用Python爬取最新疫情数据
这次重大疫情，每时每刻数据都有可能变化，这篇博文将为大家讲解如何爬取实时疫情数据，并且分析数据，作出数据可视化的效果。
报告梗概：
对中国疫情分析
1.1 展示各省疫情具体情况（包括各省的城市）
1.2 找出国内新增疫情的城市
1.3 展示各省这次疫情感染的总人数
1.4 绘制中国疫情累计感染分布图
对中国疫情累计趋势进行分析
2.1 绘制本土累计确诊趋势图
2.2 绘制全国感染新增趋势图（最近几个月）
全球其他国家疫情分析
3.1 绘制全球各国感染总人数情况分布图
查看各国疫情发展情况
第一步：疫情数据接口获取
腾讯新闻从WHO和霍普金斯大学网站获取并整理了COVID-19的疫情跟踪数据，API接口URL为：
url1 = "https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5"
url2 = "https://view.inews.qq.com/g2/getOnsInfo?name=disease_other"
url3 = "https://view.inews.qq.com/g2/getOnsInfo?name=disease_foreign"
url4 = "https://api.inews.qq.com/newsqa/v1/automation/foreign/daily/list?country=美国"
第二步：导入必要库
import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
from matplotlib.ticker import MaxNLocator
import requests
import json
from pyecharts.charts import Map, Geo
from PIL import Image
1.对中国本地的疫情进行分析
过程： 1,先从API接口得到中国本地疫情数据
2，因为提前分析过得到的json文件中’data’数据是字符串，所以把’data’转换成字典类型方便分析
url1 = "https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5"
resp=requests.get(url1)
listdata=[]
listdata=resp.json()
listdata1=json.loads(listdata['data'])
listtime=listdata1['lastUpdateTime']
pd_china=pd.DataFrame()
pd1=pd.DataFrame(listdata1['chinaTotal'],index=['chinaTotal'], columns=['confirm', 'heal','dead','suspect','nowConfirm','nowSevere','importedCase','noInfect'])
pd_china=pd_china.append(pd1)
pd1=pd.DataFrame(listdata1['chinaAdd'],index=['chinaAdd'], columns=['confirm', 'heal','dead','suspect','nowConfirm','nowSevere','importedCase','noInfect'])
pd_china=pd_china.append(pd1)
pd_china['lastUpdateTime']=listtime
pd_china=pd_china.rename(columns={"confirm": "累计确诊", "heal": "治愈","dead":"累计死亡","suspect":"疑是患者","nowConfirm":"现有患者","importedCase":"境外输入","noInfect":"无症状感染者","lastUpdateTime":"最近更新时间","nowSevere":"重症患者"})
pd_china=pd_china.rename(index={"chinaTotal":"中国累计","chinaAdd":"中国新增"})
pd_china
1.1 对国内各省市数据进行清洗分析¶
areaTree=listdata1['areaTree']
china_data=areaTree[0]['children']
china_data
china_list = []
for a in range(len(china_data)):
province = china_data[a]['name']
province_list = china_data[a]['children']
for b in range(len(province_list)):
city = province_list[b]['name']
total = province_list[b]['total']
today = province_list[b]['today']
china_dict = {}
china_dict['province'] = province
china_dict['city'] = city
china_dict['total'] = total
china_dict['today'] = today
china_list.append(china_dict)
china_data = pd.DataFrame(china_list)
china_data['最近更新时间']=listtime
print('各省各地的疫情情况')
china_data
def confirm(x):
confirm = eval(str(x))['confirm']
return confirm
def suspect(x):
suspect = eval(str(x))['suspect']
return suspect
def dead(x):
dead = eval(str(x))['dead']
return dead
def heal(x):
heal = eval(str(x))['heal']
return heal
china_data['confirm'] = china_data['total'].map(confirm)
china_data['suspect'] = china_data['total'].map(suspect)
china_data['dead'] = china_data['total'].map(dead)
china_data['heal'] = china_data['total'].map(heal)
china_data['addconfirm'] = china_data['today'].map(confirm)
china_data = china_data[["province","city","confirm","suspect","dead","heal","addconfirm"]]
