{
  "name": "browser-worker",
  "main": "src/index.ts",
  "compatibility_date": "2023-03-14",
  "compatibility_flags": ["nodejs_compat"],
  "browser": {
    "binding": "MYBROWSER"
  }
}

npm install @cloudflare/puppeteer

import puppeteer from "@cloudflare/puppeteer";

interface Env {
  MYBROWSER: Fetcher;
}

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const { searchParams } = new URL(request.url);
    const url = searchParams.get("url") || "https://example.com";

    // Launch browser
    const browser = await puppeteer.launch(env.MYBROWSER);
    const page = await browser.newPage();

    // Navigate and capture
    await page.goto(url);
    const screenshot = await page.screenshot();

    // Clean up
    await browser.close();

    return new Response(screenshot, {
      headers: { "content-type": "image/png" }
    });
  }
};

npx wrangler deploy

// Must pass binding
const browser = await puppeteer.launch(env.MYBROWSER); // ✅
// const browser = await puppeteer.launch(); // ❌ Error!

// Session reuse for performance
const sessions = await puppeteer.sessions(env.MYBROWSER);
const freeSessions = sessions.filter(s => !s.connectionId);
if (freeSessions.length > 0) {
  browser = await puppeteer.connect(env.MYBROWSER, freeSessions[0].sessionId);
}

// Keep session alive
await browser.disconnect(); // Don't close

// XPath workaround (not directly supported)
const data = await page.evaluate(() => {
  return new XPathEvaluator()
    .createExpression("/html/body/div/h1")
    .evaluate(document, XPathResult.FIRST_ORDERED_NODE_TYPE)
    .singleNodeValue.innerHTML;
});

npm install @cloudflare/playwright

{
  "compatibility_flags": ["nodejs_compat"],
  "compatibility_date": "2025-09-15"  // Required for Playwright v1.55
}

import { chromium } from "@cloudflare/playwright";

const browser = await chromium.launch(env.BROWSER);
const page = await browser.newPage();
await page.goto("https://example.com");
const screenshot = await page.screenshot();
await browser.close();

async function getBrowser(env: Env): Promise<Browser> {
  const sessions = await puppeteer.sessions(env.MYBROWSER);
  const freeSessions = sessions.filter(s => !s.connectionId);

  if (freeSessions.length > 0) {
    try {
      return await puppeteer.connect(env.MYBROWSER, freeSessions[0].sessionId);
    } catch (e) {
      console.log("Failed to connect, launching new browser");
    }
  }

  return await puppeteer.launch(env.MYBROWSER);
}

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const browser = await getBrowser(env);

    try {
      const page = await browser.newPage();
      await page.goto("https://example.com");
      const screenshot = await page.screenshot();

      await browser.disconnect(); // ✅ Keep alive for reuse

      return new Response(screenshot, {
        headers: { "content-type": "image/png" }
      });
    } catch (error) {
      await browser.close(); // ❌ Close on error
      throw error;
    }
  }
};

const browser = await puppeteer.launch(env.MYBROWSER);
const context1 = await browser.createBrowserContext(); // User 1
const context2 = await browser.createBrowserContext(); // User 2

const page1 = await context1.newPage();
const page2 = await context2.newPage();
// Separate cookies/cache per context

const browser = await puppeteer.launch(env.MYBROWSER);
const results = await Promise.all(
  urls.map(async (url) => {
    const page = await browser.newPage();
    await page.goto(url);
    const data = await page.evaluate(() => ({ title: document.title }));
    await page.close();
    return { url, data };
  })
);
await browser.close();

interface Env {
  MYBROWSER: Fetcher;
  CACHE: KVNamespace;
}

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const { searchParams } = new URL(request.url);
    const url = searchParams.get("url");
    if (!url) return new Response("Missing ?url parameter", { status: 400 });

    const normalizedUrl = new URL(url).toString();

    // Check cache first
    let screenshot = await env.CACHE.get(normalizedUrl, { type: "arrayBuffer" });

    if (!screenshot) {
      const browser = await puppeteer.launch(env.MYBROWSER);
      const page = await browser.newPage();
      await page.goto(normalizedUrl);
      screenshot = await page.screenshot();
      await browser.close();

      // Cache for 24 hours
      await env.CACHE.put(normalizedUrl, screenshot, { expirationTtl: 60 * 60 * 24 });
    }

    return new Response(screenshot, { headers: { "content-type": "image/png" } });
  }
};

interface Env {
  MYBROWSER: Fetcher;
  AI: Ai;
}

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const { searchParams } = new URL(request.url);
    const url = searchParams.get("url");

    // Scrape page content
    const browser = await puppeteer.launch(env.MYBROWSER);
    const page = await browser.newPage();
    await page.goto(url!, { waitUntil: "networkidle0" });
    const bodyContent = await page.$eval("body", el => el.innerHTML);
    await browser.close();

    // Extract structured data with AI
    const response = await env.AI.run("@cf/meta/llama-3.1-8b-instruct", {
      messages: [{
        role: "user",
        content: `Extract product info as JSON from this HTML. Include: name, price, description.\n\nHTML:\n${bodyContent.slice(0, 4000)}`
      }]
    });

    return Response.json({ url, product: JSON.parse(response.response) });
  }
};

const limits = await puppeteer.limits(env.MYBROWSER);
if (limits.allowedBrowserAcquisitions === 0) {
  const delay = limits.timeUntilNextAllowedBrowserAcquisition || 1000;
  await new Promise(resolve => setTimeout(resolve, delay));
}

// ❌ Don't use XPath directly (not supported)
// await page.$x('/html/body/div/h1')

// ✅ Use CSS selector
const heading = await page.$("div > h1");

// ✅ Or use XPath in page.evaluate()
const innerHtml = await page.evaluate(() => {
  return new XPathEvaluator()
    .createExpression("/html/body/div/h1")
    .evaluate(document, XPathResult.FIRST_ORDERED_NODE_TYPE)
    .singleNodeValue.innerHTML;
});

// ❌ Missing browser binding
const browser = await puppeteer.launch(); // Error!

