python_爬虫大学排行的代码

import requests
from bs4 import BeautifulSoup
import bs4
#1爬取网页
def GetHtml(url):
try:
r=requests.get(url,timeout=30)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
return "异常"
#2提取内容、
def  FullList(html,ulist):
soup= BeautifulSoup(html,'html.parser')
for temp in soup.find('tbody').children:
if isinstance(temp,bs4.element.Tag):
tds=temp('td')
ulist.append([tds[0].string,tds[1].string,tds[2].string])
def printUnivlist(ulist,num):
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
print(tplt.format("排名", "学校名称", "总分", chr(12288)))
for i in range(num):
u = ulist[i]
print(tplt.format(u[0], u[1], u[2], chr(12288)))

#3内容的输出
infos=[]
url='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
html=GetHtml(url)
FullList(html,infos)
printUnivlist(infos,20)