I've experimented with https://github.com/gfxmonk/python-readability but it's extremely slow. There's a decent fork called decruft that is a couple orders of magnitude faster http://www.minvolai.com/blog/decruft-arc90s-readability-in-p...

Decruft also has a couple bug fixes to python-readability. They both need a lot of work, though. You'll have to do some spelunking to figure out how to actually call the libraries correctly.