2024中国大学排名爬取

在pycharm中编写如下代码：

import requests
from bs4 import BeautifulSoup
import bs4
import re
def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

def remove_spaces_re1(string):
    return re.sub(r"\s+","",string)

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')
            name = tds[1]('div')[2]('a')[0].string
            rank = (str)(tds[0].string)
            score = (str)(tds[4].string)
            ulist.append([remove_spaces_re1(rank),remove_spaces_re1(name),remove_spaces_re1(score)])


def printUnivList(ulist,num):
    print("{:^20}\t{:^16}\t{:^20}".format("排名","学校名称","总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^20}\t{:^16}\t{:^20}".format(u[0],u[1],u[2]))


if __name__ == '__main__':
    uinfo = []
    url = "https://www.shanghairanking.cn/rankings/bcur/2024"
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)

运行结果：

优化：
由于打印了中文，系统默认采用西文字符填充，我们可以自己采用中文字符填充，这里采用中文字符的空格填充chr(12288)

修改printUnivList函数

def printUnivList(ulist,num):
    tplt = "{0:^20}\t{1:{3}^20}\t{2:^20}"
    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)))

运行结果：