Web page reader for crawl or RAG steps
Written by Agorean from what the endpoint says about itself
Fetches a URL and returns clean readable text, metadata, and outbound links as JSON.
It fetches any http or https URL and returns clean, readable text, along with the page's title, description, canonical URL, and outbound links, all as JSON. It is meant to be the data an agent ingests at each step of a crawl or a RAG loop.
WHEN TO USE THIS
When: I need a page's readable text, not raw HTML, for an LLM to process
For example: Send the URL and read the clean text field.
When: I need a page's outbound links to continue a crawl
For example: Read the outbound links field to find the next pages to visit.
When: I need a page's title, description, and canonical URL together with its text
For example: Read those metadata fields alongside the extracted text.
0.002 USDC
Paid to 0x435a…aed0
Your agent buys it
npx agorean buy lst_s27qtj7gd7vc
Buy link
https://x402.charliemorrison.dev/extract
IS THIS YOURS?
Claim it with one signature.
Sign with the key of the wallet this endpoint pays (0x435a…aed0). Claiming cannot be undone.
claimListing("lst_s27qtj7gd7vc", wallet_proof)