python爬取大学排名

import requests
from bs4 import BeautifulSoup as bf
import bs4

def getHTMLText(url):
try:

    r = requests.get(url,timeout=30)
    r.raise_for_status()
    r.encoding = r.apparent_encoding

print(r.text)

    return r.text
except:
    print('失败')

def fillUnivList(ulist,html):
soup = bf(html,“html.parser”)

print(soup.prettify())

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[3].string])

print(ulist)

def printunivlist(ulist,num):

print(ulist)

print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
for i in range(num):
    u = ulist[i]
    print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))

def main():
uinfo = []
url =‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html’
html = getHTMLText(url)
fillUnivList(uinfo,html)
printunivlist(uinfo,20)
main()

你可能感兴趣的:(python)