python3.x中的中国大学排行榜简单爬取

#使用python工具：pycharm
#使用库：requests 、bs4

代码如下(对比2016年与2017年的区别）：
1——中国大学排名2016 (不同网站的解析器格式有所不同）

import  requests
from bs4 import BeautifulSoup
import bs4

def getUniv(url):
    try:
        demo = requests.get(url,timeout = 30)
        demo.raise_for_status()
        demo.encoding = demo.apparent_encoding
        return demo.text
    except:
        print('getUniv erroor')

def fillUnivList(list,html):
    try:
        soup = BeautifulSoup(html,'html.parser')
        for tr in soup.find('tbody').children:
            if isinstance(tr,bs4.element.Tag):
                tds = tr('td')
                list.append([tds[0].string,tds[1].string,tds[2].string])
    except:
        print('fillUnivList error')

def printUnivList(list,num):
    try:
        print('{0:^5}\t{1:{3}^14}\t{2:^9}'.format('排名','校名','地址',chr(12288)))
        for i in range(num):
            ulist = list[i]
            print('{0:^6}\t{1:{3}^15}\t{2:^7}'.format(ulist[0],ulist[1],ulist[2],chr(12288)))
    except:
        print('printUnivList error')


def main():
    list = []
    url ='http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html'
    html = getUniv(url)
    fillUnivList(list,html)
    printUnivList(list,20)

main()

2——中国大学排名2017
import  requests
from bs4 import BeautifulSoup
import bs4

def getUniv(url):
    try:
        demo = requests.get(url,timeout = 30)
        demo.raise_for_status()
        demo.encoding = demo.apparent_encoding
        return demo.text
    except:
        print('getUniv erroor')

def fillUnivList(list,html):
    try:
        soup = BeautifulSoup(html,'html.parser')  #如果该处使用 'lxml'代替‘html,parser',则下面的[tds[0].contents[0].string,可以使用[tds[0].string
        for tr in soup.find('tbody').children:
            if isinstance(tr,bs4.element.Tag):
                tds = tr('td')
                list.append([tds[0].contents[0].string,tds[1].string,tds[2].string])
    except:
        print('fillUnivList error')

def printUnivList(list,num):
    print('{0:^5}\t{1:{3}^14}\t{2:^9}'.format('排名','校名','地址',chr(12288)))
    for i in range(num):
        ulist = list[i]
        print('{0:^6}\t{1:{3}^15}\t{2:^7}'.format(ulist[0],ulist[1],ulist[2],chr(12288)))


def main():
    list = []
    url ='http://www.zuihaodaxue.com/zuihaodaxuepaiming2017.html'
    html = getUniv(url)
    fillUnivList(list,html)
    printUnivList(list,10)

main()