Data Extraction with BrowseFleet

import { BrowseFleet } from 'browsefleet';
import Anthropic from '@anthropic-ai/sdk';

const bf = new BrowseFleet({ apiKey: 'bf_...' });
const anthropic = new Anthropic();

// Simple extraction via quick action
const { markdown } = await bf.scrape(
  'https://company.example.com/about'
);

// Use LLM to extract structured data from markdown
const response = await anthropic.messages.create({
  model: 'claude-sonnet-4-20250514',
  messages: [{
    role: 'user',
    content: `Extract structured data from this page:

${markdown}

Return JSON with: company_name, founded_year,
employee_count, headquarters, description`,
  }],
});

const companyData = JSON.parse(
  response.content[0].text
);

// Complex extraction with session for paginated data
const session = await bf.sessions.create({ stealth: 'full' });
const browser = await puppeteer.connect({
  browserWSEndpoint: session.websocketUrl,
});

const page = await browser.newPage();
let allResults = [];

await page.goto('https://data.example.com/results');
while (true) {
  const pageData = await page.evaluate(() => /* extract */);
  allResults.push(...pageData);

  const nextBtn = await page.$('.next-page:not([disabled])');
  if (!nextBtn) break;
  await nextBtn.click();
  await page.waitForNavigation();
}

await session.close();