From 3569db0144db90841305c4fb42bc88176c655126 Mon Sep 17 00:00:00 2001
From: hnu202309010318 <1438377688@qq.com>
Date: Thu, 6 Jun 2024 22:41:40 +0800
Subject: [PATCH] ADD file via upload

---
 疫情数据爬取.py | 142 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 142 insertions(+)
 create mode 100644 疫情数据爬取.py

diff --git a/疫情数据爬取.py b/疫情数据爬取.py
new file mode 100644
index 0000000..c5fa06c
--- /dev/null
+++ b/疫情数据爬取.py
@@ -0,0 +1,142 @@
+import requests
+from lxml import etree
+import csv
+import pandas as pd
+import matplotlib.pyplot as plt
+# 步骤一（替换sans-serif字体）
+plt.rcParams['font.sans-serif'] = ['SimHei'] 
+# 步骤二（解决坐标轴负数的负号显示问题）
+plt.rcParams['axes.unicode_minus'] = False
+# 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"
+}
+
+url = "https://www.bitpush.news/covid19/"
+
+try:
+    # 发起 GET 请求
+    response = requests.get(url, headers=headers)
+    response.raise_for_status()
+    response.encoding = response.apparent_encoding  # 确保编码正确
+    html = response.text
+except requests.RequestException as e:
+    print(f"请求出错: {e}")
+    html = ""
+
+if html:
+    # 解析 HTML
+    doc = etree.HTML(html)
+
+    # 获取国家名称
+    country= doc.xpath('//div[@class="table_container"]//tbody/tr/td/span/text()')
+    # 获取确诊人数
+    person = doc.xpath('//div[@class="table_container"]//tbody/tr/td[2]/text()')
+    person = [x.replace(",", "") for x in person]
+    # 获取死亡人数
+    death = doc.xpath('//div[@class="table_container"]//tbody/tr/td[3]/text()')
+    death = [x.replace(",", "") for x in death]
+
+    # 组合数据
+    message = list(zip(country, person, death))
+    # 按死亡人数排序
+    message1 = sorted(message, key=lambda x: int(x[-1]), reverse=True)
+
+    # 保存数据到CSV文件
+    with open("content1.csv", "w", newline='', encoding='utf-8') as f:
+        w = csv.writer(f)
+        w.writerow(["country", "person", "death"])  # 添加表头
+        w.writerows(message1)
+
+    # 读取数据
+    df = pd.read_csv("content1.csv")
+    df1 = df.head(10)
+
+    # 绘制柱状图
+    plt.figure(figsize=(12, 6))
+    plt.bar(df1["country"], df1["death"].astype(int))
+    plt.xlabel("国家", fontsize=14)
+    plt.ylabel("死亡人数", fontsize=14)
+    plt.title("COVID-19死亡人数前10的国家", fontsize=16)
+
+    # 显示每个柱的数值
+    for i, v in enumerate(df1["death"].astype(int)):
+        plt.text(i, v + 0.02 * max(df1["death"].astype(int)), str(v), ha='center', fontsize=12)
+
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    plt.show()
+    # 按确诊人数排序
+    message2 = sorted(message, key=lambda x: int(x[-2]), reverse=True)
+
+    # 保存数据到CSV文件
+    with open("content2.csv", "w", newline='', encoding='utf-8') as f:
+        w = csv.writer(f)
+        w.writerow(["country", "person", "death"])  # 添加表头
+        w.writerows(message2)
+
+    # 读取数据
+    df = pd.read_csv("content2.csv")
+    df2 = df.head(10)
+
+    # 绘制柱状图
+    plt.figure(figsize=(12, 6))
+    plt.bar(df2["country"], df2["person"].astype(int))
+    plt.xlabel("国家", fontsize=14)
+    plt.ylabel("确诊人数", fontsize=14)
+    plt.title("COVID-19确诊人数前10的国家", fontsize=16)
+
+    # 显示每个柱的数值
+    for i, v in enumerate(df2["person"].astype(int)):
+        plt.text(i, v + 0.02 * max(df2["person"].astype(int)), str(v), ha='center', fontsize=12)
+
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    plt.show()
+    # 获取州的名称
+    a=country.index('加州')
+    zhou=country[a:]
+    # 获取确诊人数
+    person1=person[a:]
+     # 获取死亡人数
+    death1=death[a:]
+    #组合数据
+    message0=list(zip(zhou,person1,death1))
+    # 按死亡人数排序
+    message3=sorted(message0, key=lambda x: int(x[-1]), reverse=True)
+    # 保存数据到CSV文件
+    with open("content3.csv", "w", newline='', encoding='utf-8') as f:
+        w = csv.writer(f)
+        w.writerow(["zhou", "person1", "death1"])  # 添加表头
+        w.writerows(message3)
+    # 读取数据
+    df = pd.read_csv("content3.csv")
+    df3 = df.head(10)
+    # 绘制折线图
+    plt.figure(figsize=(12, 6))
+    plt.plot(df3["zhou"], df3["death1"].astype(int), marker='o')
+    plt.xlabel("州", fontsize=14)
+    plt.ylabel("死亡人数", fontsize=14)
+    plt.title("美国COVID9死亡人数前十的州", fontsize=16)
+    # 显示每个点的数值
+    for i, v in enumerate(df3["death1"].astype(int)):
+        plt.text(i, v + 0.02 * max(df3["death1"].astype(int)), str(v), ha='center', fontsize=12)
+    # 按确诊人数排序
+    message4=sorted(message0, key=lambda x: int(x[-2]), reverse=True)
+    # 保存数据到CSV文件
+    with open("content4.csv", "w", newline='', encoding='utf-8') as f:
+        w = csv.writer(f)
+        w.writerow(["zhou", "person1", "death1"])  # 添加表头
+        w.writerows(message4)
+    # 读取数据
+    df = pd.read_csv("content4.csv")
+    df4 = df.head(10)
+    # 绘制折线图
+    plt.figure(figsize=(12, 6))
+    plt.plot(df4["zhou"], df4["person1"].astype(int), marker='o')
+    plt.xlabel("州", fontsize=14)
+    plt.ylabel("确诊人数", fontsize=14)
+    plt.title("美国COVID9确诊人数前十的州", fontsize=16)
+     # 显示每个点的数值
+    for i, v in enumerate(df4["person1"].astype(int)):
+        plt.text(i, v + 0.02 * max(df4["person1"].astype(int)), str(v), ha='center', fontsize=12)
\ No newline at end of file