Actions a_scrape

Web Scraper

Fetches and extracts clean content from a URL (Firecrawl or basic fetch).

What does it do?

Reads and extracts text from any web page you ask it to.

How does it work?

Visits the specified URL and cleans the HTML code to keep only the readable text (articles, prices, descriptions).

Why use it?

Ideal when a customer sends you a link ("Do you have a case for this phone: www.apple.com/iphone?"). Use this node to read the link live and understand what the customer is talking about.

Inputs

name	type
`url`	string

Outputs

name	type
`url`	string
`final_url`	string
`status`	number
`content`	string
`metadata`	object
`provider`	string
`duration_ms`	number
`bytes`	number

Branches

Fixed branches

out — Output

Configuration

url string optional

url_field string required default: "url"

format "markdown" | "html" | "text" required default: "markdown"

include_metadata boolean required default: true

include_links boolean required default: false

only_main_content boolean required default: false

timeout_ms integer required default: 30000

memory_key string optional

Default configuration

{
  "url_field": "url",
  "format": "markdown",
  "include_metadata": true,
  "include_links": false,
  "only_main_content": false,
  "timeout_ms": 30000
}

Emitted events

This node does not publish events on the pubsub channel.