Update 疫情数据爬虫.py

疫情数据爬虫.py

@@ -1,60 +1,58 @@
-# -*- coding: utf-8 -*-
-"""
-Created on Tue Dec 12 15:24:14 2023
-
-@author: Toon
-"""
-
-import requests
-from lxml import etree
-import csv
-import pandas as pd
-import matplotlib.pyplot as plt
-
-
-# 请求的url
-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
-parse = etree.HTMLParser(encoding='utf-8')  # 添加编码
-# 解析 requests 返回的响应结果
-doc = etree.HTML(html)
-state = doc.xpath('//html/body/div/div/div[2]/div[2]/div/div/div/div//tbody/tr/td/span/text()')
-# 确诊人数
-person = doc.xpath('//html/body/div/div/div[2]/div[2]/div/div/div/div//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('//html/body/div/div/div[2]/div[2]/div/div/div/div//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(state, person, death))
-with open("content.csv", "w") as f:
-    w = csv.writer(f)
-    w.writerows(message)
-df = pd.read_csv("content.csv", names=["country", "person", "death"],encoding='gbk') 
-df.head()
-df.info()
-df1 = df.head(15)
-df1 = df1[::-1]
-# 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'] = (5,5)  # 设置figure_size尺寸
-
-#制作柱形图
-x = df1["country"].values
-y = df1["person"].values
-plt.barh(x, y)
-plt.ylabel("国家",fontsize=14)
-plt.xlabel("确诊人数",fontsize=14)
-for x,y in zip(y,x):
-        plt.text(x, y,x, ha='left', va='center',color='r')
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Dec 12 15:24:14 2023
+@author: Toon
+"""
+
+import requests
+from lxml import etree
+import csv
+import pandas as pd
+import matplotlib.pyplot as plt
+
+
+# 请求的url
+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
+parse = etree.HTMLParser(encoding='utf-8')  # 添加编码
+# 解析 requests 返回的响应结果
+doc = etree.HTML(html)
+# 地区名称
+state = doc.xpath('//html/body/div/div/div[2]/div[2]/div/div/div/div//tbody/tr/td/span/text()')
+# 确诊人数
+person = doc.xpath('//html/body/div/div/div[2]/div[2]/div/div/div/div//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('//html/body/div/div/div[2]/div[2]/div/div/div/div//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(state, person, death))
+with open("content.csv", "w") as f:
+    w = csv.writer(f)
+    w.writerows(message)
+df = pd.read_csv("content.csv", names=["country", "person", "death"],encoding='gbk') 
+df.head()
+df.info()
+df1 = df.head(15)
+df1 = df1[::-1]
+# 设置中文显示
+plt.rcParams['font.sans-serif'] = ['SimHei']
+plt.rcParams['figure.figsize'] = (5,5)  # 设置figure_size尺寸
+
+#制作柱形图
+x = df1["country"].values
+y = df1["person"].values
+plt.barh(x, y)
+plt.ylabel("国家",fontsize=14)
+plt.xlabel("确诊人数",fontsize=14)
+for x,y in zip(y,x):
+        plt.text(x, y,x, ha='left', va='center',color='r')
 plt.show()