From 7a66ee0dc4b24fe2bf160df5d4311f32ace33103 Mon Sep 17 00:00:00 2001
From: Felix <>
Date: Thu, 9 Jan 2025 17:32:56 +0800
Subject: [PATCH] first commit

---
 .gitignore | 15 +++++++++++++++
 main.py    | 22 ++++++++++++++++++++++
 2 files changed, 37 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 main.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..0f47134
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,15 @@
+# 忽略构建产物目录
+/build/
+/dist/
+/venv/
+# 忽略日志文件
+*.log
+
+# 忽略一些说明文档
+*.txt
+
+# 忽略源文件
+*.html
+
+# 忽略测试输出的文件
+*.json
\ No newline at end of file
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..37240d5
--- /dev/null
+++ b/main.py
@@ -0,0 +1,22 @@
+# -*- coding:utf-8 -*-
+import json
+import re
+
+
+def htmlToJson():
+    with open('index.html', encoding='utf8') as f:
+        fileContent = f.read()
+
+    patList = re.findall(r'<script>window.data = (.*?);</script><title></title>', fileContent)
+    data_Json = json.loads(patList[0])
+    print(type(data_Json))
+    print(data_Json)
+    return data_Json
+
+if __name__ == "__main__":
+    data = htmlToJson()
+    with open('data.json', 'w', encoding='utf8') as file:
+        # 使用json.dump()方法将字典转换为json并写入文件
+        # ensure_ascii=False 保证非ASCII字符以原始形式保存
+        # indent=4 设置缩进为4个空格，使输出更加易读
+        json.dump(data, file, ensure_ascii=False, indent=4)