inc/3rdparty/site_config/standard/salon.com.txt

   1 title: //meta[@property='og:title']/@content
   2 author: (//span[@class="byline"]/a)[1]
   3 date: //span[contains(@class, "toLocalTime")]
   4 body: (//div[contains(@class, "articleInner")]//img[contains(@src, 'media.salon.com') and contains(@src, '460x')])[1] | //div[contains(@class, "articleContent") or contains(@class, "writerMeta")]
   5
   6 prune: no
   7
   8 # deal with singleton links
   9 single_page_link: (//h1/a[contains(@href, '/singleton')])[1]
  10
  11 test_url: http://www.salon.com/2011/10/25/occupying_the_rust_belt/singleton/