You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
76 lines
2.3 KiB
76 lines
2.3 KiB
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Thu May 23 22:35:58 2024
|
|
|
|
@author: Lenovo
|
|
"""
|
|
|
|
import requests
|
|
url = "https://www.bitpush.news/covid19/"
|
|
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36 Edg/116.0.1938.54"}
|
|
response = requests.get(url,headers=headers)
|
|
html = response.text
|
|
|
|
from lxml import etree
|
|
parse = etree.HTMLParser(encoding='gbk')
|
|
doc = etree.HTML(html)
|
|
|
|
area = doc.xpath('//*[@id="main"]/div[2]/div/div/div/div/div[1]/table/tbody/tr/td[1]/span/text()')
|
|
person = doc.xpath('//*[@id="main"]/div[2]/div/div/div/div/div[1]/table/tbody/tr/td[2]/text()')
|
|
person = [x.replace(",", "") for x in person]
|
|
death = doc.xpath('//*[@id="main"]/div[2]/div/div/div/div/div[1]/table/tbody/tr/td[3]/text()')
|
|
death = [x.replace(",", "") for x in death]
|
|
message = list(zip(area, person, death))
|
|
|
|
import csv
|
|
with open("content.csv", "w") as f:
|
|
w = csv.writer(f)
|
|
w.writerows(message)
|
|
|
|
import pandas as pd
|
|
df = pd.read_csv("content.csv", names=["area", "person", "death"],encoding='gbk')
|
|
df.head()
|
|
df.info()
|
|
df1 = df.drop(0).head(15)
|
|
|
|
import matplotlib.pyplot as plt
|
|
#确诊人数垂直图
|
|
plt.rcParams['font.sans-serif'] = ['SimHei']
|
|
plt.rcParams['figure.figsize'] = (10, 5)
|
|
x = df1["area"].values
|
|
y = df1["person"].values
|
|
plt.bar(x, y)
|
|
plt.xlabel("地区",fontsize=14)
|
|
plt.ylabel("确诊人数",fontsize=14)
|
|
plt.show()
|
|
#确诊人数水平图
|
|
x = df1["area"].values
|
|
y = df1["person"].values
|
|
colors=['red','green','cyan','blue']
|
|
plt.barh(x, y,height=0.8,color=colors)
|
|
plt.yticks(x)
|
|
plt.xlabel("确诊人数",fontsize=14)
|
|
plt.ylabel("地区",fontsize=14)
|
|
for i,j in zip(x,y):
|
|
plt.text(j,i,j)
|
|
plt.legend()
|
|
plt.show()
|
|
#死亡人数垂直图
|
|
plt.rcParams['font.sans-serif'] = ['SimHei']
|
|
plt.rcParams['figure.figsize'] = (10, 5)
|
|
x = df1["area"].values
|
|
y = df1["death"].values
|
|
plt.bar(x, y)
|
|
plt.xlabel("地区",fontsize=14)
|
|
plt.ylabel("死亡人数",fontsize=14)
|
|
plt.show()
|
|
#确诊人数饼图
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
labels = df1["area"].values
|
|
sizes = df1["person"].values
|
|
explode = (0.1,0,0,0,0,0,0,0,0,0,0,0,0,0,0)
|
|
plt.pie(sizes,explode,labels=labels,autopct='%.1f%%')
|
|
plt.title("美国疫情确诊人数排名 top15 地区情况")
|
|
|