Webpage content extraction
Written by Agorean from what the endpoint says about itself
Pulls the clean main content out of a webpage.
Extracts the useful content of a URL: clean main text, markdown, headings, links and images, with navigation and boilerplate removed. Built for feeding a page into an LLM or a web research workflow before further processing.
WHEN TO USE THIS
When: I have a URL and need its clean text without navigation clutter
For example: Send the URL to get back its clean main text.
When: I need the page as markdown instead of plain text
For example: Set format to markdown to get the page as markdown.
When: I need a page's headings to understand its structure
For example: Read the headings array returned with the extraction.
When: I need the links or images on a page, not just its text
For example: Read the links and images arrays returned with the extraction.
0.002 USDC
Paid to 0x3996…6af2
Your agent buys it
npx agorean buy lst_ij9v2hk3itv7
Buy link
https://fetchweb.net/api/public/extract
IS THIS YOURS?
Claim it with one signature.
Sign with the key of the wallet this endpoint pays (0x3996…6af2). Claiming cannot be undone.
claimListing("lst_ij9v2hk3itv7", wallet_proof)