招聘_boss

from selenium import webdriver
from time import sleep
from selenium.webdriver.common.by import By

# 实现反监测(三不)
from selenium.webdriver import ChromeOptions
option = ChromeOptions()
option.add_experimental_option('excludeSwitches',['enable-automation'])

# 实例化一个浏览器对象
bro = webdriver.Chrome(chrome_options=option)
bro.maximize_window()
sleep(10)

for page in range(1,4):
    # 网址
    url = f'https://www.zhipin.com/c101010100/?query=%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90%E5%B8%88&page={page}&ka=page-{page}'
    bro.get(url)
    sleep(10)

    #模拟页面下拉
    bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
    sleep(4)
    if page ==1:
        li_list = bro.find_elements(By.XPATH,'//*[@id="main"]/div/div[2]/ul/li')
        '''
        //*[@id="main"]/div/div[3]/ul/li[1]  个人热点
        //*[@id="main"]/div/div[2]/ul/li[1]  公司网络
        '''
        # print(li_list)

        for li in li_list:
            information = li.text.split('\n')
            print(information)

            #岗位信息
            job = information[0]

            # 位置信息
            address = information[1]

            #薪水
            sal = information[2]

            # 年限
            year = information[3][:(len(information[3])-2)]
            # 学历
            edu = information[3][(len(information[3])-2):]


            #公司名称
            company = information[5]

            file = open('boss招聘数据分析师.csv', 'a', encoding='gb18030')
            file.write(job+','+address+','+sal+','+year+','+edu+','+company)
            file.write('\n')
            file.close()
    else:
        li_list = bro.find_elements(By.XPATH,'//*[@id="main"]/div/div[2]/ul/li')
        # print(li_list)

        for li in li_list:
            information = li.text.split('\n')
            # print(information)

            #岗位信息
            job = information[0]

            # 位置信息
            address = information[1]

            #薪水
            sal = information[2]

            # 年限
            year = information[3][:(len(information[3])-2)]
            # 学历
            edu = information[3][(len(information[3])-2):]

            #公司名称
            company = information[5]
            file = open('boss招聘数据分析师.csv', 'a', encoding='gb18030')
            file.write(job+','+address+','+sal+','+year+','+edu+','+company)
            file.write('\n')
            file.close()

bro.close()