用Jupyter—Notebook爬取網頁資料例項14

用selenium庫爬取中華英才網校招資訊

看來都是姚老闆的

哦，正事差點忘了，上程式碼

#引入selenium、 pandas、openpyxl庫
from selenium import webdriver
import pandas as pd
import openpyxl
#定義儲存變數
zwgs=[]
xixl=[]
wssj=[]
#獲取網頁原始碼
for i in range(4):
    url='http://campus.chinahr.com/qz/p'+str(i)+'/'
    browser = webdriver.Chrome()
    browser.get(url)
#解析原始碼，提取所需資料資訊     
    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({'職位公司':zwgs,'薪資學歷':xixl,'網申時間':wssj})
data=pd.DataFrame({'職位公司':zwgs,'薪資學歷':xixl,'網申時間':wssj})
writer=pd.ExcelWriter('zhonghuayingcaiwang.xlsx')
data.to_excel(writer,'爬蟲資料')
writer.save()