中国大学排名定向爬虫

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:
        return ""
def fillUnivList(uList, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find(‘tbody‘).children:  # 遍历tbody子节点列表
        if isinstance(tr, bs4.element.Tag): # 判断两个类型是否相同
            tds = tr(‘td‘)  # 等价于tds = tr.find_all(‘td‘),返回一个列表
            uList.append([tds[0].string, tds[1].string, tds[3].string])
def printUnivList(uList, num):
    tplt = "{0:^10}\t{1:{3}^8}\t{2:10}"   # 解决中文字符对齐问题
    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)))
def main():
    uinfo = []
    url = ‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html‘
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 10)
main()