import csv
import requests
from bs4 import BeautifulSoup
#请求头
headers={'User-Agent':"Opera/9.80(WindowsNT6.1;U;en)Presto/2.8.131Version/11.11"}
def getInfo(url):
#获取页面代码
html=requests.get(url,headers=headers).content.decode('utf-8','ignore')
soup=BeautifulSoup(html,'lxml')
#获取表头
theadList=[]
thead=soup.select('thead th')
for head in thead:
theadList.append(head.text)
print(theadList)
with open('ranking.csv', 'w') as f:
writer = csv.writer(f)
writer.writerow(theadList)
#获取学校列表
schoolList=soup.select('tr.alt')
for school in schoolList:
#排名
ranking=school.select('td:nth-of-type(1)')[0].text
#学校名称
schoolName=school.select('td:nth-of-type(2)')[0].text
#省市
schoolAddress=school.select('td:nth-of-type(3)')[0].text
#社会捐赠收入（千元）
socialIncome = school.select('td:nth-of-type(4)')[0].text
#综合排名
compreRanking=school.select('td:nth-of-type(5)')[0].text
if len(compreRanking)==0:
compreRanking='暂无数据'
data=[ranking,schoolName,schoolAddress,socialIncome,compreRanking]
print(data)
#写入csv
with open('ranking.csv','a+') as f:
writer=csv.writer(f)
writer.writerow(data)
if __name__ == '__main__':
url='http://www.zuihaodaxue.com/shehuishengyupaiming2018.html'
getInfo(url)
