   1 # metadata
   2 author://div[@class = 'post']/div[@class='meta']/a[1]
   3 date://div[@id = 'rap']/h2[1]
   4 body://div[@class = 'post']
   5
   6 # wrapping caption and image
   7 wrap_in(fieldset)://div[contains(@class, 'wp-caption')]
   8
   9
  10 # clean up
  11 strip://div[@class = 'post']/h3[@class = 'storytitle']
  12 strip://div[@class = 'post']/div[@class = 'social']
  13 strip://img[@style = 'display:none;']
  14 strip://img[@height='0' and @width='0']
  15 test_url: http://blogs.smithsonianmag.com/adventure/2011/10/tips-for-women-traveling-in-turkey/