大学排名定向爬虫

import requests
import bs4
from bs4 import BeautifulSoup
def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        #print(r.text)
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print('发生错误')
        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].next_element,tds[1].string,tds[2].string])

def printUnivlList(ulist,num):
    #转化成中文空格
    print('{0:^10}	{1:{3}^10}	{2:^10}'.format('排名','学校','城市',chr(12288)))
    for i in range(num):
        u = ulist[i]
        print('{0:^10}	{1:{3}^10}	{2:^10}'.format(u[0],u[1],u[2],chr(12288)))
        #print(u)
    print('Suc' + str(num))

def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2017.html'
    getHTMLText(url)
    html = getHTMLText(url)
    fillunivList(uinfo,html)
    printUnivlList(uinfo,80)#only 20 schools
main()