Crawlee + CaptchaAI: integración moderna para scraping

Crawlee es un framework de scraping moderno para Node.js de Apify. A continuación se explica cómo integrar CaptchaAI para la resolución automática de CAPTCHA en tus spiders Crawlee.

Por qué Crawlee + CaptchaAI

Integración básica

const { CheerioCrawler } = require('crawlee');
const https = require('https');

const API_KEY = process.env.CAPTCHAAI_API_KEY;

async function solveCaptcha(sitekey, pageurl) {
    // Submit task
    const submitData = new URLSearchParams({
        key: API_KEY,
        method: 'userrecaptcha',
        googlekey: sitekey,
        pageurl: pageurl,
        json: '1',
    });

    const submitResp = await fetch('https://ocr.captchaai.com/in.php', {
        method: 'POST',
        body: submitData,
    });
    const submitResult = await submitResp.json();

    if (submitResult.status !== 1) {
        throw new Error(`Submit error: ${submitResult.request}`);
    }

    const taskId = submitResult.request;

    // Poll for result
    await new Promise(r => setTimeout(r, 15000));

    for (let i = 0; i < 24; i++) {
        const pollResp = await fetch(
            `https://ocr.captchaai.com/res.php?key=${API_KEY}&action=get&id=${taskId}&json=1`
        );
        const pollResult = await pollResp.json();

        if (pollResult.status === 1) return pollResult.request;
        if (pollResult.request !== 'CAPCHA_NOT_READY') {
            throw new Error(`Solve error: ${pollResult.request}`);
        }

        await new Promise(r => setTimeout(r, 5000));
    }

    throw new Error('Solve timeout');
}

// Crawlee spider with CAPTCHA handling
const crawler = new CheerioCrawler({
    maxConcurrency: 5,
    requestHandlerTimeoutSecs: 180,

    async requestHandler({ request, $, log }) {
        // Check if page has CAPTCHA
        const captchaDiv = $('[data-sitekey]');

        if (captchaDiv.length > 0) {
            const sitekey = captchaDiv.attr('data-sitekey');
            log.info(`CAPTCHA found on ${request.url}, solving...`);

            const token = await solveCaptcha(sitekey, request.url);
            log.info('CAPTCHA solved, submitting form');

            // Submit form with token
            const formData = new URLSearchParams({
                'g-recaptcha-response': token,
            });

            const resp = await fetch(request.url, {
                method: 'POST',
                body: formData,
            });
            const html = await resp.text();
            // Parse the result page...
        }

        // Extract data
        const title = $('title').text();
        const data = $('table tr').map((i, row) => ({
            col1: $(row).find('td:eq(0)').text().trim(),
            col2: $(row).find('td:eq(1)').text().trim(),
        })).get();

        log.info(`Scraped ${data.length} rows from ${request.url}`);
    },

    failedRequestHandler({ request, log }) {
        log.error(`Failed: ${request.url}`);
    },
});

// Run
(async () => {
    await crawler.run([
        'https://example.com/page1',
        'https://example.com/page2',
    ]);
})();

PlaywrightCrawler con CAPTCHA

const { PlaywrightCrawler } = require('crawlee');

const crawler = new PlaywrightCrawler({
    maxConcurrency: 3,
    requestHandlerTimeoutSecs: 180,
    launchContext: {
        launchOptions: {
            headless: true,
            args: [],
        },
    },

    async requestHandler({ request, page, log }) {
        await page.goto(request.url, { waitUntil: 'networkidle' });

        // Check for reCAPTCHA
        const sitekey = await page.evaluate(() => {
            const el = document.querySelector('[data-sitekey]');
            return el ? el.getAttribute('data-sitekey') : null;
        });

        if (sitekey) {
            log.info(`CAPTCHA detected, solving for ${request.url}`);

            const token = await solveCaptcha(sitekey, request.url);

            // Inject token
            await page.evaluate((t) => {
                const ta = document.querySelector('[name="g-recaptcha-response"]');
                if (ta) {
                    ta.style.display = 'block';
                    ta.value = t;
                }
                // Trigger callback
                const widget = document.querySelector('.g-recaptcha');
                if (widget) {
                    const cb = widget.getAttribute('data-callback');
                    if (cb && typeof window[cb] === 'function') {
                        window[cb](t);
                    }
                }
            }, token);

            await page.click('button[type="submit"]');
            await page.waitForNavigation({ waitUntil: 'networkidle' });
        }

        // Extract data
        const title = await page.title();
        const content = await page.textContent('body');
        log.info(`Page: ${title}, length: ${content.length}`);
    },
});

Resolución de CAPTCHA consciente de la sesión

const { CheerioCrawler, Session } = require('crawlee');

const crawler = new CheerioCrawler({
    useSessionPool: true,
    sessionPoolOptions: {
        maxPoolSize: 10,
        sessionOptions: {
            maxUsageCount: 50,
        },
    },

    async requestHandler({ request, $, session, log }) {
        // If blocked, solve CAPTCHA and mark session as usable
        if ($('.captcha-container').length > 0) {
            const sitekey = $('[data-sitekey]').attr('data-sitekey');
            const token = await solveCaptcha(sitekey, request.url);

            // Store token in session for subsequent requests
            session.userData = session.userData || {};
            session.userData.captchaToken = token;
            session.userData.tokenTime = Date.now();

            log.info('CAPTCHA solved, session updated');
        }

        // Normal scraping
        const items = $('div.item').map((i, el) => ({
            name: $(el).find('.name').text().trim(),
            price: $(el).find('.price').text().trim(),
        })).get();

        log.info(`Found ${items.length} items`);
    },
});

Preguntas frecuentes

¿Crawlee tiene soporte CAPTCHA incorporado?

No. Crawlee maneja sesiones, proxies y reintentos, pero debes agregar la resolución CAPTCHA a través de CaptchaAI u otro servicio.

¿Qué crawler de Crawlee debo usar?

Usa CheerioCrawler para páginas estáticas, PlaywrightCrawler para páginas renderizadas con JavaScript y CAPTCHA, y PuppeteerCrawler como alternativa a Playwright.

¿Puedo usar Crawlee con CaptchaAI en Apify?

Sí. Despliega tu actor Crawlee en Apify y usa CaptchaAI mediante llamadas API HTTP. Define la clave API como variable de entorno en Apify.

Guías relacionadas

• Scrapy Spider Middleware para CaptchaAI
• Referencia de códigos de error CaptchaAI

Agrega resolución CAPTCHA a Crawlee: obtén tu clave CaptchaAI.