aiohttp + CaptchaAI: resolución asíncrona de CAPTCHA

aiohttp habilita solicitudes HTTP sin bloqueo en Python. Combínelo con CaptchaAI para resolver múltiples CAPTCHA simultáneamente sin bloquear el bucle de eventos.

Requisitos

pip install aiohttp

Cliente asíncrono CaptchaAI

import aiohttp
import asyncio


class AsyncCaptchaAI:
    def __init__(self, api_key):
        self.api_key = api_key
        self.base_url = "https://ocr.captchaai.com"

    async def submit(self, session, params):
        """Submit a CAPTCHA task and return the task ID."""
        params["key"] = self.api_key
        async with session.get(
            f"{self.base_url}/in.php", params=params
        ) as resp:
            text = await resp.text()

        if not text.startswith("OK|"):
            raise Exception(f"Submit failed: {text}")

        return text.split("|")[1]

    async def poll(self, session, task_id, timeout=300):
        """Poll for the result with a timeout."""
        params = {
            "key": self.api_key,
            "action": "get",
            "id": task_id,
        }
        deadline = asyncio.get_event_loop().time() + timeout

        while asyncio.get_event_loop().time() < deadline:
            await asyncio.sleep(5)

            async with session.get(
                f"{self.base_url}/res.php", params=params
            ) as resp:
                text = await resp.text()

            if text == "CAPCHA_NOT_READY":
                continue
            if text.startswith("OK|"):
                return text.split("|", 1)[1]
            raise Exception(f"Solve failed: {text}")

        raise TimeoutError(f"Task {task_id} timed out after {timeout}s")

    async def solve(self, session, params, timeout=300):
        """Submit and poll in one call."""
        task_id = await self.submit(session, params)
        return await self.poll(session, task_id, timeout)

    async def get_balance(self, session):
        """Check account balance."""
        params = {"key": self.api_key, "action": "getbalance"}
        async with session.get(
            f"{self.base_url}/res.php", params=params
        ) as resp:
            return float(await resp.text())

Resolver un solo CAPTCHA

import asyncio
import os

async def main():
    solver = AsyncCaptchaAI(os.environ["CAPTCHAAI_API_KEY"])

    async with aiohttp.ClientSession() as session:
        # Check balance
        balance = await solver.get_balance(session)
        print(f"Balance: ${balance:.2f}")

        # Solve reCAPTCHA v2
        token = await solver.solve(session, {
            "method": "userrecaptcha",
            "googlekey": "6Le-wvkS...",
            "pageurl": "https://example.com",
        })
        print(f"Token: {token[:50]}...")

asyncio.run(main())

Resuelva múltiples CAPTCHA simultáneamente

async def solve_batch(urls, site_key):
    solver = AsyncCaptchaAI(os.environ["CAPTCHAAI_API_KEY"])

    async with aiohttp.ClientSession() as session:
        tasks = [
            solver.solve(session, {
                "method": "userrecaptcha",
                "googlekey": site_key,
                "pageurl": url,
            })
            for url in urls
        ]

        results = await asyncio.gather(*tasks, return_exceptions=True)

        for url, result in zip(urls, results):
            if isinstance(result, Exception):
                print(f"FAILED {url}: {result}")
            else:
                print(f"SOLVED {url}: {len(result)} chars")

        return results


urls = [
    "https://example.com/page1",
    "https://example.com/page2",
    "https://example.com/page3",
    "https://example.com/page4",
    "https://example.com/page5",
]
asyncio.run(solve_batch(urls, "6Le-wvkS..."))

Raspado con manejo de CAPTCHA

async def scrape_with_captcha(url, site_key):
    solver = AsyncCaptchaAI(os.environ["CAPTCHAAI_API_KEY"])

    async with aiohttp.ClientSession() as session:
        # Fetch the page
        async with session.get(url) as resp:
            html = await resp.text()

        # Check if page has a CAPTCHA
        if "g-recaptcha" not in html:
            return html  # No CAPTCHA, return content

        # Solve the CAPTCHA
        token = await solver.solve(session, {
            "method": "userrecaptcha",
            "googlekey": site_key,
            "pageurl": url,
        })

        # Submit with solved token
        async with session.post(url, data={
            "g-recaptcha-response": token,
        }) as resp:
            return await resp.text()

Semáforo para control de velocidad

Limite las soluciones simultáneas para evitar sobrecargar la API:

async def solve_with_limit(urls, site_key, max_concurrent=10):
    solver = AsyncCaptchaAI(os.environ["CAPTCHAAI_API_KEY"])
    semaphore = asyncio.Semaphore(max_concurrent)

    async def solve_one(session, url):
        async with semaphore:
            return await solver.solve(session, {
                "method": "userrecaptcha",
                "googlekey": site_key,
                "pageurl": url,
            })

    async with aiohttp.ClientSession() as session:
        tasks = [solve_one(session, url) for url in urls]
        results = await asyncio.gather(*tasks, return_exceptions=True)

    solved = sum(1 for r in results if not isinstance(r, Exception))
    print(f"Solved {solved}/{len(urls)} CAPTCHAs")
    return results

Ejemplo de Turnstile

async def solve_turnstile(url, sitekey):
    solver = AsyncCaptchaAI(os.environ["CAPTCHAAI_API_KEY"])

    async with aiohttp.ClientSession() as session:
        token = await solver.solve(session, {
            "method": "turnstile",
            "sitekey": sitekey,
            "pageurl": url,
        })
        return token

Solución de problemas

Preguntas frecuentes

¿Por qué aiohttp en lugar de httpx?

aiohttp es la biblioteca HTTP asíncrona más madura en Python y con una opción sólida rendimiento para cargas de trabajo de alta concurrencia. httpx también funciona: consulte la guía de integración httpx.

¿Cuántas soluciones simultáneas puedo ejecutar?

CaptchaAI maneja más de 100 solicitudes simultáneas. Utilice un semáforo para controlar su concurrencia según sus necesidades y saldo.

¿Puedo reutilizar la sesión en varias soluciones?

Sí, y deberías hacerlo. Las sesiones de aiohttp mantienen grupos de conexiones, lo que hace que las solicitudes posteriores sean más rápidas.

Guías relacionadas

• Integración HTTPX + CaptchaAI
• Resolución de CAPTCHA en paralelo vs. secuencial
• Integración Scrapy + CaptchaAI