步骤

• 获取网页文本
• 将网页文本中所需内容存入列表
• 打印列表
  注意
• BeautifulSoup类中string与text的区别：在标签的子标签中有不止一个标签含有字符串时，string会返回none，text可以以字符串形式返回所有标签
• 获取网页文本框架：别忘了判断状态
• 遍历子标签时需过滤掉字符串类型

import requests
from bs4 import BeautifulSoup
import bs4

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


def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:
        # filter strings, preserve tags
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].text, tds[1].text.split(' ')[1], tds[4].text])


def printUnivList(ulist, num):
'''
# 排版：用中文空格替代西文字符
tplt = "{0:^10}\t{1:^{3}10}\t{2:^10}"
print(tplt.format("排名", "学校", "总分", chr(12288))
    for i in range(num):
        u = ulist[i]
        print(tplt.format(u[0].strip(), u[1].strip(), u[2].strip(), chr(12288)))
'''
    print("{:^10}\t{:^30}\t{:^10}".format("排名", "学校", "总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^30}\t{:^10}".format(u[0].strip(), u[1].strip(), u[2].strip()))


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


main()