[alextp]

Visual classification sounds interesting. So you render the page and use location-based features to extract content?

[miket]

In short, yes. The key innovation is that we've come up with a lossy, fixed-length representation of the visual features that we can use to do classification upon. I'll try to do a more detailed writeup on our blog when I find some time.

btw, our blog has no rss feed, but you can just use our RSS API :-) http://www.diffbot.com/api/rss/http:/www.diffbot.com/blog