Python :中国大学排名爬取

# -*- coding: UTF-8 -*-

# http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html
#爬取中国大学排名

   #  1.从网页获取网页内容     getHTMLText（）
   #  2.提取网页内容中信息到合适的数据结构    fillUnivList()
   #  3.利用数据结构展示并输出结果   printUnivList()


import requests
import bs4
import sys
from bs4 import BeautifulSoup

reload(sys)
sys.setdefaultencoding('utf8')
def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        print r.status_code
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return " "

def fillUnivList(ulist,html):
    soup = BeautifulSoup(html,"html.parser")
    f                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       or tr in soup.find('tbody').children:
        if isinstance(tr,bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string,tds[1].string,tds[2].string])

def printUnivList(ulist,num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
        print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))


def run():
    uinfo = []
    url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)  #20所大学信息


run()