实战教程

用于验证码解决并行性的 Python ThreadPoolExecutor

asyncio 功能强大,但需要将整个调用链重写为异步。 ThreadPoolExecutor 为您提供与标准同步代码的并行性 - 将其放入现有项目中而无需重组。

为什么使用 ThreadPoolExecutor 进行验证码

验证码解析为I/O-bound(等待HTTP响应)。 Python 线程在 I/O 操作期间释放 GIL,使 ThreadPoolExecutor 对此工作负载高效:

方法 复杂 适合现有代码 I/O 的并行性
顺序 没有任何 是的 没有任何
线程池执行器 低的 是的 好的
异步 高的 需要异步重写 最好的
多重处理 中等的 大多 对 I/O 来说太过分了

基本实现

import os
import time
from concurrent.futures import ThreadPoolExecutor, as_completed
import requests

API_KEY = os.environ["CAPTCHAAI_API_KEY"]


def solve_captcha(sitekey, pageurl):
    """Synchronous CAPTCHA solve — submit and poll."""
    # Submit
    resp = requests.post("https://ocr.captchaai.com/in.php", data={
        "key": API_KEY,
        "method": "userrecaptcha",
        "googlekey": sitekey,
        "pageurl": pageurl,
        "json": 1
    })
    data = resp.json()

    if data.get("status") != 1:
        raise RuntimeError(data.get("request", "Submit failed"))

    captcha_id = data["request"]

    # Poll for result
    for _ in range(60):
        time.sleep(5)
        result = requests.get("https://ocr.captchaai.com/res.php", params={
            "key": API_KEY,
            "action": "get",
            "id": captcha_id,
            "json": 1
        }).json()

        if result.get("status") == 1:
            return result["request"]
        if result.get("request") != "CAPCHA_NOT_READY":
            raise RuntimeError(result.get("request", "Unknown error"))

    raise TimeoutError("Solve timeout after 300s")


# Batch solve with ThreadPoolExecutor
tasks = [
    {"sitekey": "6Le-wvkSAAAAAPBMRTvw0Q4Muexq9bi0DJwx_mJ-", "pageurl": f"https://example.com/page/{i}"}
    for i in range(20)
]

start = time.time()

with ThreadPoolExecutor(max_workers=10) as executor:
    futures = {
        executor.submit(solve_captcha, t["sitekey"], t["pageurl"]): t
        for t in tasks
    }

    solved = 0
    failed = 0

    for future in as_completed(futures):
        task = futures[future]
        try:
            solution = future.result()
            solved += 1
            print(f"[OK] {task['pageurl']}: {solution[:30]}...")
        except Exception as e:
            failed += 1
            print(f"[ERR] {task['pageurl']}: {e}")

elapsed = time.time() - start
print(f"\nDone: {solved} solved, {failed} failed in {elapsed:.1f}s")

使用会话进行连接重用

每个请求创建一个新的 TCP 连接会浪费时间。每个线程共享一个 requests.Session

import threading

# Thread-local storage for sessions
thread_local = threading.local()


def get_session():
    """Get or create a thread-local session."""
    if not hasattr(thread_local, "session"):
        thread_local.session = requests.Session()
        # Configure connection pooling
        adapter = requests.adapters.HTTPAdapter(
            pool_connections=10,
            pool_maxsize=10,
            max_retries=2
        )
        thread_local.session.mount("https://", adapter)
    return thread_local.session


def solve_captcha_pooled(sitekey, pageurl):
    """Solve using thread-local connection pooling."""
    session = get_session()

    resp = session.post("https://ocr.captchaai.com/in.php", data={
        "key": API_KEY,
        "method": "userrecaptcha",
        "googlekey": sitekey,
        "pageurl": pageurl,
        "json": 1
    })
    data = resp.json()

    if data.get("status") != 1:
        raise RuntimeError(data.get("request"))

    captcha_id = data["request"]

    for _ in range(60):
        time.sleep(5)
        result = session.get("https://ocr.captchaai.com/res.php", params={
            "key": API_KEY,
            "action": "get",
            "id": captcha_id,
            "json": 1
        }).json()

        if result.get("status") == 1:
            return result["request"]
        if result.get("request") != "CAPCHA_NOT_READY":
            raise RuntimeError(result.get("request"))

    raise TimeoutError("Solve timeout")

map() 用于简单的批量操作

当您不需要每个任务的错误处理时:

def solve_task(task):
    """Wrapper that returns result dict."""
    try:
        solution = solve_captcha_pooled(task["sitekey"], task["pageurl"])
        return {"url": task["pageurl"], "solution": solution, "error": None}
    except Exception as e:
        return {"url": task["pageurl"], "solution": None, "error": str(e)}


with ThreadPoolExecutor(max_workers=10) as executor:
    results = list(executor.map(solve_task, tasks))

solved = [r for r in results if r["solution"]]
failed = [r for r in results if r["error"]]
print(f"Solved: {len(solved)}, Failed: {len(failed)}")

