用Python可视化新冠疫情数据

requests lxml JSON openpyxl

pandas  pyecharts（可视化库）

pip instll xx  

pip install xx（库名） -i https://pypi.tuna.tsinghua.edu.cn/simple gevent（清华镜像）

1 import requests
2 from lxml import etree
3 import json
4 import openpyxl
5 
6 #通用爬虫
7 url = 'https://voice.baidu.com/act/newpneumonia/newpneumonia'
8 headers = {
9    "User-Agent": ".....(换成自己的)"
10 }
11 response = requests.get(url=url,headers=headers).text
12 #在使用xpath的时候要用树形态
13 html = etree.HTML(response)
14 #用xpath来获取我们之前找到的页面json数据  并打印看看
15 json_text = html.xpath('//script[@type="application/json"]/text()')
16 json_text = json_text[0]
17 print(json_text)

1 #用python本地自带的库转换一下json数据
2 result = json.loads(json_text)
3 print(result)
4 #通过打印出转换的对象我们可以看到我们要的数据都要key为component对应5 的值之下  所以现在我们将值拿出来
6 result = result["component"]
7 #再次打印看看结果
8 print(result)
9 获取国内当前数据
10 result = result[0]['caseList']
11 print(result)

1 #创建工作簿
2 wb = openpyxl.Workbook()
 3 创建工作表
4 ws = wb.active
5 设置表的标题
6 ws.title = "国内疫情"
7  写入表头
8 ws.append(["省份","累计确诊","死亡","治愈"])
9 #获取各省份的数据并写入
10 for line in result:
11     line_name = [line["area"],line["confirmed"],line["died"],line["crued"]]
12     for ele in line_name:
13         if ele == '':
14             ele = 0
15     ws.append(line_name)
16 #保存到excel中
17 wb.save('./china.xlsx')

1 #可视化部分
2 import pandas  as pd
3 from pyecharts.charts import Map,Page
4 from pyecharts import options as opts

1  设置列对齐
2 pd.set_option('display.unicode.ambiguous_as_wide', True)
3  pd.set_option('display.unicode.east_asian_width', True)
4   打开文件
5 df = pd.read_excel('china.xlsx')
6 对省份进行统计
7  data2 = df['省份']
8 data2_list = list(data2)
9 data3 = df['累计确诊']
10  data3_list = list(data3)
11  data4 = df['死亡']
12  data4_list = list(data4)
13 data5 = df ['治愈']
14 data5_list = list(data5)

1 c = (
2    Map()
3       .add("治愈", [list(z) for z in zip(data2_list, data5_list)], "china")
4      .set_global_opts(
5         title_opts=opts.TitleOpts(),
6         visualmap_opts=opts.VisualMapOpts(max_=200),
7     )
8 )
9 c.render()

1 a = (
2     Map()
3     .add("累计确诊", [list(z) for z in zip(data2_list, data3_list)], "china")
4        .set_global_opts(
5       title_opts=opts.TitleOpts(),
6        visualmap_opts=opts.VisualMapOpts(max_=200),
7    )
8 )
9 
10 b = (
11     Map()
12       .add("死亡", [list(z) for z in zip(data2_list, data4_list)], "china")
13       .set_global_opts(
14         title_opts=opts.TitleOpts(),
15         visualmap_opts=opts.VisualMapOpts(max_=200),
16     )
17 )
18 
19 c = (
20     Map()
21        .add("治愈", [list(z) for z in zip(data2_list, data5_list)], "china")
22         .set_global_opts(
23      title_opts=opts.TitleOpts(),
24       visualmap_opts=opts.VisualMapOpts(max_=200),
25     )
26 )
27 
28 page = Page(layout=Page.DraggablePageLayout)
29 page.add(
30     a,
31     b,
32     c,
33 )
34  先生成render.html文件
35 page.render()

1 #完成上一步之后把 page.render()这行注释掉
2 #然后循行这下面
3 Page.save_resize_html("render.html",
4     cfg_file="chart_config.json",
5     dest="my_test.html")