Skip to Content

Extract

Perform advanced AI scraping to extract data from any website. Search on all subdomains and combine your scrape with web search.

Billable OperationProviderBilling Mode
Docs
Connection
Docs
Cost per operation
Docs
firecrawl-website-extract
P
Firecrawl
On Success
Managed, User

2.00 credits

Input Fields

string
website_url

Output Fields

json
firecrawl_extract_result
  Enabled by default

const options = {
  method: 'POST',
  headers: {'content-type': 'application/json', authorization: 'Bearer <TOKEN>'},
  body: JSON.stringify({
    config: {environment: 'production'},
    pipes: [
      {
        pipe_id: 'website:extract:firecrawl@1',
        config: {
          extraction_prompt: 'Extract the company mission as well as the latest news.',
          enable_full_domain_crawl: true,
          enable_web_search: true,
          json_schema: {
            type: 'object',
            required: ['company_mission', 'latest_news'],
            properties: {company_mission: {type: 'string'}, latest_news: {type: 'string'}}
          }
        }
      }
    ],
    input: [{id: '1', company_website_url: 'Pipe0'}]
  })
};

fetch('https://api.pipe0.com/v1/pipes/run', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));