超时保护

防止失控线程阻塞池:

from concurrent.futures import TimeoutError as FuturesTimeout

with ThreadPoolExecutor(max_workers=10) as executor:
    futures = {
        executor.submit(solve_captcha_pooled, t["sitekey"], t["pageurl"]): t
        for t in tasks
    }

    for future in as_completed(futures, timeout=600):  # 10 min global timeout
        task = futures[future]
        try:
            solution = future.result(timeout=120)  # 2 min per task
            print(f"[OK] {task['pageurl']}")
        except FuturesTimeout:
            print(f"[TIMEOUT] {task['pageurl']}")
        except Exception as e:
            print(f"[ERR] {task['pageurl']}: {e}")

进度回调

实时跟踪完成情况:

import threading

progress_lock = threading.Lock()
progress = {"done": 0, "total": 0}


def solve_with_progress(task):
    result = solve_task(task)
    with progress_lock:
        progress["done"] += 1
        pct = progress["done"] / progress["total"] * 100
        print(f'\r  Progress: {progress["done"]}/{progress["total"]} ({pct:.0f}%)', end="")
    return result


progress["total"] = len(tasks)

with ThreadPoolExecutor(max_workers=10) as executor:
    results = list(executor.map(solve_with_progress, tasks))

print()  # Newline after progress

选择 max_workers

工人 并发解决 开销 最适合
5 5 很低 小批量,保守使用
10 10 低的 一般用途
25 25 缓和 大容量管道
50 50 更高 最大吞吐量

更多的工作线程意味着更多的并发 API 连接。从 10 开始,在监控错误率的同时增加。

ThreadPoolExecutor 与 asyncio

# ThreadPoolExecutor — drop into existing sync code
with ThreadPoolExecutor(max_workers=10) as executor:
    results = list(executor.map(solve_task, tasks))

# asyncio — requires async function chain
async def main():
    async with aiohttp.ClientSession() as session:
        tasks = [solve_async(session, t) for t in task_list]
        results = await asyncio.gather(*tasks)

在以下情况下使用 ThreadPoolExecutor:

  • 您现有的代码库是同步的
  • 您使用不支持异步的库(Selenium、某些 ORM)
  • 您想要快速并行而不需要重组

在以下情况下使用 asyncio:

  • 从头开始构建
  • 最大效率很重要(更少的操作系统线程)
  • 已经在异步框架中(FastAPI、aiohttp)

故障排除

问题 原因 处理方式
所有线程都被阻塞 每个线程在轮询期间等待 time.sleep 这是预期的——线程在睡眠期间释放 GIL
ConnectionError 秒杀 并发连接数过多 减少max_workers;使用连接池
结果乱序 as_completed 按完成顺序返回 使用 map() 获取有序结果,或使用 dict 进行跟踪
记忆力增长 期货中持有的大型结果对象 as_completed循环中处理结果;不存储全部

常问问题

GIL 会阻止真正的并行吗?

不 - 对于像 HTTP 请求和 time.sleep 这样的 I/O-bound 工作,Python 释放了 GIL。您的线程在网络调用期间真正并发运行。GIL 仅限制 CPU 绑定的并行性。

ThreadPoolExecutor 每小时可以处理多少个验证码?

10 名工作人员和 15 秒的平均解决时间:每小时约 2,400 个。拥有 25 名工人:每小时约 6,000 人。瓶颈是 CaptchaAI 求解时间,而不是 Python 线程。

我应该使用 ProcessPoolExecutor 吗?

不会。验证码解决是 I/O-bound. ProcessPoolExecutor 增加了进程间通信开销,但没有任何好处。坚持使用线程。

下一步

并行验证码解决 -获取您的 CaptchaAI API 密钥并将 ThreadPoolExecutor 放入管道中。

相关指南:

该文章已禁用评论。