中国大学排名数据分析

 

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)
            tds=tr('td')
            ulist.append([tds[0].string,tds[1].string,tds[3].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(u[0],u[1],u[2]))

def main():
    uinfo=[]
    url='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html'
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20) #排名前二十
main()

 

 

 

用python生成图像

import pandas as pd

import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
df=pd.read_excel(''1")
x=df['学校名称']
y=df['总分']
plt.bar(x,y,label='分数')
plt.xlabel('学校')
plt.ylabel('分数')
plt.legend()
plt.show()