Integrasi HTTPX + CaptchaAI

HTTPX adalah klien HTTP Python modern dengan dukungan async dan HTTP/2. Panduan ini menunjukkan cara menggunakannya dengan CaptchaAI untuk penyelesaian CAPTCHA sinkronisasi dan asinkron.

Prasyarat

pip install httpx

Klien Sinkron

import httpx
import time
import os


class CaptchaAISync:
    def __init__(self, api_key):
        self.api_key = api_key
        self.base_url = "https://ocr.captchaai.com"
        self.client = httpx.Client(timeout=30)

    def solve(self, params, timeout=300):
        params["key"] = self.api_key

        # Submit
        resp = self.client.get(f"{self.base_url}/in.php", params=params)
        text = resp.text

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

        task_id = text.split("|")[1]

        # Poll
        deadline = time.time() + timeout
        poll_params = {"key": self.api_key, "action": "get", "id": task_id}

        while time.time() < deadline:
            time.sleep(5)
            result = self.client.get(
                f"{self.base_url}/res.php", params=poll_params
            )

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

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

    def get_balance(self):
        resp = self.client.get(f"{self.base_url}/res.php", params={
            "key": self.api_key, "action": "getbalance"
        })
        return float(resp.text)

    def close(self):
        self.client.close()


# Usage
solver = CaptchaAISync(os.environ["CAPTCHAAI_API_KEY"])

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

Klien Asinkron

import httpx
import asyncio
import os


class CaptchaAIAsync:
    def __init__(self, api_key):
        self.api_key = api_key
        self.base_url = "https://ocr.captchaai.com"
        self.client = httpx.AsyncClient(timeout=30)

    async def solve(self, params, timeout=300):
        params["key"] = self.api_key

        # Submit
        resp = await self.client.get(
            f"{self.base_url}/in.php", params=params
        )
        text = resp.text

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

        task_id = text.split("|")[1]

        # Poll
        deadline = asyncio.get_event_loop().time() + timeout
        poll_params = {"key": self.api_key, "action": "get", "id": task_id}

        while asyncio.get_event_loop().time() < deadline:
            await asyncio.sleep(5)
            result = await self.client.get(
                f"{self.base_url}/res.php", params=poll_params
            )

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

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

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

    async def close(self):
        await self.client.aclose()


# Usage
async def main():
    solver = CaptchaAIAsync(os.environ["CAPTCHAAI_API_KEY"])

    # Solve multiple concurrently
    tasks = [
        solver.solve({
            "method": "userrecaptcha",
            "googlekey": "6Le-wvkS...",
            "pageurl": f"https://example.com/page{i}",
        })
        for i in range(5)
    ]

    results = await asyncio.gather(*tasks, return_exceptions=True)
    for i, r in enumerate(results):
        if isinstance(r, Exception):
            print(f"Page {i}: FAILED - {r}")
        else:
            print(f"Page {i}: solved ({len(r)} chars)")

    await solver.close()

asyncio.run(main())

Dukungan HTTP/2

HTTPX mendukung HTTP/2, mengurangi overhead koneksi:

pip install httpx[http2]

client = httpx.AsyncClient(http2=True, timeout=30)

HTTP/2 meng-multiplex request melalui satu koneksi, meningkatkan performa saat submit dan poll beberapa CAPTCHA secara bersamaan.

Contoh Scraping dengan Penanganan CAPTCHA

import httpx
import re
import os

async def scrape_with_captcha(url, solver):
    async with httpx.AsyncClient() as client:
        # Fetch page
        resp = await client.get(url)
        html = resp.text

        # Check for reCAPTCHA
        match = re.search(
            r'data-sitekey=["\']([A-Za-z0-9_-]+)["\']', html
        )
        if not match:
            return html

        site_key = match.group(1)
        token = await solver.solve({
            "method": "userrecaptcha",
            "googlekey": site_key,
            "pageurl": url,
        })

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


async def main():
    solver = CaptchaAIAsync(os.environ["CAPTCHAAI_API_KEY"])
    content = await scrape_with_captcha("https://example.com", solver)
    print(f"Got {len(content)} chars")
    await solver.close()

asyncio.run(main())

Perbandingan: httpx vs requests vs aiohttp

Pertanyaan Umum

Haruskah saya menggunakan httpx daripada requests?

Untuk proyek baru, ya. httpx memiliki API yang kompatibel dengan requests ditambah dukungan async dan HTTP/2. Untuk kode yang sudah ada yang menggunakan requests, migrasinya mudah.

Apakah httpx lebih cepat dari aiohttp?

aiohttp memiliki overhead sedikit lebih rendah untuk beban kerja async murni. httpx lebih cepat untuk koneksi HTTP/2 dan lebih nyaman untuk kode sync/async campuran.

Bisakah saya menggunakan httpx dengan Scrapy?

Tidak secara langsung — Scrapy menggunakan event loop Twisted. Gunakan httpx dalam script mandiri atau dengan framework berbasis asyncio seperti FastAPI.

Panduan Terkait

• aiohttp + CaptchaAI Async
• Axios + CaptchaAI (Tanpa Browser)
• Panduan Python Scraping CAPTCHA