Just download information about the primary article content on the submitted page:

 import Diffbot

 main = do
     let token = "11111111111111111111111111111111"
         url   = "http://blog.diffbot.com/diffbots-new-product-api-teaches-robots-to-shop-online/"
     resp <- diffbot token url defaultArticle
     print resp

You can control which fields are returned:

 main = do
     let token  = "11111111111111111111111111111111"
         url    = "http://blog.diffbot.com/diffbots-new-product-api-teaches-robots-to-shop-online/"
         fields = Just "meta,querystring,images(*)"
     resp <- diffbot token url $ setFields fields defaultArticle
     print resp

If your content is not publicly available (e.g., behind a firewall), you can POST markup for analysis directly:

 {-# LANGUAGE OverloadedStrings #-}
 import Diffbot

 main = do
     let token   = "11111111111111111111111111111111"
         url     = "http://www.diffbot.com/our-apis/article"
         content = Content TextPlain "Now is the time for all good robots to come to the aid of their -- oh never mind, run!"
     -- Please note that the 'url' is still required, and will be used
     -- to resolve any relative links contained in the markup.
     resp <- diffbot token url $ setContent (Just content) defaultArticle
     print resp