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.
62 lines
1.9 KiB
62 lines
1.9 KiB
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
|
|
html
|
|
# 导入 lxml
|
|
from lxml import etree
|
|
# 若是本地没有安装 lxml 的同学可以通过“pip install lxml”来安装
|
|
# 创建一个 lxml 对象，编码方式设为 utf-8
|
|
parse = etree.HTMLParser(encoding='utf-8') # 添加编码
|
|
# 解析 requests 返回的响应结果
|
|
doc = etree.HTML(html)
|
|
country = 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(country, person, death))
|
|
message
|
|
import csv
|
|
with open("content.csv", "w") 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='gbk')
|
|
df.head()
|
|
df.info()
|
|
df1 = df.drop(0).tail(58)
|
|
df2=df1.head(15)
|
|
print(df2)
|
|
import matplotlib.pyplot as plt
|
|
|
|
# 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 = df2["country"].values
|
|
# y轴坐标
|
|
y = df2["death"].values
|
|
# 绘制柱状图
|
|
plt.bar(x, y)
|
|
# 设置x轴名称
|
|
plt.xlabel("国家",fontsize=14)
|
|
# 设置x轴名称
|
|
plt.ylabel("死亡人数",fontsize=14)
|
|
plt.show()
|