定向网页爬虫

import requests
from bs4 import BeautifulSoup
import bs4

#爬取定向网页的内容
def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print('error')


def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children: #遍历tbody下的子标签
        if isinstance(tr, bs4.element.Tag): #是标签类型，非字符串
            tds = tr('td') #简写，输出列表
            ulist.append([tds[0].string, tds[1].string, tds[2].string])


def printUnivList(ulist, num):
    tplt = "{0:^10}	{1:{3}^10}	{2:^10}" #采用宽度不够，中文空格填充，保证中文对齐
    print(tplt.format("排名","学校名称","省份", 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.com/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20)

main()