用快代理换Ip爬取boss直聘招聘信息

import requests
import random
from prettytable import PrettyTable
tb = PrettyTable()
tb.field_names = ['区域','详情页链接','领导','经营领域','公司名','招聘人数','学历要求','工作经验要求','职位名称','期望薪资','技能要求','福利']

headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
    "Cookie":"lastCity=101240200; wd_guid=48d68397-7249-4f0f-bb46-d46109d91c45; historyState=state; _bl_uid=smlkOr6koyqh9y7eI6q3qhqi9FRb; __zp_seo_uuid__=adebcacd-2035-4cf3-9f73-7a36cbfa3926; __g=-; __l=r=https%3A%2F%2Fcn.bing.com%2F&l=%2Fwww.zhipin.com%2Fchengshi%2Fc101240200%2F&s=1&g=&s=3&friend_source=0; Hm_lvt_194df3105ad7148dcf2b98a91b5e727a=1709172158; __fid=0ffb8b698ee87b386c5ed3d71d3e37f0; Hm_lpvt_194df3105ad7148dcf2b98a91b5e727a=1709180059; __c=1709172158; __a=50791990.1704706028.1705900640.1709172158.23.4.16.23; __zp_stoken__=2e9cfPjrDpcK5XcK7RTQNCREVCkAtNzoxdkU%2BLjk8QT46Qz4%2FPjo7HD0uVi8%2Fw51iw4s1PCs%2BOjo8OEA6Qz8bPkbFgcK5Nz0wYyhDw5dmw5JeMcK%2BBzsNOMK%2BBysNwoBDKAvCuz03Q0JZwro3w4UKwr49w4ETw4U5w4M3O0I5MzsKZBBaOztPSloJTVtJYF9REFJWUC1CQDc%2BdsO6w7kxPBYHEBQSFgcQFBIQDRYREw8OFRETFAkSFhAyQ8Kewr3EgnhSxK3EgsSdwpxiwqbDhcKMwqjCn8KswrRswpXCsMO3wrLCmlTCssKGwohIwr5ywqlaYmRSY3J%2FVXlTw4TDhkrCu2xVwrpxXmIPEWTCgWIJOxM1JsOI"
}
for i in range(1,5):
    api_url = "https://dps.kdlapi.com/api/getdps/?secret_id=o8lhq88am27nzd51rego&num=5&signature=jp967bz15n8ensgnpksu6fbvfahzcfuh&pt=1&format=json&sep=1"
    proxy_ip = requests.get(api_url).json()['data']['proxy_list']

    # 用户名密码认证(私密代理/独享代理)

    username = "d3400384165"
    password = "f5s8g9pk"
    proxies = {
        "http": "http://%(user)s:%(pwd)s@%(proxy)s/" % {'user': username, 'pwd': password,
                                                        'proxy': random.choice(proxy_ip)},
        "https": "http://%(user)s:%(pwd)s@%(proxy)s/" % {'user': username, 'pwd': password,
                                                         'proxy': random.choice(proxy_ip)}
    }
    i = i+1
    boss_url = f"https://www.zhipin.com/wapi/zpgeek/search/joblist.json?scene=1&query=Python&city=100010000&experience=&payType=&partTime=&degree=&industry=&scale=&stage=&position=&jobType=&salary=&multiBusinessDistrict=&multiSubway=&page={i}&pageSize=30"
    json_data = requests.get(url=boss_url，headers=headers).json()['zpData']['jobList']
    for data in json_data:
        area = data['areaDistrict'] # 区域
        link = data['bossAvatar']   # 详情页链接
        boss_name = data['bossName'] # 领导
        brandIndustry = data['brandIndustry']  # 领域
        brandName = data['brandName']  #公司名
        brandScaleName = data['brandScaleName'] # 招聘人数
        jobDegree = data['jobDegree']  #学历要求
        jobExperience = data['jobExperience']  #工作经验要求
        jobName = data['jobName']  #职位名称
        salaryDesc = data['salaryDesc']  # 期望薪资
        skills = data['skills']  # 技能要求
        welfareList = data['welfareList'] #福利
        tb.add_row([area,link,boss_name,brandIndustry,brandName,brandScaleName,jobDegree,jobExperience,jobName,salaryDesc,skills,welfareList])
print(tb)

总结：在这个案例中，它的cookie是频繁变化的， 不加cookie，访问不到数据，加了cookie，时间长了之后会失效。所以这又回到了逆向的方面，它的cookie是如何生成的，我该如何生成cookie？

尝试了用快代理免费的代理池，用于更换ip，以防止封ip类型的反扒手段 。

结果展现：

令我奇怪的是在cookie时效呢，加了proxies=proxies反而会报错，不知道为啥