页面比较

{
    "clientKey": "cc9c18d3e263515c2c072b36a7125eecc078618f",
    "task": {
      "type": "CloudFlareTaskS2",
      "websiteURL": "https://nowsecure.nlin",
      "proxy": "http://JN3wWChA:Dsg7ckfv@45.91.239.47:62930", //请用你自己的代理，这个只是演示
      "waitLoad": false, // 是否需要等待加载完成（如果你需要完整内容就写true，会增加识别时间）
      "requiredCookies": ["cf_clearance"] // 可以要求获取指定Cookies名称，可不填，不一定能获取到
    }
}

fromimport curl_cffirequests
import requeststime
import timere


# 创建任务创建任务函数
def create_task(url, proxy, client_key):
    data"""
 = {  创建Cloudflare防护页面的任务

    :param #url: 填您自己的密钥目标网址
    :param proxy: 代理服务器地址
 "clientKey": clientKey,  :param client_key: 客户端密钥
    "task": {:return: 创建任务的响应结果
    """
    data "type": "CloudFlareTaskS2",= {
        "websiteURLclientKey": urlclient_key,
        "proxytask": proxy{
        }     }"type": "CloudFlareTaskS2",
    url = "https://api.yescaptcha.com/createTask"     response  "userAgent": "",  # 指定chrome内核, 可以为空，如："Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"
            "waitLoad": True,
            "websiteURL": url,
            "proxy": proxy
        }
    }
    api_url = "https://api.yescaptcha.com/createTask"
    response = requests.post(api_url, json=data).json()
    return response

  
# 获取任务结果函数
def get_task(task_id, client_key):
    """
    获取任务的执行结果

    :param task_id: 任务ID
    :param client_key: 客户端密钥
    :return: 任务结果的响应结果
    """
    api_url = "https://api.yescaptcha.com/getTaskResult"
    data = {
        "clientKey": client_key,
        "taskId": task_id
    }
    response = requests.post(api_url, json=data).json()
    return response



# 获取结果完整的请求函数
def get_task(task_idresult(url, proxy, client_key):
  url = "http://api.yescaptcha.com/getTaskResult"""
  data = {完整的创建任务并获取结果的流程

    :param #url: 填您自己的密钥目标网址
      "clientKey":param proxy: clientKey,
 代理服务器地址
    "taskId":param taskclient_id
  }
  response = requests.post(url, json=data).json()key: 客户端密钥
    :return: response任务执行结果
  # 完整的请求 def get_result(*args, **kwargs):"""
    uuidtask_response = create_task(*argsurl, proxy, **kwargs)client_key)
    if not uuidtask_response or not uuidtask_response.get('taskId'):
        return uuidtask_response

    print("TaskID:", uuidtask_response)
    for i_ in range(30):
        time.sleep(3)
        result = get_task(uuidtask_response.get('taskId'), client_key)
        if result.get('status') == 'processing':':
            continue
        elif result.get('status') == 'ready':
            return result
        else:
        print("Fail:", result)
    raise Exception(result)
    return {"status": "timeout"}



if __name__ == '__main__':
    # 客户端密钥, 登陆yescaptcha.com获取
    #client_key 填您的密钥= "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
   clientKey =
"xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"    # 代理服务器地址，填您自己的代理地址
    # 填您自己的代理，不要填本地的地址不要填本地地址（如：http://127.0.0.1:1080，http://localhost:1080这种，这个只有你自己能用）
    proxy = "http://JN3wWChAuser:Dsg7ckfv@176password@103.222147.59170.86108:6404864484"
    proxies = {
        'http': proxy, 
        'https': proxy,
    }
    
    # 要访问的网址目标网址
    url = "https://nowsecure.nlin/"


    # 正常情况是这样的
使用普通requests请求
   # response = requests.get(url, proxies=proxies)

   # print("请求响应：", response.status_code)
    # print("网页标题：", re.search(r"<title>(.*?)</title>", response.text[:200])
    # 返回：请求响应： 403


    # 使用 curl_cffi.requests请求
    # response = requests.get(url, proxies=proxies, impersonate="chrome110")
    # print("请求响应：)) if response.text else print("网页标题：", response.status_code)
text[:1000])
   # print("网页标题：",是否为CF盾：", "cf_chl" in response.text[:200])

   # 返回：请求响应：
200       # 使用接口返回的值来请求
    task_result = get_result(url, proxy=proxy, client_key)
    if not task_result.get("solution"):
        print("任务失败", task_result)
        exit()
  
    
     solution = task_result.get("solution")
    # 从solution中获取请求头和cookies
    headers = {solution.get("request_headers")
    headers.update(solution.get("headers"))
     'User-Agent':cookies = solution.get("user_agentcookies")
    } print("Headers:", headers)
    print("UaCookies：", headerscookies)
    
    cookies = solution.get("cookies")
 # 使用curl_cffi.requests请求
    # 请先安装curl_cffi库，并且是pre版本：pip install curl_cffi --pre
   print("Cookies：", cookies)
     from curl_cffi import requests as curl_requests
    response = curl_requests.get(url, headers=headers, cookies=cookies, proxies=proxies, impersonate="chrome110chrome120")
    print("请求响应：", response.status_code)
    print("网页标题：", re.search(r"<title>(.*?)</title>", response.text)) if response.text else print("网页标题：", response.text[:2001000])
    print("是否为CF盾：", "cf_chl" in response.text)