// ❌ Wrong - trying to call launch() on Fetcher directly
const browser = await env.MYBROWSER.launch(); // "RPC receiver does not implement the method 'launch'"

// ✅ Pass binding to Puppeteer/Playwright wrapper
const browser = await puppeteer.launch(env.MYBROWSER);
// or for Playwright:
const browser = await chromium.launch(env.MYBROWSER);

interface Env {
  MYBROWSER: Fetcher; // It's a Fetcher, not a Browser!
}

// Extend timeout to 5 minutes for long-running tasks
const browser = await puppeteer.launch(env.MYBROWSER, {
  keep_alive: 300000 // 5 minutes = 300,000 ms
});

// 1. Check limits before launching
const limits = await puppeteer.limits(env.MYBROWSER);
if (limits.allowedBrowserAcquisitions === 0) {
  return new Response("Concurrency limit reached", { status: 429 });
}

// 2. Reuse sessions
const sessions = await puppeteer.sessions(env.MYBROWSER);
const freeSessions = sessions.filter(s => !s.connectionId);
if (freeSessions.length > 0) {
  const browser = await puppeteer.connect(env.MYBROWSER, freeSessions[0].sessionId);
}

// 3. Use tabs instead of multiple browsers
const browser = await puppeteer.launch(env.MYBROWSER);
const page1 = await browser.newPage();
const page2 = await browser.newPage(); // Same browser, different tabs

// wrangler.jsonc for local development
{
  "browser": {
    "binding": "MYBROWSER",
    "remote": true  // Use real headless browser during dev
  }
}

// ❌ Cannot bypass bot protection
// Requests will always be identified as bots

// ✅ If scraping your own Cloudflare zone (Enterprise plan only):
// 1. Go to Security > WAF > Custom rules
// 2. Create skip rule with custom header:
//    Header: X-Custom-Auth
//    Value: your-secret-token
// 3. Pass header in your scraping requests

await page.setExtraHTTPHeaders({
  'X-Custom-Auth': 'your-secret-token'
});

// Note: Automatic headers are included:
// - cf-biso-request-id
// - cf-biso-devtools

// ❌ Avoid nested function declarations
const data = await page.evaluate(async () => {
  function toNumber(str: string | undefined): number | undefined {
    const num = typeof str === 'string' ? str.replaceAll('.', '').replaceAll(',', '.').match(/[+-]?([0-9]*[.])?[0-9]+/) : false;
    if (num) {
      return Number(num[0]);
    } else {
      return undefined;
    }
  }
  return toNumber('123.456');
});
// Error: ReferenceError: __name is not defined

// ✅ Inline the logic without nested functions
const data = await page.evaluate(async () => {
  const str = '123.456';
  const num = typeof str === 'string' ? str.replaceAll('.', '').replaceAll(',', '.').match(/[+-]?([0-9]*[.])?[0-9]+/) : false;
  return num ? Number(num[0]) : undefined;
});

// ✅ Or update to wrangler 3.83.0+
// npm install wrangler@latest

// ❌ Old behavior - would hang forever if selector not found
await page.waitForSelector('#dynamic-element');

// ✅ New behavior - properly times out (set explicit timeout)
try {
  await page.waitForSelector('#dynamic-element', { timeout: 5000 });
} catch (error) {
  if (error.name === 'TimeoutError') {
    console.log('Element not found within 5 seconds');
    // Handle missing element gracefully
  } else {
    throw error;
  }
}

// ✅ Use longer timeout for slow-loading elements
await page.waitForSelector('#slow-element', { timeout: 30000 }); // 30 seconds

async function withBrowser<T>(env: Env, fn: (browser: Browser) => Promise<T>): Promise<T> {
  let browser: Browser | null = null;

  try {
    // 1. Check limits before launching
    const limits = await puppeteer.limits(env.MYBROWSER);
    if (limits.allowedBrowserAcquisitions === 0) {
      throw new Error("Rate limit reached");
    }

    // 2. Try session reuse first
    const sessions = await puppeteer.sessions(env.MYBROWSER);
    const freeSessions = sessions.filter(s => !s.connectionId);
    browser = freeSessions.length > 0
      ? await puppeteer.connect(env.MYBROWSER, freeSessions[0].sessionId)
      : await puppeteer.launch(env.MYBROWSER);

    // 3. Execute user function
    const result = await fn(browser);

    // 4. Disconnect (keep alive)
    await browser.disconnect();
    return result;
  } catch (error) {
    // 5. Close on error
    if (browser) await browser.close();
    throw error;
  }
}

undefined

undefined