Thank you! This is exactly what I want to do with this. I have embeddings for all the images but hadn’t figured out the last step to getting them onto a grid like that. Can’t wait to try this.
I’m one of the makers of this - thank you for posting!
We built it in early 2024 and it’s due an update.
While the main visualisation is currently out of date we’ve been grabbing screenshots monthly for the last 18 months. There’s a a free (no key required) API to all the data at https://ScreenshotOf.com
I’d love to hear any ideas you have for improving it.
That’s right. On our standard self-service plans we automatically charge a better rate as volume increases. You only pay the difference between tiers as you move through them.
It’s rare that anyone makes that kind of mistake. It probably helps that our rate limits are relatively low compared to other APIs and we email you when you get close to stepping up a tier. If you did make such a mistake we would, like all good dev tools, work with you to resolve. If it happened a lot we might introduce some additional controls.
We’ve been in this business for over 12 years and currently have over 700 customers so we’re fairly confident we have the balance right.
In my experience our customers are more worried about having the service stop when they hit the limit of a tier than they are about being charged a few more dollars.
If you’re worried about the security risks, edge cases, maintenance pain and scaling challenges of self hosting there are various solid hosted alternatives:
I had so much fun with this with my 7 year old. Was super easy to take their art and make games with it. You can start by editing one of the many example games it comes with.
We might be able to help you get the content from URLs like these in one step. We have quite a bit of power in the Urlbox API that url2text isn't using.
Sorry the pricing isn't a good fit for you. Urlbox has been running for over 11 years. We're bootstrapped and profitable with a team of 3 (plus a few contractors). We're priced to be sustainable so our customers can depend on us in the long term. We automatically give volume discounts as your usage grows.
Great idea to offer image downloads and filtering with GPT!
I built a similar tool last year that doesn't have those features:
https://url2text.com/
Apologies if the UI is slow - you can see some example output on the homepage.
The API it's built on is Urlbox's website screenshot API which performs far better when used directly. You can request markdown along with JS rendered HTML, metadata and screenshot all in one go:
https://urlbox.com/extracting-text
You can even have it all saved directly to your S3-compatible storage:
https://urlbox.com/s3
I've been running over 1 million renders per month using Urlbox's markdown feature for a side project. It's so much better using markdown like this for embeddings and in prompts.
If you want to scrape whole websites like this you might also want to checkout this new tool by dctanner:
https://usescraper.com/
Here’s another Christmassy alternative: https://display.archive.org/xmas
I’m one of the makers of OneMillionScreenshots.com and I’m currently working on an update to it.