Puppeteer CAPTCHA resolvendo com Node.js e CaptchaAI

Puppeteer é o navegador headless ideal para automação Node.js. Quando sites de destino atendem CAPTCHAs, a API do CaptchaAI os resolve externamente - o Puppeteer extrai os parâmetros, CaptchaAI retorna o token e o Puppeteer o injeta de volta.

Requisitos

Como funciona

1. O Puppeteer navega até a página com o CAPTCHA
2. Seu script extrai a chave do site CAPTCHA do DOM
3. CaptchaAI resolve o desafio do lado do servidor
4. Seu script injeta o token e envia o formulário

Etapa 1: Crie o Módulo Solver

// solver.js
const axios = require("axios");

const API_KEY = "YOUR_API_KEY";
const POLL_INTERVAL = 5000;
const MAX_ATTEMPTS = 60;

async function solveRecaptchaV2(siteKey, pageUrl) {
  // Submit task
  const submitResp = await axios.get("https://ocr.captchaai.com/in.php", {
    params: {
      key: API_KEY,
      method: "userrecaptcha",
      googlekey: siteKey,
      pageurl: pageUrl,
    },
  });

  if (!submitResp.data.startsWith("OK|")) {
    throw new Error(`Submit failed: ${submitResp.data}`);
  }

  const taskId = submitResp.data.split("|")[1];
  console.log(`Task submitted: ${taskId}`);

  // Poll for result
  for (let i = 0; i < MAX_ATTEMPTS; i++) {
    await new Promise((r) => setTimeout(r, POLL_INTERVAL));

    const result = await axios.get("https://ocr.captchaai.com/res.php", {
      params: { key: API_KEY, action: "get", id: taskId },
    });

    if (result.data === "CAPCHA_NOT_READY") continue;
    if (result.data.startsWith("OK|")) {
      return result.data.split("|")[1];
    }
    throw new Error(`Solve failed: ${result.data}`);
  }
  throw new Error("Solve timed out");
}

async function solveTurnstile(siteKey, pageUrl) {
  const submitResp = await axios.get("https://ocr.captchaai.com/in.php", {
    params: {
      key: API_KEY,
      method: "turnstile",
      sitekey: siteKey,
      pageurl: pageUrl,
    },
  });

  if (!submitResp.data.startsWith("OK|")) {
    throw new Error(`Submit failed: ${submitResp.data}`);
  }

  const taskId = submitResp.data.split("|")[1];

  for (let i = 0; i < MAX_ATTEMPTS; i++) {
    await new Promise((r) => setTimeout(r, POLL_INTERVAL));
    const result = await axios.get("https://ocr.captchaai.com/res.php", {
      params: { key: API_KEY, action: "get", id: taskId },
    });
    if (result.data === "CAPCHA_NOT_READY") continue;
    if (result.data.startsWith("OK|")) return result.data.split("|")[1];
    throw new Error(`Solve failed: ${result.data}`);
  }
  throw new Error("Solve timed out");
}

module.exports = { solveRecaptchaV2, solveTurnstile };

Etapa 2: configurar o Puppeteer com QA de navegador

const puppeteer = require("puppeteer");

async function createBrowser() {
  const browser = await puppeteer.launch({
    headless: "new",
    args: [
      "--no-sandbox",
      "--disable-setuid-sandbox",
      "--disable-blink-features=AutomationControlled",
    ],
  });

  const page = await browser.newPage();
  await page.setUserAgent(
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
  );

  // Hide automation indicators
  await page.evaluateOnNewDocument(() => {
    Object.defineProperty(navigator, "webdriver", { get: () => false });
  });

  return { browser, page };
}

Etapa 3: Resolva o reCAPTCHA em uma página

const { solveRecaptchaV2 } = require("./solver");

async function scrapeWithCaptcha(url) {
  const { browser, page } = await createBrowser();

  try {
    await page.goto(url, { waitUntil: "networkidle2" });

