页面比较

...
代码块
import requests
import time
import re


# 创建任务
def create_task(url, proxy):
    data = {
        # 填您自己的密钥
        "clientKey": clientKey,
        "task": {
            "type": "CloudFlareTaskS2",
            # 指定chrome120内核 
            "userAgent":指定内核 "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120126.0.0.0 Safari/537.36"
            "userAgent": "",
            "waitLoad": False,
            "websiteURL": url,
            "proxy": proxy
        }
    }
    url = "https://api.yescaptcha.com/createTask"
    # url = "http://localhost:8000/createTask"
    response = requests.post(url, json=data).json()
    return response
  
# 获取结果
def get_task(task_id):
  url = "http://api.yescaptcha.com/getTaskResult"
  data = {
      # 填您自己的密钥
      "clientKey": clientKey,
      "taskId": task_id
  }
  response = requests.post(url, json=data).json()
  return response


# 完整的请求
def get_result(*args, **kwargs):
  uuid = create_task(*args, **kwargs)
  if not uuid or not uuid.get('taskId'):
    return uuid
  print("TaskID:", uuid)
  for i in range(30):
    time.sleep(3)
    result = get_task(uuid.get('taskId'))
    if result.get('status') == 'processing':
        continue
    elif result.get('status') == 'ready':
        return result
    else:
        raise Exception(result)



if __name__ == '__main__':
    
    # 填您的密钥
    clientKey = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
    
    # 填您自己的代理，不要填本地的地址
    proxy = "http://JN3wWChA:Dsg7ckfv@176.222.59.86:64048"
    proxies = {
        'http': proxy, 
        'https': proxy,
    }
    
    # 要访问的网址
    # url = "https://apkpure.com/"
    url = "https://billetterie.psg.fr/"


    # 正常情况是这样的：使用普通requests请求
    # import requests
    # 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)[0])
    # >>> 请求响应： 403
    # >>> 网页标题： <title>Attention Required! | Cloudflare</title>


    # 使用 curl_cffi.requests请求
    # from curl_cffi import requests
    # response = requests.get(url, proxies=proxies, impersonate="chrome110")
    # print("请求响应：", response.status_code)
    # print("网页标题：", re.search(r"<title>(.*?)</title>", response.text)[0])
    # >>> 如果使用curl_cffi就可以正常请求，说明并没有开启严格的5s盾
    # >>> 请求响应： 403
    # >>> 网页标题： <title>Just a moment...</title>


    # 使用接口返回的值来请求
    # 创建任务
    task = get_result(url, proxy=proxy)
    if not task.get("solution"):
        print("任务失败", task)
        exit()
    
    # 获取结果
    solution = task.get("solution")
    headers = solution.get("request_headers")
    headers.update(solution.get("headers"))
    print("Headers", headers)
    cookies = solution.get("cookies")
    print("Cookies：", cookies)
    
    from curl_cffi import requests
    # 这里也配套指定impersonate="chrome120"
    response = requests.get(url, headers=headers, cookies=cookies, proxies=proxies, impersonate="chrome120")
    print("请求响应：", response.status_code)
    print("网页标题：", re.search(r"<title>(.*?)</title>", response.text)[0])
版本比较

旧版本 32

新版本 33

密钥
