Scrape Website

Fetch a public web page and return its readable text.

What it does

Fetches a public page and returns its readable text. No key, no cost, no account. When a job needs to know what a page says right now, start here before reaching for anything paid.

What you need

Nothing. This one runs on RAiN — no key, no account, no per-use cost from the provider.

Connecting it

Nothing to connect. It is available to every project already — tick it on an agent, or choose it in an Action step.

Using it in a step

An Action step runs one tool with the arguments you type, exactly as written, with no model involved — so it costs nothing per run and behaves the same every time. Add one from the canvas toolbar, choose Scrape Website, and fill in:

Field	Required	What goes in it
`url`	yes	A public page. Returns its readable text, without the furniture.

Values can carry results forward: {{previous}} is the step before, and {{row:column}} is a column from the row this run is about when the trigger fans out.

Press Try it to run the step on its own before committing to a whole sequence.

Using it with an agent

Tick Scrape Website on any agent that should be able to call it, and the agent decides when to. Use an agent when the judgement matters and an Action step when the certainty does.

A worked example

A distributor watches a supplier's price list page every morning. The text is compared with yesterday's, and only a change sends an email.

When it goes wrong

HTTP 403 or a page of nothing. Some sites refuse anything that is not a browser. That is when Firecrawl Scrape earns its key — it renders the page properly.

It refuses a private address. Same rule as everywhere: public hosts only.