china_data=china_data.rename(columns={"province":"省份","city":"城市","confirm":"累计感染","suspect":"疑似","dead":"死亡","heal":"治愈","addconfirm":"新增感染"})
print('各省各地的疫情具体情况')
china_data['最近更新时间']=listtime
china_data
1.2 找出国内新增疫情的城市
china_data1=china_data[china_data['新增感染']>=1]
china_data1
1.3 计算各省感染的总人数，并绘制柱状图
area_data = china_data.groupby("省份")["累计感染"].sum().reset_index()
area_data.columns = ["省份","累计感染"]
print('\n各省份感染总人数比较\n')
print(area_data )
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
plt.figure(figsize = (10,8),dpi=100)
plt.bar(x=0,bottom=area_data['省份'],height=0.5,width=area_data['累计感染'],orientation='horizontal',label='人数',color='red',alpha=0.5 )
for x1, yy in zip(area_data['累计感染'], area_data['省份']):
plt.text(x1+1, yy , str(x1), va='center', fontsize=10, rotation=0)
plt.title("各省感染总人数情况")
plt.xlabel("感染人数")
plt.ylabel("省份")
plt.legend(loc="upper right")
plt.show()
plt.close()
1.4 绘制中国疫情累计感染分布图¶
privince=[]
columns=[]
x=[]
for i in range(len(area_data)):
privince.append(area_data.loc[i]['省份'])
columns.append(int(area_data.loc[i]['累计感染']))
for z in zip(list(privince), list(columns)):
list(z)
x.append(z)
from pyecharts.charts import Map
import pyecharts.options as opts
from pyecharts import options
from pyecharts.globals import ChartType
area_map = Map()
area_map.add("中国疫情感染人数分布图",x, "china",is_map_symbol_show=False)
area_map.set_global_opts(title_opts=opts.TitleOpts(title="中国疫情累计感染人数分布地图"),visualmap_opts=opts.VisualMapOpts(is_piecewise=True,
pieces=[
{"min": 1500, "label": '>10000人', "color": "#6F171F"},
{"min": 500, "max": 15000, "label": '500-1000人', "color": "#C92C34"},
{"min": 100, "max": 499, "label": '100-499人', "color": "#E35B52"},
{"min": 10, "max": 99, "label": '10-99人', "color": "#F39E86"},
{"min": 1, "max": 9, "label": '1-9人', "color": "#FDEBD0"}]))
area_map.render_notebook()
2 对中国疫情累计趋势进行分析
url2 = "https://view.inews.qq.com/g2/getOnsInfo?name=disease_other"
resp=requests.get(url2)
listdata=[]
listdata=resp.json()
listdata2=json.loads(listdata['data'])
chinaDayList=listdata2['chinaDayList']
i=len(chinaDayList)
china_date=pd.DataFrame()
for n in range(i):
pd1=pd.DataFrame(data=chinaDayList[n],index=[n],columns=['confirm','dead','heal','nowConfirm','nowSevere','healRate','date'])
china_date=china_date.append(pd1)
china_date=china_date.rename(columns={"confirm":"累计确诊","dead":"累计死亡","heal":"累计治愈","nowConfirm":"现有确诊","nowSevere":"本土新增","healRate":"治愈率","date":"日期"})
print('\n全国疫情累计情况（展示最后五条）')
china_date.tail()
2.1 绘制本土累计确诊趋势图
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
plt.figure(figsize=(10,4),dpi=90)
plt.xticks(rotation=70)
x=np.array(china_date['日期'])
y=np.array(china_date['累计确诊'])
plt.xticks(range(0,i,4))
plt.plot(x,y)
plt.title('全国疫情累计趋势图')
plt.xlabel("日 期")
plt.ylabel("感 染 人 数")
plt.show()
2.2 绘制全国感染新增趋势图（最近几个月）
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
plt.figure(figsize=(10,4),dpi=90)
plt.xticks(rotation=70)
x=np.array(china_date['日期'])
y=np.array(china_date['本土新增'])
plt.xticks(range(0,i,4))
plt.plot(x,y)
plt.title('全国感染新增趋势图')
plt.xlabel("日 期")
plt.ylabel("感 染 人 数")
plt.show()
- 全球其他国家疫情分析
url3 = "https://view.inews.qq.com/g2/getOnsInfo?name=disease_foreign"
resp=requests.get(url3)
listdata=[]
