爬虫入门，中国大学排名

此爬虫本人初学所写，仅能实现较少功能

ps:需要使用到beautifulsoup, requests库

安装方法：pip install beautifulsoup4

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")                   #利用beautifulsoup煲粥
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')                                        #截取<td>标签内的内容
            ulist.append([tds[0].string, tds[1].string, tds[3].string])
    pass

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 main():
    uninfo =[]
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html'
    html = getHTmLText(url)
    fillUnivList(uninfo, html)
    printUnivList(uninfo, 100)

main()

打印时使用了chr(12288)进行了中文对齐，美观一些