Turn any webpage into markdown for LLM-friendly input
Add r.jina.ai/ in front of any URL to turn the entire page into Markdown for LLM-friendly input. Works on PDFs too. I created a bookmarklet to do this for you.
Last week I posted about a web app that turns a GitHub repo into a single text file for LLM-friendly input.
This is great for capturing LLM-friendly text from a GitHub repo, but what about any other arbitrary website or PDF? I was catching up on Simon Willison’s newsletter reading about an app he made with Claude artifacts that uses the Jina Reader API to generate Markdown from a website.
You don’t need to use the API to do this. Simply adding r.jina.ai/
in front of any URL will return LLM-friendly markdown for the website.
Demo
The examples below demonstrate using this service to get LLM-friendly plain text Markdown from a website, PDF, and a GitHub repo.
My Learning in Public post:
This also works on PDFs. This paper on arXiv, “WorkflowHub: a registry for computational workflows”:
Bookmarklet
I created a bookmarklet that will add r.jina.ai/
in front of the URL for any page you’re currently on.
javascript:(function(){window.location.href='https://r.jina.ai/' + window.location.href;})();
To use this:
Copy the code above.
Open your browser’s bookmarks manager, or on Chrome, right-click your bookmark bar and add a new page.
In the URL/location field, paste the code above and save the bookmark.
When you’re on a page, click the button and
r.jina.ai/
will be added in front of the URL.