listdata=resp.json()
listdata3=json.loads(listdata['data'])
areaTree=listdata3['foreignList']
country_list=pd.DataFrame()
for a in range(len(areaTree)):
pd1=pd.DataFrame(areaTree[a],index=[a],columns=['name','continent','y','date','confirmAdd','confirm','dead','heal','nowConfirm'])
country_list=country_list.append(pd1)
country_list=country_list.rename(columns={"name":"名字","continent":"所属大洲","y":"年","date":"日期","confirmAdd":"新增","confirm":"感染","dead":"死亡","heal":"治愈","nowConfirm":"现存感染人数"})
print('\n展示前10条记录')
country_list.head(10)
3.1 绘制全球各国感染总人数情况分布图
info_list = []
name2=[]
confirm2=[]
for a in range(len(areaTree)):
name = areaTree[a]['name']
name2.append(name)
confirm = int(areaTree[a]["confirm"])
confirm2.append(confirm)
info_tuple = (name,confirm)
info_list.append(info_tuple)
nameMap = {
'Singapore Rep.':'新加坡',
'Dominican Rep.':'多米尼加',
'Palestine':'巴勒斯坦',
'Bahamas':'巴哈马',
'Timor-Leste':'东帝汶',
'Afghanistan':'阿富汗',
'Guinea-Bissau':'几内亚比绍',
"Côte d'Ivoire":'科特迪瓦',
'Siachen Glacier':'锡亚琴冰川',
"Br. Indian Ocean Ter.":'英属印度洋领土',
'Angola':'安哥拉',
'Albania':'阿尔巴尼亚',
'United Arab Emirates':'阿联酋',
'Argentina':'阿根廷',
'Armenia':'亚美尼亚',
'French Southern and Antarctic Lands':'法属南半球和南极领地',
'Australia':'澳大利亚',
'Austria':'奥地利',
'Azerbaijan':'阿塞拜疆',
'Burundi':'布隆迪',
'Belgium':'比利时',
'Benin':'贝宁',
'Burkina Faso':'布基纳法索',
'Bangladesh':'孟加拉国',
'Bulgaria':'保加利亚',
'The Bahamas':'巴哈马',
'Bosnia and Herz.':'波斯尼亚和黑塞哥维那',
'Belarus':'白俄罗斯',
'Belize':'伯利兹',
'Bermuda':'百慕大',
'Bolivia':'玻利维亚',
'Brazil':'巴西',
'Brunei':'文莱',
'Bhutan':'不丹',
'Botswana':'博茨瓦纳',
'Central African Rep.':'中非',
'Canada':'加拿大',
'Switzerland':'瑞士',
'Chile':'智利',
'China':'中国',
'Ivory Coast':'象牙海岸',
'Cameroon':'喀麦隆',
'Dem. Rep. Congo':'刚果民主共和国',
'Congo':'刚果',
'Colombia':'哥伦比亚',
'Costa Rica':'哥斯达黎加',
'Cuba':'古巴',
'N. Cyprus':'北塞浦路斯',
'Cyprus':'塞浦路斯',
'Czech Rep.':'捷克',
'Germany':'德国',
'Djibouti':'吉布提',
'Denmark':'丹麦',
'Algeria':'阿尔及利亚',
'Ecuador':'厄瓜多尔',
'Egypt':'埃及',
'Eritrea':'厄立特里亚',
'Spain':'西班牙',
'Estonia':'爱沙尼亚',
'Ethiopia':'埃塞俄比亚',
'Finland':'芬兰',
'Fiji':'斐',
'Falkland Islands':'福克兰群岛',
'France':'法国',
'Gabon':'加蓬',
'United Kingdom':'英国',
'Georgia':'格鲁吉亚',
'Ghana':'加纳',
'Guinea':'几内亚',
'Gambia':'冈比亚',
'Guinea Bissau':'几内亚比绍',
'Eq. Guinea':'赤道几内亚',
'Greece':'希腊',
'Greenland':'格陵兰',
'Guatemala':'危地马拉',
'French Guiana':'法属圭亚那',
'Guyana':'圭亚那',
'Honduras':'洪都拉斯',
'Croatia':'克罗地亚',
'Haiti':'海地',
'Hungary':'匈牙利',
'Indonesia':'印度尼西亚',
'India':'印度',
'Ireland':'爱尔兰',
'Iran':'伊朗',
'Iraq':'伊拉克',
'Iceland':'冰岛',
'Israel':'以色列',
'Italy':'意大利',
'Jamaica':'牙买加',
'Jordan':'约旦',
'Japan':'日本',
'Japan':'日本本土',
'Kazakhstan':'哈萨克斯坦',
'Kenya':'肯尼亚',
'Kyrgyzstan':'吉尔吉斯斯坦',
'Cambodia':'柬埔寨',
'Korea':'韩国',
'Kosovo':'科索沃',
'Kuwait':'科威特',
'Lao PDR':'老挝',
'Lebanon':'黎巴嫩',
'Liberia':'利比里亚',
'Libya':'利比亚',
'Sri Lanka':'斯里兰卡',
'Lesotho':'莱索托',
'Lithuania':'立陶宛',
'Luxembourg':'卢森堡',
'Latvia':'拉脱维亚',
'Morocco':'摩洛哥',
'Moldova':'摩尔多瓦',
'Madagascar':'马达加斯加',
'Mexico':'墨西哥',
'Macedonia':'马其顿',
'Mali':'马里',
'Myanmar':'缅甸',
'Montenegro':'黑山',
'Mongolia':'蒙古',
'Mozambique':'莫桑比克',
'Mauritania':'毛里塔尼亚',
'Malawi':'马拉维',
'Malaysia':'马来西亚',
'Namibia':'纳米比亚',
