用selenium库爬取中华英才网校招信息
看来都是姚老板的
哦,正事差点忘了,上代码
#引入selenium、 pandas、openpyxl库
from selenium import webdriver
import pandas as pd
import openpyxl
#定义存储变量
zwgs=[]
xixl=[]
wssj=[]
#获取网页源代码
for i in range(4):
url='http://campus.chinahr.com/qz/p'+str(i)+'/'
browser = webdriver.Chrome()
browser.get(url)
#解析源代码,提取所需数据信息
for i in browser.find_elements_by_class_name('item'):
zwgs.append(i.find_elements_by_class_name('top-area')[0].text.replace('\n',''))
xixl.append(i.find_elements_by_class_name('center-area')[0].find_elements_by_class_name('job-info')[0].text.replace('\n',''))
wssj.append(i.find_elements_by_class_name('bottom-area')[0].text.replace('\n',''))
pd.DataFrame({'职位公司':zwgs,'薪资学历':xixl,'网申时间':wssj})
data=pd.DataFrame({'职位公司':zwgs,'薪资学历':xixl,'网申时间':wssj})
writer=pd.ExcelWriter('zhonghuayingcaiwang.xlsx')
data.to_excel(writer,'爬虫数据')
writer.save()