如何通过 Python 解决 AWS 验证码/挑战

pip install capsolver requests beautifulsoup4

import capsolver
import requests
from bs4 import BeautifulSoup
import re
from urllib.parse import urlparse

# -------------------请修改以下值-------------------
# 代理服务器信息，格式为：http://用户名:密码@IP:端口
PROXY = "http://用户名:密码@IP:端口"
# 您要解决AWS WAF的网站目标URL
PAGE_URL = "https://www.您要访问的AWS保护网站.com"
# 从CapSolver仪表板获取的API密钥
CAPSOLVER_API_KEY = "您的API密钥"
# ---------------------------------------------------

def solve_aws_waf(is_captcha_challenge, **kwargs):
    """
    使用CapSolver解决AWS WAF挑战或验证码。
    :param is_captcha_challenge: True表示验证码（405状态码），False表示JS挑战（202状态码）。
    :param kwargs: 解决任务所需的参数。
    :return: 解决方案对象，或在失败时返回None。
    """
    task_type = "AntiAwsWafTask" if is_captcha_challenge else "AntiAwsWafTaskProxyLess"
    print(f"创建 '{task_type}' 任务...")
    
    task_payload = {
        "type": task_type,
        "websiteURL": PAGE_URL,
    }
    
    # 根据挑战类型添加特定参数
    if is_captcha_challenge:
        # 对于验证码挑战，需要awsKey、awsIv、awsContext
        task_payload.update({
            "awsKey": kwargs.get("awsKey"),
            "awsIv": kwargs.get("awsIv"),
            "awsContext": kwargs.get("awsContext"),
            "awsChallengeJS": kwargs.get("awsChallengeJS"),
            "proxy": PROXY
        })
    else:
        # 对于JS挑战，只需要awsChallengeJS的URL
        task_payload["awsChallengeJS"] = kwargs.get("awsChallengeJS")

    try:
        solution = capsolver.solve(task_payload)
        if solution and solution.get("errorId", 0) == 0:
            print("成功获取解决方案！")
            return solution
        else:
            error_desc = solution.get('errorDescription', '未知错误') if solution else '未知错误'
            print(f"解决任务失败: {error_desc}")
            return None
    except Exception as e:
        print(f"调用CapSolver时发生异常: {e}")
        return None

def main():
    """执行整个过程的主函数。"""
    capsolver.api_key = CAPSOLVER_API_KEY
    session = requests.Session()
    session.proxies = {"http": PROXY, "https": PROXY}
    
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8",
        "Accept-Language": "en-US,en;q=0.9",
    }

    print(f"尝试访问: {PAGE_URL}")
    response = session.get(PAGE_URL, headers=headers)
    print(f"收到状态码: {response.status_code}")

    solution = None
    
    # 场景1：处理AWS JavaScript挑战（状态码202）
    if response.status_code == 202:
        print("检测到AWS JavaScript挑战。")
        soup = BeautifulSoup(response.content, 'html.parser')
        script_tag = soup.find('script', {'src': re.compile(r'token\.awswaf\.com')})
        if script_tag:
            challenge_js_url = script_tag['src']
            print(f"找到挑战JS URL: {challenge_js_url}")
            solution = solve_aws_waf(is_captcha_challenge=False, awsChallengeJS=challenge_js_url)
        else:
            print("错误：无法找到AWS挑战脚本。")

    # 场景2：处理AWS验证码（状态码405）
    elif response.status_code == 405:
        print("检测到AWS验证码。")
        soup = BeautifulSoup(response.content, 'html.parser')
        script_tag = soup.find('script', {'src': re.compile(r'token\.awswaf\.com')})
        script_text_tag = soup.find('script', string=re.compile('.*key.*'))
        
        if script_tag and script_text_tag:
            challenge_js_url = script_tag['src']
            script_text = script_text_tag.string
            
            key = re.search(r'"key":"(.*?)"', script_text).group(1)
            iv = re.search(r'"iv":"(.*?)"', script_text).group(1)
            context = re.search(r'"context":"(.*?)"', script_text).group(1)
            
            print(f"提取的参数: Key={key[:5]}..., IV={iv[:5]}..., Context={context[:5]}...")
            solution = solve_aws_waf(
                is_captcha_challenge=True,
                awsKey=key,
                awsIv=iv,
                awsContext=context,
                awsChallengeJS=challenge_js_url
            )
        else:
            print("错误：无法从页面中提取所有必需的验证码参数。")

    # 如果成功解决，设置cookie并重试请求
    if solution and solution.get("cookie"):
        aws_token = solution["cookie"]
        print(f"成功获取aws-waf-token: {aws_token[:30]}...")
        
        domain = f".{urlparse(PAGE_URL).netloc}"
        session.cookies.set("aws-waf-token", aws_token, domain=domain)
        
        print("Cookie已设置。正在重试请求...")
        final_response = session.get(PAGE_URL, headers=headers)
        print(f"最终请求状态码: {final_response.status_code}")
        
        if final_response.status_code == 200:
            print("成功绕过AWS WAF！")
            # print(final_response.text) # 取消注释以查看页面内容
        else:
            print("设置Cookie后请求失败。请检查token或代理。")
    else:
        print("无法解决AWS WAF。退出。")

if __name__ == "__main__":
    main()