Python采集全国疫情数据，可视化展视图示各数据数值

前言

最近很多同学因为毕设和大作业的原因，想要分析疫情的数据，今天就在这里写一篇

开发环境

• python 3.8: 解释器
• pycharm: 代码编辑器

知识点

1. 代码基本流程
2. requests 发送请求
3. re 正则表达式
4. json 结构化数据解析
5. pyecharts 可视化

先是疫情的数据

实现代码

1. 发送请求
2. 获取数据
3. 解析数据
4. 保存数据

1. 发送请求

headers = {
    
    
    # 浏览器基本信息
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.67 Safari/537.36'
}
response = requests.get(url=url, headers=headers)
print(response)

返回<Response [200]>: 已经请求成功了

2. 获取数据

html_data = response.text

3. 解析数据

: 转义字符(把一些含有特定字符的内容转变为普通的字符)
[(.*)]
[]: [ ]
(): 我只需要 (里面的内容)
.: 匹配任意字符一次
*: 匹配零次或者多次

json_str = re.findall('"component":\[(.*)\],', html_data)[0]
# python 字典数据容器
# 键值对取值
json_dict = json.loads(json_str)
caseList = json_dict['caseList']
for case in caseList:
    area = case['area']     # 省份
    curConfirm = case['curConfirm']     # 确诊人数
    curConfirmRelative = case['curConfirmRelative']     # 确诊人数
    confirmed = case['confirmed']     # 确诊人数
    crued = case['crued']     # 治愈人数
    died = case['died']     # 死亡人数
    print(area, curConfirm, curConfirmRelative, confirmed, crued, died)

4. 保存数据(表格)

with open('data.csv', mode='a', encoding='utf-8', newline='') as f:
    csv_writer = csv.writer(f)
    csv_writer.writerow([area, curConfirm, curConfirmRelative, confirmed, crued, died])

可视化代码

导入数据

df = pd.read_csv('data.csv', encoding='utf-8')
df.head()

各地区确诊人数

china_map = (
    Map()
    .add("现有确诊", [list(i) for i in zip(df['area'].values.tolist(),df['curConfirm'].values.tolist())], "china")
    .set_global_opts(
        title_opts=opts.TitleOpts(title="各地区确诊人数"),
        visualmap_opts=opts.VisualMapOpts(max_=200, is_piecewise=True),
    )
)
china_map.render_notebook()

新型冠状病毒全国疫情地图

import pyecharts
from pyecharts.charts import *
from pyecharts import options as opts
from pyecharts.commons.utils import JsCode
from pyecharts.datasets import register_url

cofirm, currentCofirm, cured, dead = [], [], [], []

tab = Tab()

_map = (
    Map(init_opts=opts.InitOpts(theme='dark', width='1000px'))
    .add("累计确诊人数", [list(i) for i in zip(df['area'].values.tolist(),df['confirmed'].values.tolist())], 
         "china", is_map_symbol_show=False,  is_roam=False)
    .set_series_opts(label_opts=opts.LabelOpts(is_show=True))
    .set_global_opts(
        title_opts=opts.TitleOpts(title="新型冠状病毒全国疫情地图",
                                  ),
        legend_opts=opts.LegendOpts(is_show=False),
        visualmap_opts=opts.VisualMapOpts(is_show=True, max_=1000,
                                          is_piecewise=False,
                                          range_color=['#FFFFE0', '#FFA07A', '#CD5C5C', '#8B0000'])
    )
)
tab.add(_map, '累计确诊')

_map = (
    Map(init_opts=opts.InitOpts(theme='dark', width='1000px'))
    .add("当前确诊人数", [list(i) for i in zip(df['area'].values.tolist(),df['curConfirm'].values.tolist())], "china", is_map_symbol_show=False,  is_roam=False)
    .set_series_opts(label_opts=opts.LabelOpts(is_show=True))
    .set_global_opts(
        title_opts=opts.TitleOpts(title="新型冠状病毒全国疫情地图",
                                  ),
        legend_opts=opts.LegendOpts(is_show=False),
        visualmap_opts=opts.VisualMapOpts(is_show=True, max_=100,
                                          is_piecewise=False,
                                          range_color=['#FFFFE0', '#FFA07A', '#CD5C5C', '#8B0000'])
    )
)
tab.add(_map, '当前确诊')

_map = (
    Map(init_opts=opts.InitOpts(theme='dark', width='1000px'))
    .add("治愈人数", [list(i) for i in zip(df['area'].values.tolist(),df['crued'].values.tolist())], "china", is_map_symbol_show=False,  is_roam=False)
    .set_series_opts(label_opts=opts.LabelOpts(is_show=True))
    .set_global_opts(
        title_opts=opts.TitleOpts(title="新型冠状病毒全国疫情地图",
                                  ),
        legend_opts=opts.LegendOpts(is_show=False),
        visualmap_opts=opts.VisualMapOpts(is_show=True, max_=1000,
                                          is_piecewise=False,
                                          range_color=['#FFFFE0', 'green'])
    )
)
tab.add(_map, '治愈')

_map = (
    Map(init_opts=opts.InitOpts(theme='dark', width='1000px'))
    .add("死亡人数", [list(i) for i in zip(df['area'].values.tolist(),df['died'].values.tolist())], "china", is_map_symbol_show=False,  is_roam=False)
    .set_series_opts(label_opts=opts.LabelOpts(is_show=True))
    .set_global_opts(
        title_opts=opts.TitleOpts(title="新型冠状病毒全国疫情地图",
                                  ),
        legend_opts=opts.LegendOpts(is_show=False),
        visualmap_opts=opts.VisualMapOpts(is_show=True, max_=50,
                                          is_piecewise=False,
                                          range_color=['#FFFFE0', '#FFA07A', '#CD5C5C', '#8B0000'])
    )
)
tab.add(_map, '死亡')

tab.render_notebook()

各地区确诊人数与死亡人数情况

bar = (
    Bar()
    .add_xaxis(list(df['area'].values)[:6])
    .add_yaxis("死亡", df['died'].values.tolist()[:6])
    .add_yaxis("治愈", df['crued'].values.tolist()[:6])
    .set_global_opts(
        title_opts=opts.TitleOpts(title="各地区确诊人数与死亡人数情况"),
        datazoom_opts=[opts.DataZoomOpts()],
        )
)
bar.render_notebook()

Python爬取百度疫情数据