python爬虫 学习 中国大学排名显示及保存文件 DAY3

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 "爬取异常"
 
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[3].string])
 
def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    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 wtxt(ulist,num):
    f = open(r"C:\Users\lenovo\Desktop\中国大学排名.txt",'w+')
    ls = ['排名','学校名称','总分']
    s = "\t\t".join(ls)
    f.write(s+'\n')
    for i in range(num):
        line = ulist[i]
        line = "\t\t".join(line)
        f.write(line+'\n')
    f.close()
        
        
     
def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs
    wtxt(uinfo,20)
main()