How does instapaper and apple reader strip down articles? I mean any other tool I use like it produces no where near as beautiful results as instapaper.
I believe Instapaper uses a custom parsing engine for stripping content from pages.<p>There's a page here which lists the site specific rules Instapaper uses for extracting content:<p><a href="http://www.instapaper.com/bodytext" rel="nofollow">http://www.instapaper.com/bodytext</a><p>I think this is why you see such good results from Instapaper.
Take a look at ruby-readability: <a href="https://github.com/iterationlabs/ruby-readability" rel="nofollow">https://github.com/iterationlabs/ruby-readability</a>