软科中国最好大学排名2016网页中的排名信息（网址：http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html）

import requests
from bs4 import BeautifulSoup
import bs4

def getHTMLText(url):
    try:
        r = requests.get(url)
        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].string, tds[1].string, tds[3].string])
    pass

def printUnivList(ulist, num):
    # print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
    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)))
        # 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) # 20 univ

main()

最终的效果如下：

原文链接:https://blog.csdn.net/weixin_43969654/article/details/106439550