2020风月最新python爬中国大学排名 贺院

import  requests
from bs4 import  BeautifulSoup
import bs4
allUniv=[] #全部大学的信息
def findtd(soup): #获取信息
    for tr in soup.find('tbody').children: #查找tbody的全部子结点即是tr标签
        if isinstance(tr,bs4.element.Tag): #排除不是tag标签的
            tdall=tr.find_all('td')
            a=tdall[1].find('a').string.strip() #d大学名字
            b=tdall[0].contents[0].strip() #排名
            c = tdall[2].contents[0].strip() #省份
            d = tdall[3].contents[0].strip() #类型
            f = tdall[4].contents[0].strip() # 总分
            e = tdall[5].contents[0].strip() #办学层次
            allUniv.append([b,a,c,d,f,e]) #一个学校的信息 存入总信息 列表的一个元素即一个学校的信息
'''
def printallUn(num):
    print("{:^4}{:^10}{:^5}{:^6}{:^8}{:^10}".format("排名","学校名称","省市","类型","总分","办学层次"))
    for i in range(num):
        u=allUniv[i]#单个学校的信息
        print("{:^4}{:^10}{:^5}{:^6}{:^8}{:^10}".format(u[0],u[1],u[2],u[3],u[4],u[5]))
'''

def printallUn(num): #格式化输出
        print("{0:^10}\t{1:^10}\t{2:^10}\t{3:^10}\t{4:^10}\t{5:^10}".format("排名","学校名称","省市","类型","总分","办学层次", chr(12288)))
        for i in range(num):
            info=allUniv[i]
            print("{0:^10}\t{1:^10}\t{2:^10}\t{3:^10}\t{4:^10}\t{5:^10}".format(info[0], info[1], info[2],info[3],info[4],info[5], chr(12288)))


def getHtmlText(url): #请求网页 并获取源代码
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding='utf-8'
        return r.text
    except:
        return ''

def main(num): #主函数
    url='https://www.shanghairanking.cn/rankings/bcur/202011'
    html=getHtmlText(url)
    soup=BeautifulSoup(html,'html.parser')
    findtd(soup)
    printallUn(num)
main(10)