GUI练习：疫情数据查询、动态统计图(数据太大，基于技术设计，加载需要时间，某些数据掉点，主要作为学习交流参考)。

此版本中的疫情下载方式只到11.20之前，更新的下载连接格式为:http://www.sy72.com/download/D_yiqing.asp?c=5&d=1&s=1,其中c=为国家代码，d=为下载格式，s不变，即可得到对应国家的历史疫情数据，最新好像还开放了接口可以直接得到数据。文件可能有错无法实现，但是主题思路是没问题的。

PS:历史疫情数据网址：http://www.sy72.com/world/world6.html (中国的数据是独立的，需要对页面数据进行爬取在写成xls文件)。

代码如下：

import requests
import xlwt
import xlrd
import re
import sys
import threading
import os
import PySimpleGUI as sg
from bs4 import BeautifulSoup
import matplotlib.pyplot as plt
import matplotlib
def url_text_get(url,code='utf-8'):#一个网页类容获取
    r=requests.get(url)
    kv={'User-angent':'Mozilla/5.0'}
    r.raise_for_status()
    r.encoding=code
    return r.text
def url_infor_get():#总人口链接信息提取
    start_url='https://www.phb123.com/city/renkou/rk_'
    r_url_lis=[]
    for i in range(1,13):
        r_url_lis.append(start_url+str(i)+'.html')
    return r_url_lis
def ayurl(html):#总疫情链接类容获取
    soup=BeautifulSoup(html,'html.parser')
    y_url_list_infor=list(list())
    lp=soup('ul')
    soup1=BeautifulSoup(str(lp[1]),'html.parser')
    l=soup1('a')
    i=0
    for link in soup1.find_all('a'):
        li=[]
        li.append(l[i].string)
        i=i+1
        li.append(link.get('href'))
        y_url_list_infor.append(li)
    return y_url_list_infor
def download(li,p_list):
    global apath
    root = "d:/python练习文档/全球历史数据"
    isExists = os.path.exists(root)
    if not isExists:
        os.makedirs(root)
    else:
        pass
    path = root +'/'+ li[0] + '.xls'
    apath=root
    url =li[1]
    r = requests.get(url)
    with open(path, 'wb') as t:
        t.write(r.content)
        t.close()
    try:
        d_xieru(p_list, path, li[0])
    except:
        pass
def down(li,p_list):
    day = lp(p_list)
    for i in li:
        t=threading.Thread(target=download,args=(i,p_list,))
        t.start()
    while threading.activeCount() !=1:
        pass
    return day
def yqlj():#历史疫情情况链接获取
    y_url_list_infor2=list(list())
    ul='http://www.sy72.com/xls/world'
    ul2='http://www.sy72.com/world/world417_25970.html'
    y_url_list_infor=ayurl(url_text_get(ul2))
    for i in range(0,len(y_url_list_infor)):
        ty=[]
        ty.append(y_url_list_infor[i][0])
        number=''.join(re.findall(r'[0-9]+',y_url_list_infor[i][1]))
        ty.append(ul+number+'.xls')
        y_url_list_infor2.append(ty)
    return y_url_list_infor2
def text_renkou_get(html,li):#一个人口数获取
    soup=BeautifulSoup(html,'html.parser')
    s=soup.find_all('tr')
    o=BeautifulSoup(str(s),'html.parser').find_all('td')
    for i in range(int(len(o)/5)):
        ls=[]
        ls.append(o[5*i+1].p.string)
        ls.append(o[5*i+2].string)
        li.append(ls)
def renkouhuode(ur_list):#总人口数获得
    global window
    layout = [[sg.Text('人口下载进度'),sg.Text('0.00%',key='2')],
              [sg.ProgressBar(len(ur_list), orientation='h', size=(20, 20), key='progressbar')],
              [sg.Cancel()]]
    window1= sg.Window('下载进度', layout)
    progress_bar = window1['progressbar']
    t_li=list(list())
    for i in range(len(ur_list)):
        url=ur_list[i]
        text_renkou_get(url_text_get(url),t_li)
        event, values = window1.read(timeout=20)
        if event == "Cancel":
            sys.exit(0)
        progress_bar.UpdateBar(i+ 1)
        window1.FindElement("2").Update(str("{:.2f}".format((i/len(ur_list)) * 100) + '%'))
    window1.close()
    # window.Element('2').Update(disabled=True)
    # window.Element('4').Update(disabled=True)
    window.Element('6').Update("***全球人口下载成功！***")
    event, values = window.read(timeout=100)
    f = xlwt.Workbook()
    sheet1 = f.add_sheet('class')
    for i in range(len(t_li)):
        sheet1.write(i + 1, 0, t_li[i][0])
        sheet1.write(i + 1, 1, t_li[i][1])
    f.save('全球国家人口数.xls')
    window.Element('6').Update(values.get('6')+"***全球人口保存路径为："+os.path.split(os.path.realpath(__file__))[0]+"***")
    return t_li
def tjs(x,y):#天数计算
    day=0
    if(x==1):
        day=y
    elif(x==2):
        day=31+y
    elif(x==3):
        day=60+y
    elif(x==4):
        day=91+y
    elif(x==5):
        day=121+y
    elif(x==6):
