Web Extract Tool
Extracts structured data from web pages using Firecrawl AI-powered extraction with custom prompts and schemas
Quick Start
import { WebExtractTool } from '@bubblelab/bubble-core';
import { CredentialType } from '@bubblelab/shared-schemas';
const result = await new WebExtractTool({
url: 'example', // The URL to extract structured data from
prompt: 'example', // Detailed prompt describing what data to extract from the web page
schema: 'example', // JSON schema string defining the structure of the data to extract
credentials: {
[CredentialType.FIRECRAWL_API_KEY]: process.env.FIRECRAWL_API_KEY as string,
},
}).action();
Operation Details
execute
- Input Schema
- Output Schema
urlstring required- The URL to extract structured data from
promptstring required- Detailed prompt describing what data to extract from the web page
schemastring required- JSON schema string defining the structure of the data to extract
timeoutnumber- Timeout in milliseconds for the extraction (default: 30000)
credentialsRecord<CredentialType,string>- Required credentials including FIRECRAWL_API_KEY
urlstring required- The original URL that was processed
successboolean required- Whether the extraction was successful
errorstring required- Error message if extraction failed
extractedDataunknown required- The extracted structured data matching the provided schema
metadataobject- Additional metadata about the extraction