python学习之BeautifulSoup解析网页

from bs4 import BeautifulSoup
import requests
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 "产生异常"

def getSchoolList(htmlStr, ulist):
    soup = BeautifulSoup(htmlStr, "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[3].string])
            
def printSchoolList(schList, num):
    print("{0:^10}\t{1:{3}^10}\t{2:^10}".format("排名","学校名称","总分", chr(12288)))
    for i in range(num):
        u = schList[i]
        print("{0:^10}\t{1:{3}^10}\t{2:^10}".format(u[0], u[1], u[2], chr(12288)))


def main():
    urlstr = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html"
    schList = []
    htmlStr = getHtmlText(urlstr)
    getSchoolList(htmlStr, schList)
    printSchoolList(schList, 20)

main()