        day=152+y
    elif(x==7):
        day=182+y
    elif (x == 8):
        day = 213 + y
    elif (x == 9):
        day = 244+ y
    elif (x == 10):
        day = 274 + y
    elif (x == 11):
        day = 305+ y
    elif (x == 12):
        day = 335 + y
    return day
def wenjianhuoqu():#文件夹所有子文件目录获取
    filepath = 'd:/python练习文档/全球历史数据/'
    r_lis = list()
    pathDir=os.listdir(filepath)
    for allDir in pathDir:
        try:
            r_lis.append(os.path.join('%s%s'%(filepath,allDir)))
        except:
            print('{0:}位元素出错'.format(i))
    return r_lis
def lp(p_list):
    url="http://www.sy72.com/covid/index.asp?s1=0&s2=0"
    soup=BeautifulSoup(url_text_get(url),"html.parser")
    l=soup.find('tr',id="cx")
    data=list()
    adata=list()
    path="D:/python练习文档/全球历史数据/中国.xls"
    for i in l.children:
        soupl=BeautifulSoup(str(i),"html.parser")
        p=soupl.find_all("span")
        if(p!=[]):
            g=[]
            for k in p:
                g.append(k.string)
            data.append(g)
    y=['国家','疫情总确诊','疫情治愈','疫情死亡','时间']
    adata.append(y)
    for j in range(len(data[0])):
        t=list()
        t.append("中国")
        t.append(data[2][j])
        t.append(data[3][j])
        t.append(data[4][j])
        t.append(str(tjs(int(data[0][j].split(".")[-2]),int(data[0][j].split(".")[-1]))))
        adata.append(t)
    for j in range(len(p_list)):
        if(p_list[j][0]=="中国"):
            adata[0].append('人口')
            adata[0].append('占比')
            for o in range(1,len(adata)):
                adata[o].append(p_list[j][1])
                adata[o].append(int(adata[o][1])/cf(p_list[j][1].split(',')))
    renkoubaocun(adata, path)
    return len(adata)-1
def riqizhuanhuan(data,p_list,s):#日期转换为天数
    for i in range(1,len(data)):
        try:
            k=tjs(int(data[i][4].split('/')[-2]),int(data[i][4].split('/')[-1]))
            data[i][4]=str(k)
        except:
            print("第{0:}行出错".format(i))
    for j in range(len(p_list)):
        if(p_list[j][0]==s):
            data[0].append('人口')
            data[0].append('占比')
            for o in range(1,len(data)):
                data[o].append(p_list[j][1])
                data[o].append(int(data[o][1])/cf(p_list[j][1].split(',')))
    return data
def cf(li):#'千分号字符转换int'
    s=''
    for i in range(len(li)):
        s=s+li[i]
    return int(s)
def renkoubaocun(l_li,filename2):#疫情信息人口保存.xls
    f=xlwt.Workbook()
    sheet1 = f.add_sheet('class')
    for i in range(0,len(l_li)):
        try:
            sheet1.write(i,0,l_li[i][0])
            sheet1.write(i,1,l_li[i][1])
            sheet1.write(i,2,l_li[i][2])
            sheet1.write(i,3,l_li[i][3])
            sheet1.write(i,4,l_li[i][4])
            sheet1.write(i,5,l_li[i][5])
            sheet1.write(i,6,l_li[i][6])
        except:
            break
    f.save(filename2)
def d_xieru(p_list,path,s):#多个文件天数转换加xls转换
    l_list=riqizhuanhuan(read_txt(path),p_list,s)
    renkoubaocun(l_list,path)
def read_txt(filename):
    data=list()
    file=open(filename,'r',encoding='ANSI')
    file_data=file.readlines()
    for row in file_data:
        row = re.sub(r'<.*?>', "\t",row)
        tmp_list=row.split('\t')
        tmp_list[-1]=tmp_list[-1].replace('\n','')
        tmp_list.pop(-1)
        data.append(tmp_list)
    file.close()
    return data
def pxu(e_list):#排序
    for lis in e_list:
        for i in range(len(lis)-1):
            for k in range(i+1,len(lis)):
                if(lis[k][1]>lis[i][1]):
                    p=lis[i]
                    lis[i]=lis[k]
                    lis[k]=p
def xieru(r_lis,e_list,z_list,day):#每天的数据读入
    global window
    n=26
    layout = [[sg.Text('数据加载进度'),sg.Text('0.00%',key='2')],
              [sg.ProgressBar(day, orientation='h', size=(20, 20), key='progressbar')],
              [sg.Cancel()]]
    window1= sg.Window('加载进度', layout)
    progress_bar = window1['progressbar']
    for i in range(n,day+n-1):
        e_list.append([])
        z_list.append([])
        for j in range(len(r_lis)):
            try:
                data=xlrd.open_workbook(r_lis[j])
