import requests
from bs4 import BeautifulSoup
import bs4                                                       #Tag类型判断是需要用到这里的库



def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ‘产生异常‘

def fillUnivList(ulist, html):
    soup = BeautifulSoup(html,‘html.parser‘)
    for tr in soup.find(‘tbody‘).children:                        #所有的排名信息包含在这个tbody的标签中
        if isinstance(tr, bs4.element.Tag):                       #每个大学的排名信息单独一个独立的tr标签中，它是tbody标签的子标签
            tds = tr(‘td‘)
            ulist.append([tds[0].string, tds[1].string, tds[3].string])

def printUnivList(ulist, num):
    tplt=‘{0:^10}\t{1:{3}^10}\t{2:^10}‘                           #{3},代表用format的第四个变量填充没用完的位置 即chr(12288)
    print(tplt.format(‘排名‘,‘学校名称‘,‘分数‘,chr(12288)))
    for i in range(num):                                          #ulist是一个二维数组
        u = ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))


def main():
    uinfo = []
    url = ‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html‘
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    num = 20
    printUnivList(uinfo, num)

main()