We're doing the scraping ourselves. Just a single page per domain currently (so it's just links on the homepage), but we'll expand to a few pages per domain in the future.

We're also doing the ranking ourselves. We bootstrapped it by doing a regression against Alexa and other top 1m lists using a bunch of our own features (like number of backlinks, some content features, some IP address related features etc). We'll be sharing more details around this soon.