                table=data.sheet_by_name(data.sheet_names()[0])
                rowNum=table.nrows
                kli=[]
                cli=[]
                key=0
                for l in range(1,rowNum):
                    if(int(table.cell(l,4).value)==i and table.cell(l,0).value==table.cell(2,0).value):
                        kli.append(table.cell(l,0).value)
                        kli.append(table.cell(l,6).value)
                        try:
                            cli.append(table.cell(l,0).value)
                            cli.append(int(table.cell(l,3).value)/int(table.cell(l,1).value))
                        except:
                            cli.append(0)
                        key=1
                        break
                if(key==1):
                    e_list[i-n].append(kli)
                    z_list[i-n].append(cli)
            except:
                continue
        event, values = window1.read(timeout=20)
        if event=="Cancel":
            window1.close()
            sys.exit(0)
        progress_bar.UpdateBar(i-n+1)
        window1.FindElement("2").Update(str("{:.2f}".format(((i-n)/(day))*100)+'%'))
    window1.close()
    #window.Element('2').Update(disabled=True)
    #window.Element('4').Update(disabled=True)
    try:
        e_list.remove([])
        z_list.remove([])
    except:
        return
def plante(e_list,t):#循环画图
    plt.switch_backend('TkAgg')
    plt.ion()
    matplotlib.rc('font', family='SimHei', weight='bold')
    try:
        for j in range(len(e_list)):
            if((j+26)==153 or (j+26)==133 ):
                continue
            else:
                if(len(e_list[j])>=20):
                    N=20
                else :
                    N=len(e_list[j])
                name=[]
                for i in range(N):
                    name.append(e_list[j][i][0])
                for i in range(N,20):
                    name.append('暂无数据')
                city_name = name
                city_name.reverse()
                data = []
                we=10
                while(e_list[j][0][1]*we<50):
                    we=we*10
                if(e_list[j][0][1]*we>200):
                    we=we/5
                for i in range(N,20):
                    data.append(0)
                for i in range(N):
                    data.append(((e_list[j][N-i-1][1])*we))
                colors = ['red', 'yellow', 'blue', 'green', 'gray','pink','black']
                colors.reverse()
                plt.barh(range(len(data)),width=data, tick_label=city_name, color=colors)
                for a,b in zip(data,range(len(data))):
                    plt.text(a+3, b,'{0:.2f}'.format(a), ha='center', va= 'center',fontsize=7)
                if(t==1):
                    plt.title('2020年第{0:}天全球国家感染率'.format(j+26))
                    plt.xlabel('累计人数/总人口（1/{0:}）'.format(we))
                if(t==2):
                    plt.title('2020年第{0:}天全球国家治愈率'.format(j+26))
                    plt.xlabel('治愈人数/总确诊（1/{0:}）'.format(we))
                plt.pause(0.275)
                plt.show()
                if(j==len(e_list)-1):
                    break
                plt.clf()
    except:
        pass
def guojiachaxun(r_list,s):
    li=list()
    for i in r_list:
        if(i.split("/")[-1].split(".")[0]==s):
            data = xlrd.open_workbook(i)
            table = data.sheet_by_name(data.sheet_names()[0])
            rowNum = table.nrows
            for l in range(0, rowNum):
                kli = []
                key = 0
                kli.append(table.cell(l, 0).value)
                kli.append(table.cell(l, 1).value)
                kli.append(table.cell(l, 4).value)
                kli.append(table.cell(l, 5).value)
                kli.append(table.cell(l, 6).value)
                try:
                    kli.remove([])
                except:
                    pass
                li.append(kli)
    return li
def riqichaxun(e_list,z_list,s):
    i=list()
    try:
        day=tjs(int(s.split(".")[0]),int(s.split(".")[1]))
        i=e_list[day-26]
