爬虫爬取大学排名示例

# -*- coding: utf-8 -*-
"""
Created on Wed Nov  7 19:33:21 2018

#步骤1：从网络上获取大学排名网页内容
 getHTMLText
#步骤2： 提取网页内容中信息到合适的数据结构
 fillUnivList()
#步骤3:利用数据结构展示并输出结果
  printUnivList()
"""

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')
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag): #过滤掉非element.Tag类型的数据
            tds = tr('td')  #存td标签
            ulist.append([tds[0].string, tds[1].string, tds[2].string])

def printUnivList(ulist, num):
    "^居中对齐，^10为宽度设定，中文字符不够时，默认用英文字符填充，中文空格char(12288)"
    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名","得分"))
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format("排名","学校名","得分",chr(12288)))
#    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名","得分"))
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))
        
    print("Suc" + str(num))

def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20)

if '__name__'=='__main__':
    main()