From 022266171bd17d7d1ace9852ca427461787f052c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=9D=8E=E7=9B=9F?= <1127928805@qq.com>
Date: Tue, 4 Mar 2025 05:20:16 +0000
Subject: [PATCH] Upload New File

---
 json2excel.py | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)
 create mode 100644 json2excel.py

diff --git a/json2excel.py b/json2excel.py
new file mode 100644
index 0000000..23c4f3b
--- /dev/null
+++ b/json2excel.py
@@ -0,0 +1,33 @@
+import os 
+import re
+import json
+import pandas as pd
+
+file_list = os.listdir("/home/limeng/NLP/LLM/code/0220/result")
+files_sorted = sorted(file_list, key=lambda x: int(re.search(r'(\d+)', x).group()))
+json_folder_path = "/home/limeng/NLP/LLM/code/0220/result"
+
+for filename in files_sorted:    
+    # 读取 JSON 文件
+    file_path = os.path.join(json_folder_path, filename)
+    with open(file_path, 'r', encoding='utf-8') as file:
+        data = json.load(file)
+        
+        # 提取 extracted_info 字段
+        extracted_info = data.get("extracted_info", {})
+        
+        # 创建一个字典用于存储这条数据
+        row_data = {}
+        
+        # 遍历 extracted_info 中的键值对，填充到字典中
+        for key, value in extracted_info.items():
+            row_data[key] = value
+        for column in df.columns:
+            if column not in row_data:
+                row_data[column] = "无"
+        # 将 row_data 添加到 DataFrame 中
+        new_row = pd.DataFrame([row_data])
+        df = pd.concat([df, new_row], ignore_index=True)
+
+# 输出结果 DataFrame
+print(df)
\ No newline at end of file
-- 
2.22.0