import requests
from bs4 import BeautifulSoup
import bs4
#网页请求
def getHTMLText(url):
try:
r = requests.get(url,timeout = 60)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ""
#对获取的网页源码进行解析与信息提取
def fillUnivList(ulist,html):
soup = BeautifulSoup(html,'html.parser')
for tr in soup.find('tbody').children:
if isinstance(tr,bs4.element.Tag):
tds = tr('td')
ulist.append([tds[0].string,tds[1].string,tds[4].string])
#对提取的信息进行格式化打印
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)))
def main():
uinfo = []
url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2020.html"
html = getHTMLText(url)
fillUnivList(uinfo,html)
printUnivList(uinfo,20)
main()
08-08
376
![](https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png)
08-06
298
![](https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png)
08-09
874
![](https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png)