mmz批量多页抓取数据-AES.CBC算法-爬虫

news2024/9/20 0:53:39

目标：mmz多页下载

方法：加一个for循环实现多页的下载

问题：浏览器传输服务器时对页码参数做了加密处理

解决方法：

1、判断加密算法模式（mmz是AES-CBC算法）

2、找到加密的key和iv

代码：

import json
import time

import requests
import base64
from Crypto.Cipher import AES
from Crypto.Util.Padding import pad,unpad

for page in range(2, 10):
    # ==============================================第一部分（模仿浏览器对页码加密传输服务器）=================================
    # 获取到mmz网站加密的明文数据
    data = {"Type": 0, "page": page, "expire": 1710571993849}
    # dic转化为json字符串进行处理
    data = json.dumps(data)
    # print(type(data))
    fill_btext = pad(data.encode(), 16)
    # print(fill_btext)

    # 解析mmz网站js拿到kv,浏览器向服务器传送加密的kv
    key = '55b3b62613aef1a0'.encode()
    vi = key
    encry = AES.new(key, AES.MODE_CBC, vi)
    # AES加密
    encry_data = encry.encrypt(fill_btext)

    # 加密 b64
    b64encode_data = base64.b64encode(encry_data)
    # print(b64encode.decode())
    # ============================================第二部分（拿到加密的参数获取服务器返回的数据并解密）=================================
    # 解密服务器返回的数据

    cookies = {
        'PHPSESSID': '48nu182kdlsmgfo2g7hl6eufsa',
        'Hm_lvt_6cd598ca665714ffcd8aca3aafc5e0dc': '1710568549',
        'SECKEY_ABVK': 'FUnr+pnCS/p1Ou/WiS6a82jLBmKcwlQfvALD/bEpSYS0EV42eXkFNYpCmcekNiiKvyrlcEHfDw6QLw7GSqcv/w%3D%3D',
        'Hm_lpvt_6cd598ca665714ffcd8aca3aafc5e0dc': '1710568575',
        'BMAP_SECKEY': 'FUnr-pnCS_p1Ou_WiS6a82jLBmKcwlQfvALD_bEpSYRjgInAaoK-vELl57QFAxX-y1kv64ZfrWIegR6xAqZk5YPrHMNgpor4__VOFQ2YBt9ZLJyD0Ru3kQ8TLNDX9tgT2rE6la_DNO7NooPoKY8lg-7nkrw7RqULcxikq6qpjt72ToZ7LhtjeWs5kU5TcRy2ruVzAKFKBpjmyUlPmKeBwJM_HQkgSUF_-wJjonbLE8U',
    }
    headers = {
        'Accept': '*/*',
        'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
        'Connection': 'keep-alive',
        'Content-Type': 'application/json; charset=UTF-8',
        # 'Cookie': 'PHPSESSID=48nu182kdlsmgfo2g7hl6eufsa; Hm_lvt_6cd598ca665714ffcd8aca3aafc5e0dc=1710568549; SECKEY_ABVK=FUnr+pnCS/p1Ou/WiS6a82jLBmKcwlQfvALD/bEpSYS0EV42eXkFNYpCmcekNiiKvyrlcEHfDw6QLw7GSqcv/w%3D%3D; Hm_lpvt_6cd598ca665714ffcd8aca3aafc5e0dc=1710568575; BMAP_SECKEY=FUnr-pnCS_p1Ou_WiS6a82jLBmKcwlQfvALD_bEpSYRjgInAaoK-vELl57QFAxX-y1kv64ZfrWIegR6xAqZk5YPrHMNgpor4__VOFQ2YBt9ZLJyD0Ru3kQ8TLNDX9tgT2rE6la_DNO7NooPoKY8lg-7nkrw7RqULcxikq6qpjt72ToZ7LhtjeWs5kU5TcRy2ruVzAKFKBpjmyUlPmKeBwJM_HQkgSUF_-wJjonbLE8U',
        'Origin': 'https://www.maomaozu.com',
        'Referer': 'https://www.maomaozu.com/',
        'Sec-Fetch-Dest': 'empty',
        'Sec-Fetch-Mode': 'cors',
        'Sec-Fetch-Site': 'same-origin',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36 Edg/122.0.0.0',
        'sec-ch-ua': '"Chromium";v="122", "Not(A:Brand";v="24", "Microsoft Edge";v="122"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
    }
    response = requests.post('https://www.maomaozu.com/index/build.json', cookies=cookies, headers=headers,
                             data=b64encode_data)
    res = response.text

    # 解密 b64
    b64decode = base64.b64decode(res)

    # 解析mmz网站js拿到kv，服务器向浏览器传送数据的解密kv
    key = '0a1fea31626b3b55'.encode()
    vi = key
    cry = AES.new(key, AES.MODE_CBC, vi)

    # print(cry.decrypt(b64decode).decode())
    # unpad去除填充
    mmz_text = unpad(cry.decrypt(b64decode),16).decode()
    print(mmz_text)
    time.sleep(1)

浏览器和服务器之间关系示意图：