最好大学网python爬虫代码

#爬虫代码由北京理工课程内容课程所书写
#最好大学网无robots协议
#2017/4/28函数过于简单，不再赘述
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:
        print('get wrong!')

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].string,tds[1].string,tds[2].string,tds[3].string])

def PrintUnivlist(ulist,num):
    tclt = '{0:^10}\t{1:{4}^10}\t{2:^10}\t{3:^10}'
    print(tclt.format('数字','学校名称','省份','分数',chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(tclt.format(u[0], u[1], u[2],u[3],chr(12288)))

def themain():
    uinfo = []
    url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html"
    html = getHTMLText(url)
    fillunivlist(uinfo,html)
    PrintUnivlist(uinfo,30)

if __name__ == '__main__':
    themain()