HTTPX + 验证码人工智能集成

HTTPX 是一个现代 Python HTTP 客户端，具有异步支持和 HTTP/2. 本指南演示如何将其与 CaptchaAI 一起使用来解决同步和异步验证码问题。

要求

pip install httpx

同步客户端

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()

异步客户端

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())

HTTP/2 支持

HTTPX 支持 HTTP/2，减少连接开销：

pip install httpx[http2]

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

HTTP/2 通过单个连接复用请求，从而提高提交和轮询多个验证码时的性能。

使用验证码处理进行抓取示例

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())

比较：httpx、requests、aiohttp

常问问题

我应该在请求上使用 httpx 吗？

对于新项目来说，是的。 httpx 具有请求兼容的 API 以及异步和 HTTP/2 支持。对于使用请求的现有代码，迁移非常简单。

httpx 比 aiohttp 快吗？

aiohttp 对于纯异步工作负载的开销略低。 httpx 对于 HTTP/2 连接来说更快，对于混合sync/async 代码更方便。

我可以在 Scrapy 中使用 httpx 吗？

不直接 - Scrapy 使用 Twisted 的事件循环。在独立脚本中使用 httpx 或与基于 asyncio 的框架（如 FastAPI）一起使用。

相关指南

• aiohttp + CaptchaAI 异步
• Axios + CaptchaAI（无浏览器）
• 验证码抓取 Python 指南