python爬取最好大学网排名实例代码

import bs4
import requests
from bs4 import BeautifulSoup

def getHIMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return ""

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].text.strip(),tds[1].text.split()[0],tds[4].text.strip()])


def printUnivList(ulist,num):
    print(f'{"排名":^10}\t{"学校名称":10}\t{"总分":^10}')
    for t in range(num):
        i=ulist[t]
        print(f'{i[0]:^10}\t{i[1]:10}\t{i[2]:^10}')
    print(f'suc\t{num}')

def main():
    uinfo=[]
    url='https://www.shanghairanking.cn/rankings/bcur/2020'
    html=getHIMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)

main()