        for j in range(len(z_list[day-26])):
            i[j].append(z_list[day-26][j][1])
    except:
        pass
    return i
if __name__=="__main__":#程序入口
    global window,apath
    apath=''
    sg.theme('Dark Brown 1')
    gn = [
        [sg.InputText(default_text="请输入国家名", key='0', font=("Helvetica", 10)),
         sg.Button('G查询', size=(10, 1),key=('5'), font=("Helvetica", 10),disabled=True),
         sg.Text('叙述', size=(3, 1), font=("Helvetica", 10)),
         sg.Button('确诊统计图', size=(10, 1),key=('2'), font=("Helvetica", 10),disabled=True)],
        [sg.InputText(default_text="请输入日期(x.y)", key='1', font=("Helvetica", 10)),
         sg.Button('T查询', size=(10, 1),key=('3'),font=("Helvetica", 10),disabled=True),
         sg.Text('叙述', size=(3, 1), font=("Helvetica", 10)),
         sg.Button('治愈统计图', size=(10, 1),key=('4'),font=("Helvetica", 10),disabled=True)],
    ]
    headings = ['', '', '', '', '']
    header = [[sg.Text('  ')] + [sg.Text(h, size=(12, 1)) for h in headings]]
    input_rows = [[sg.Multiline('', key='6', size=(75, 45), autoscroll=True)]]
    layout = gn + header + input_rows
    window = sg.Window('全球新冠历史数据', layout, icon='icon/puple128.ico', font='Courier 12', size=(750, 500))
    event, values = window.read(timeout=100)
    try:
        day=down(yqlj(),renkouhuode(url_infor_get()))#文件下载加转换集合
    except:
        window.Element('6').Update( "***全球疫情信息下载失败，将使用历史文件信息！***")
    event, values = window.read(timeout=100)
    window.Element('6').Update(values.get('6')+"***全球疫情信息下载转换成功！***")
    window.Element('6').Update(values.get('6') + "***历史疫情保存地址为:{:}***".format(apath))
    window.Element('2').Update(disabled=False)
    window.Element('4').Update(disabled=False)
    window.Element('3').Update(disabled=False)
    window.Element('5').Update(disabled=False)
    event, values = window.read(timeout=100)
    e_list = list(list(list()))
    z_list = list(list(list()))
    try:
        xieru(wenjianhuoqu(), e_list, z_list, day)
    except:
        window.Element('2').Update(disabled=True)
        window.Element('4').Update(disabled=True)
        window.Element('3').Update(disabled=True)
        window.Element('6').Update(values.get('6') + "***数据载入失败！***")
    event, values = window.read(timeout=100)
    window.Element('6').Update(values.get('6') + "***数据加载成功！***"+"\n"+"***请开始进行操作***"+"\n",autoscroll=False)
    pxu(e_list)
    pxu(z_list)
    while True:
        event, values = window.read()
        if event in (None,'关闭'):
            break
        if event in(None,'5'):
            try:
                t = "{0:<8}{1:<12}{2:<5}{3:<15}{4:<20}"
                window.Element('6').Update(t.format("国家","疫情总确诊","时间","人口","确诊占比"))
                s = values.get('0')
                data = guojiachaxun(wenjianhuoqu(), s)
                if(s=="中国"):
                    data=data[:1:-1]
                for l in range(1,len(data)):
                    ty=[]
                    event, values = window.read(timeout=100)
                    for i in range(len(data[l])):
                        ty.append(str(data[l][i]))
                    window.Element('6').Update(values.get('6') +t.format(ty[0],ty[1],ty[2],ty[3],ty[4]))
            except:
                window.Element('6').Update(values.get('6') + "***错误！***")
        if event in(None,'3'):
            '''try:'''
            t="{0:<4}{1:<8}{2:<20}{3:<20}{4:<6}"
            window.Element('6').Update(t.format("排名","国家","确诊占比","治愈占比","日期"))
            s = values.get('1')
            data = riqichaxun(e_list,z_list,s)
            for l in range(len(data)):
                ty=list()
                event, values = window.read(timeout=100)
                for i in range(len(data[l])):
                    ty.append(str(data[l][i]))
                window.Element('6').Update(values.get('6')+t.format(str(l),ty[0],ty[1],ty[2],s))
            '''except:
                window.Element('6').Update(values.get('6') + "***错误！***")'''
        if event in (None,'2'):
            t=1
            plante(e_list, t)
        if event in (None,'4'):
            t=2
            plante(z_list, t)
    window.close()