Extract Data

Component Details

v1.0.0

Basic Information

appmixer.firecrawl.core.ExtractData

Extract Data

1.0.0

Public

Extract structured data from one or more URLs using an LLM prompt and/or a JSON schema. By default the component waits for the extraction to finish and returns the extracted data; turn off waiting to only get the job ID and fetch results later with Get Extract Status.

Input Ports

in

FieldTypeDescription
URLs textarea One or more URLs to extract data from, separated by commas or new lines. Append /* to a URL to extract from the whole site, e.g. https://example.com/*.
Prompt textarea Natural language description of the data to extract, e.g. Extract the product name, price and availability. Provide a prompt, a JSON schema, or both.
JSON Schema textarea Optional JSON Schema describing the structure of the extracted data, e.g. {"type":"object","properties":{"price":{"type":"number"}}}. Provide a prompt, a JSON schema, or both.
Enable Web Search toggle Allow the extraction to follow links outside the provided URLs to gather additional data.
Wait For Completion toggle Wait for the extraction to finish and return the extracted data. When off, the component returns the job ID immediately; use Get Extract Status to fetch the result later.
Polling Timeout (seconds) number How long to wait for the extraction to finish before giving up. Defaults to 600 seconds (10 minutes). Only applies when waiting for completion.

Output Ports

out

FieldTypeDescription
Job ID string -
Status string -
Extracted Data object -
Tokens Used number -

Full Metadata