'New Caledonia':'新喀里多尼亚',
'Niger':'尼日尔',
'Nigeria':'尼日利亚',
'Nicaragua':'尼加拉瓜',
'Netherlands':'荷兰',
'Norway':'挪威',
'Nepal':'尼泊尔',
'New Zealand':'新西兰',
'Oman':'阿曼',
'Pakistan':'巴基斯坦',
'Panama':'巴拿马',
'Peru':'秘鲁',
'Philippines':'菲律宾',
'Papua New Guinea':'巴布亚新几内亚',
'Poland':'波兰',
'Puerto Rico':'波多黎各',
'Dem. Rep. Korea':'朝鲜',
'Portugal':'葡萄牙',
'Paraguay':'巴拉圭',
'Qatar':'卡塔尔',
'Romania':'罗马尼亚',
'Russia':'俄罗斯',
'Rwanda':'卢旺达',
'W. Sahara':'西撒哈拉',
'Saudi Arabia':'沙特阿拉伯',
'Sudan':'苏丹',
'S. Sudan':'南苏丹',
'Senegal':'塞内加尔',
'Solomon Is.':'所罗门群岛',
'Sierra Leone':'塞拉利昂',
'El Salvador':'萨尔瓦多',
'Somaliland':'索马里兰',
'Somalia':'索马里',
'Serbia':'塞尔维亚',
'Suriname':'苏里南',
'Slovakia':'斯洛伐克',
'Slovenia':'斯洛文尼亚',
'Sweden':'瑞典',
'Swaziland':'斯威士兰',
'Syria':'叙利亚',
'Chad':'乍得',
'Togo':'多哥',
'Thailand':'泰国',
'Tajikistan':'塔吉克斯坦',
'Turkmenistan':'土库曼斯坦',
'East Timor':'东帝汶',
'Trinidad and Tobago':'特里尼达和多巴哥',
'Tunisia':'突尼斯',
'Turkey':'土耳其',
'Tanzania':'坦桑尼亚',
'Uganda':'乌干达',
'Ukraine':'乌克兰',
'Uruguay':'乌拉圭',
'United States':'美国',
'Uzbekistan':'乌兹别克斯坦',
'Venezuela':'委内瑞拉',
'Vietnam':'越南',
'Vanuatu':'瓦努阿图',
'West Bank':'西岸',
'Yemen':'也门',
'South Africa':'南非',
'Zambia':'赞比亚',
'Zimbabwe':'津巴布韦'
}
during = [
{"min":10000000},
{"min": 1000000, "max":9999999},
{"min": 100000, "max": 999999},
{"min": 10000, "max": 99999},
{"min": 1000, "max": 9999},
{"min":0,"max":999},
]
map = Map(opts.InitOpts(width='1000px',height='600px')).add(series_name="",
data_pair=info_list,
maptype="world",
name_map=nameMap,
is_map_symbol_show=False)
map.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
map.set_global_opts(
title_opts=opts.TitleOpts(pos_left="40px",title="世界疫情分布情况地图（我国除外）",subtitle_textstyle_opts=opts.TextStyleOpts(font_size=20)),
legend_opts=opts.LegendOpts(selected_mode='multiple'),
visualmap_opts=opts.VisualMapOpts(max_=10000000,is_piecewise=True,pieces=during),
)
map.render_notebook()
4 查看各国疫情发展情况
name=input('想查看的国家： ')
url='https://api.inews.qq.com/newsqa/v1/automation/foreign/daily/list?country='
url4 = url+str(name)
resp=requests.get(url4)
listdata=[]
listdata=resp.json()
listForeign=pd.DataFrame(listdata['data'])
listForeign=listForeign.rename(columns={"y":"年","date":"日期","confirm_add":"新增感染人数","confirm":"感染总人数","heal":"治愈","dead":"死亡总数"})
i=len(listForeign)
list=[]
for n in range(i):
list.append(listForeign['日期'][n].replace('.','-'))
del listForeign['日期']
listForeign['日期']=list
listForeign['时间']=listForeign['年'].astype(str)+'-'+listForeign['日期'].astype(str)
del listForeign['日期']
del listForeign['年']
listForeign=listForeign[listForeign['新增感染人数']>0]
listForeign
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
plt.figure(figsize=(12,4),dpi=90)
plt.xticks(rotation=70)
i=len(listForeign)
x=np.array(listForeign['时间'])
y=np.array(listForeign['新增感染人数'])
plt.xticks(range(0,i,20))
plt.plot(x,y,color='red',label='新增感染人数')
plt.title(name+'感染新增趋势图')
plt.xlabel("日 期")
plt.ylabel("新 增 感 染 人 数")
plt.show()
Original: https://blog.csdn.net/sunzhipan11/article/details/122353967
Author: 孙志攀
Title: 用python爬取全国和全球疫情数据，并进行可视化分析(过程详细代码可运行)
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/692599/
转载文章受原作者版权保护。转载请注明原作者出处！