爬取boss直聘招聘信息带有bug

import requests,time,json,csv
import pymysql
from urllib.parse import urlencode
from bs4 import BeautifulSoup

list_data = []
csv_data=[]
# 发送请求页面并存下数据
def spider_boss(url, data,):
    req = requests.post(url, headers=headers, data=data, timeout=5,).text
    list = json.loads(req)
    if 'jobList' not in list['zpData'].keys():
        print('cookie过期请更换...')
        exit()
    try:
        for i in list['zpData']['jobList']:
            title = i['jobName']  # 职业信息
            jobDegree = i['jobDegree']  # 学历
            brandName = i['brandName']  # 公司名称
            areaDistrict = i['areaDistrict'] + i['businessDistrict']  # 地区加地址
            salaryDesc = i['salaryDesc']  # 工资
            jobExperience = i['jobExperience']  # 经验
            urladdr = 'https://www.zhipin.com/job_detail/' + i['encryptJobId'] + '.html'  # url地址
            skills = ','.join(i['skills'])  # 工作内容
            welfareList = ','.join(i['welfareList'])  # 公司福利
            mag = {
                'title': title,
                'jobDegree': jobDegree,
                'brandName': brandName,
                'areaDistrict': areaDistrict,
                'salaryDesc': salaryDesc,
                'jobExperience': jobExperience,
                'urladdr': urladdr,
                'skills': skills,
                'welfareList': welfareList,
            }
            list_data.append(mag)
        print(list_data)
        return list_data
    except:
        print('请检查cookies是否过期...')
        time.sleep(2)
        spider_boss(url, data)


#储存mysql数据库
def server(data):
    #连接数据库
    con = pymysql.connect(host='127.0.0.1', user='root', password='root', db='boss', charset='utf8')
    cursor = con.cursor()
    for conter in data:
        try:
            sql = "INSERT INTO heji(title,jobDegree,brandName,areaDistrict,salaryDesc,jobExperience,urladdr,skills,welfareList) VALUES('%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s')" % (
                conter['title'], conter['jobDegree'], conter['brandName'], conter['areaDistrict'], conter['salaryDesc'],
                conter['jobExperience'], conter['urladdr'], conter['skills'], conter['welfareList'])
            cursor.execute(sql)
            con.commit()
        except:
            con.rollback()
            print('请检查sql语句..')
        print('数据库写入成功...')
    #完成后关闭数据库
    con.close()

def server_csv(data):
    #遍历数据，处理成存储数据
    for conter in data:
        csv_list = [conter['title'], conter['jobDegree'], conter['brandName'], conter['areaDistrict'],conter['salaryDesc'], conter['jobExperience'], conter['urladdr'], conter['skills'],conter['welfareList']]
        csv_data.append(csv_list)
    with open('求职信息.csv','w',encoding='utf-8',newline='') as f:
        writer=csv.writer(f)
        writer.writerow(['职业', '学历', '公司名称', '地区', '工资', '经验', 'url地址', '工作内容', '公司福利'])
        writer.writerows(csv_data)
        print('cvs表格写入成功..')

def strat(url,data):
    #开启抓取页面
    list_data = spider_boss(url,data)
    #储存mysql数据库
    server(list_data)
    # 存储csv表格
    server_csv(list_data)

if __name__ == '__main__':
    #目标网站url
    url = 'https://www.zhipin.com/wapi/zpgeek/recommend/job/list.json'
    #cookie更改 bug中，每次查询5次需要手动更换
    cookie='lastCity=101280100; __g=-; Hm_lvt_194df3105ad7148dcf2b98a91b5e727a=1620300454; wt2=DGYNTwimCoXqwtqG0OOhtIK-83huFIIq0ojwNVqE4S9zEJUvL9jIT_i-Bpp2Ywvg1uzq6xL9ISxkK3mWPiuo_wg~~; _bl_uid=OIkUzos5cUbttt2O0oLtxO6sOkh3; __fid=d60538005c9afb998b6d815b2f9a381b; Hm_lpvt_194df3105ad7148dcf2b98a91b5e727a=1620361396; __c=1620300454; __l=l=%2Fwww.zhipin.com%2Fweb%2Fgeek%2Frecommend%3Fka%3Dheader-username&s=3&friend_source=0&s=3&friend_source=0; __a=89029989.1620300454..1620300454.52.1.52.52; geek_zp_token=V1QNslFuz_21xqVtRvzR0bLyOw7j7TxS0~; __zp_stoken__=3ac4cMT5GbxZwTFwEO3t%2FMH9udkY6L2NQbWxKBllkYjB0HTBGc3NgeF5HHHdBIjZ5Wl0HUBF%2BBwYrLTU2IS9TBVItewtYLj5mezdvWQRBIwEfTklDWAB8FQ8uU11WRF5can4XbRstDmxcYAYW'
    #设置headers请求头信息
    headers = {
        "referer": "https://www.zhipin.com/web/geek/recommend?expectId=136314657&sortType=1&page=4&districtCode=0&cityCode=101280100",
        "cookie":cookie,
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36",
    }
    #批量遍历页面url
    for num in range(1,30):
        data = {
            "expectId": "136314657",
            "sortType": 1,
            "page": num,
            "salary": "",
            "payType": "",
            "degree": "",
            "experience": "",
            "stage": "",
            "scale": "",
            "districtCode": 0,
            "businessCode": "",
        }

        data = urlencode(data)
        strat(url,data)