BossXX 岗位信息简单自动化抓取

import requests from bs4 import BeautifulSoup from selenium import webdriver import csv def paQufun(a): f = open('./data/' + a + '.csv', mode='a', encoding='utf-8', newline='') data = csv.DictWriter(f, fieldnames=['招聘职业', '地区', '公司', '薪资', '工作经验要求', '学历要求', '工作介绍', '公司福利', '详情页']) data.writeheader() # 实例化浏览器 driver = webdriver.Chrome() # driver.get('https://sou.zhaopin.com/?jl=763&kw=%E5%89%8D%E7%AB%AF') ''' city接城市后编码 business接区编码，可不加 ''' driver.get('https://www.zhipin.com/web/geek/job?query=&city=101270100&areaBusiness=510108') # 隐式等待 driver.implicitly_wait(50) find = driver.find_element('css selector', ' .search-input-box .input') driver.find_element('css selector', ' .search-input-box .input').send_keys(a) # 点击搜索 driver.implicitly_wait(50) driver.find_element('css selector', '.search-btn').click() # css选择器直接定位元素 lists = driver.find_elements('css selector', '.search-job-result li.job-card-wrapper') for li in lists: job = li.find_element('css selector', ' .job-name').text area = li.find_element('css selector', ' .job-area').text company = li.find_element('css selector', ' .company-name').text salary = li.find_element('css selector', ' .salary').text yao = li.find_element('css selector', ' .job-info.clearfix .tag-list').text lines = yao.split("\n") line1 = lines[0] line2 = lines[1] jie = li.find_element('css selector', ' .job-card-footer.clearfix .info-desc').text fuLi = li.find_element('css selector', ' .job-card-footer.clearfix .tag-list').text href = li.find_element('css selector', ' .job-card-left').get_attribute('href') dit = { '招聘职业': job, '地区': area, '公司': company, '薪资': salary, '工作经验要求': line1, '学历要求': line2, '工作介绍': jie, '公司福利': fuLi, '详情页': href, } data.writerow(dit) print(job, area, company) print(salary, line1, line2, jie, fuLi, href) print('\n')