# -*- coding: utf-8 -*-
"""
Created on Fri Dec  2 21:14:38 2022
@name:全球疫情数据爬取
@author: 86156
"""
#爬取网页内容
import requests
from lxml import etree
import pandas as pd
import csv
import matplotlib.pyplot as plt
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/95.0.4638.69 Safari/537.36"
}
response = requests.get(url, headers=headers)
html = response.text
html
#使用lxml解析数据信息
parse = etree.HTMLParser(encoding='utf-8')
doc = etree.HTML(html)
#使用xpath语句筛选美国疫情数据
country = doc.xpath('//div[@class="table_container"]//tbody/tr/td/span/text()')
person = doc.xpath('//div[@class="table_container"]//tbody/tr/td[2]/text()')
death = doc.xpath('//div[@class="table_container"]//tbody/tr/td[3]/text()')
st=country.index('加州')#st=101
en=country.index('美属萨摩亚')#en=158
person = [x.replace(",", "") for x in person[st:en+1]]
death = [x.replace(",", "") for x in death[st:en+1]]
state=country[st:en+1]
#将数据打包并转换成列表
message = list(zip(state, person, death))
message

#将message中的文件保存至csv文件中
df = pd.DataFrame(message)
df.to_csv('content.csv')#保存在csv文件


# 读取数据
df = pd.read_csv("content.csv", names=["State", "person", "death"])
df=df.sort_values(by=['person'],ascending=False)
df1 = df.head(15)

import matplotlib.pyplot as plt

# 设置中文显示
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['figure.figsize'] = (15, 5)  # 设置figure_size尺寸


# x轴坐标
x = df1["State"].values
# y轴坐标
y = df1["person"].values
# 绘制柱状图
plt.bar(x, y)
# 设置x轴名称
plt.xlabel("不同地区",fontsize=14)
# 设置x轴名称
plt.ylabel("确诊人数",fontsize=14)
plt.show()