    // Extract site key
    const siteKey = await page.$eval(
      ".g-recaptcha",
      (el) => el.getAttribute("data-sitekey")
    );
    console.log("Site key:", siteKey);

    // Solve with CaptchaAI
    const token = await solveRecaptchaV2(siteKey, url);
    console.log("Token received:", token.substring(0, 50));

    // Inject token
    await page.evaluate((token) => {
      document.getElementById("g-recaptcha-response").innerHTML = token;
      document.getElementById("g-recaptcha-response").style.display = "";
    }, token);

    // Submit the form
    await page.click('button[type="submit"]');
    await page.waitForNavigation({ waitUntil: "networkidle2" });

    // Scrape the content
    const content = await page.content();
    console.log("Page loaded successfully");
    return content;
  } finally {
    await browser.close();
  }
}

Etapa 4: lidar com retornos de chamada

Alguns sites usam retornos de chamada JavaScript em vez de envio de formulário:

// Trigger the reCAPTCHA callback
await page.evaluate((token) => {
  // Method 1: Direct callback
  if (typeof ___grecaptcha_cfg !== "undefined") {
    const clients = ___grecaptcha_cfg.clients;
    Object.keys(clients).forEach((key) => {
      const client = clients[key];
      // Find the callback function
      const findCallback = (obj) => {
        for (const prop in obj) {
          if (typeof obj[prop] === "function") {
            obj[prop](token);
            return true;
          }
          if (typeof obj[prop] === "object" && obj[prop] !== null) {
            if (findCallback(obj[prop])) return true;
          }
        }
        return false;
      };
      findCallback(client);
    });
  }
}, token);

Exemplo de trabalho completo

const puppeteer = require("puppeteer");
const axios = require("axios");

const API_KEY = "YOUR_API_KEY";

async function solveCaptcha(siteKey, pageUrl) {
  const submit = await axios.get("https://ocr.captchaai.com/in.php", {
    params: {
      key: API_KEY,
      method: "userrecaptcha",
      googlekey: siteKey,
      pageurl: pageUrl,
    },
  });
  const taskId = submit.data.split("|")[1];

  while (true) {
    await new Promise((r) => setTimeout(r, 5000));
    const result = await axios.get("https://ocr.captchaai.com/res.php", {
      params: { key: API_KEY, action: "get", id: taskId },
    });
    if (result.data === "CAPCHA_NOT_READY") continue;
    if (result.data.startsWith("OK|")) return result.data.split("|")[1];
    throw new Error(result.data);
  }
}

(async () => {
  const browser = await puppeteer.launch({
    headless: "new",
    args: ["--disable-blink-features=AutomationControlled"],
  });
  const page = await browser.newPage();

  try {
    await page.goto("https://staging.example.com/qa-login", {
      waitUntil: "networkidle2",
    });

    // Get the site key
    const siteKey = await page.$eval(".g-recaptcha", (el) =>
      el.getAttribute("data-sitekey")
    );

    // Solve
    const token = await solveCaptcha(siteKey, page.url());

    // Inject and submit
    await page.evaluate((t) => {
      document.getElementById("g-recaptcha-response").innerHTML = t;
    }, token);

    await page.click("#submit-btn");
    await page.waitForNavigation();

    console.log("Done:", page.url());
  } finally {
    await browser.close();
  }
})();

Solução de problemas

Perguntas frequentes

Devo usar o modo modo headless ou modo headless?

O modo Headless funciona bem com CaptchaAI, pois o CAPTCHA é resolvido no lado do servidor. Use o modo headed apenas para depuração.

Posso usar o Puppeteer com Cloudflare Turnstile?

Sim. Extraia data-sitekey da div .cf-turnstile e use method=turnstile com CaptchaAI. Veja a função solveTurnstile acima.

Como lidar com vários CAPTCHAs em uma página?

Extraia cada chave de site separadamente e resolva-as em paralelo usando Promise.all().

Guias Relacionados

• Manipulação de Selênio CAPTCHA com Python
• Manipulação de CAPTCHA do dramaturgo
• Raspagem CAPTCHA com Node.js