# -*- coding: utf-8 -*-
"""
Created on Thu May 26 16:41:59 2022

@author: 张舒心 保婧芝
"""

import csv  #用于把爬取的数据存储为csv格式，可以excel直接打开的
import time  #用于对请求加延时，爬取速度太快容易被反爬
from time import sleep #同上
import random  #用于对延时设置随机数，尽量模拟人的行为
import requests  #用于向网站发送请求
from lxml import etree    #lxml为第三方网页解析库，强大且速度快
import pandas as pd
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/101.0.4951.64 Safari/537.36 Edg/101.0.1210.53"}
response = requests.get(url, headers=headers,timeout=10)
html=response.text

parse = etree.HTMLParser(encoding='utf-8')
doc = etree.HTML(html)
continent = doc.xpath('//div[@class="table_container"]//tbody/tr/td/span/text()')
# 确诊人数
person = doc.xpath('//div[@class="table_container"]//tbody/tr/td[2]/text()')
# 由于确诊人数中有逗号，我们使用列表推导式删除
person = [x.replace(",", "") for x in person]
# 死亡人数
death = doc.xpath('//div[@class="table_container"]//tbody/tr/td[3]/text()')
# 同样使用列表推导式删除逗号
death = [x.replace(",", "") for x in death]
message = list(zip(continent, person, death))
message1=message[101:159]




with open("pandemic.csv", "w") as f:
    w = csv.writer(f)
    w.writerows(message1)


df = pd.read_csv("pandemic.csv", names=["continent", "person", "death"],encoding='gbk')
df.info()

df1=df1.head(15)
print(df1)


# 在jupyter中直接展示图像
%matplotlib inline
# 设置中文显示
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['figure.figsize'] = (10, 5)  # 设置figure_size尺寸

# x轴坐标
x = df1["continent"].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("地区",fontsize=14)
# 设置x轴名称
plt.ylabel("确诊人数",fontsize=14)
plt.show()