There are many services out there which scan the web for you. For example, some notify you if your product gets mentioned in social media.
I had a similar business idea. It would involve downloading quite a few websites and analyzing their content, and I would offer that as a web app.
However, I’m concerned about the legal aspects. My idea would not violate copyright. But it could easily happen that my service accidentially downloads illegal websites that match some search terms.
Well-funded startups might have the resources to defend against that, however as a solo bootstrapper it sounds like a dangerous undertaking.
Has anyone tried something like that, or has some opinions on that issue?