Scrape Element

Fetch a public page and extract elements by CSS selector.

What it does

Fetches one part of a page, chosen by CSS selector. Use it when the page is noisy and you want the price, the status line, or the table — not the navigation and the footer.

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 Element, and fill in:

Field	Required	What goes in it
`url`	yes	A public page.
`css_selector`	yes	What to pull out — `.price`, `#status`, `table.results tr`. Copy it from the browser's inspector.

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 Element 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 logistics firm checks a carrier's tracking page and pulls only the status cell, so the agent reads In transit rather than four hundred words of page furniture.

When it goes wrong

It returns nothing. The selector no longer matches — sites change their markup without warning. Open the page, inspect the element, and copy the selector again.