import requests
url = "https://www.bitpush.news/covid19/"
# 设置请求头信息
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"
}
# 使用reqeusts模快发起 GET 请求
response = requests.get(url, headers=headers)
# 获取请求的返回结果
html = response.text
# 导入 lxml
from lxml import etree
parse = etree.HTMLParser(encoding='utf-8')        # 添加编码
# 解析 requests 返回的响应结果
doc = etree.HTML(html)
# 州名
country = doc.xpath('//*[@id="main"]/div[2]/div/div/div/div/div[1]/table/tbody/tr/td/span/text()')
# 确诊人数
person = doc.xpath('//*[@id="main"]/div[2]/div/div/div/div/div[1]/table/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('//*[@id="main"]/div[2]/div/div/div/div/div[1]/table/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]
# 打包数据之后将其转换成列表
message = list(zip(country, person, death))
message=message[:10]
# 导入python中的内置模块csv
import csv
with open("content.csv", "w",encoding="utf-8") as f:
    w = csv.writer(f)
    w.writerows(message)
import pandas as pd

# 读取数据
df = pd.read_csv("content.csv", names=["country", "person", "death"],encoding="utf-8")
print(df)
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei'] 
plt.rcParams['axes.unicode_minus'] = False  
plt.rcParams['figure.figsize'] = (10, 5)
x = df["country"]
y = df["death"]
plt.bar(x,y)
plt.xlabel("美国州名",fontsize=14)
plt.ylabel("死亡人数",fontsize=14)
plt.show()