[
  {
    "instruction": "1",
    "input": "2",
    "output": "3"
  }
]

import os
import json
import pandas as pd
from collections import OrderedDict


def read_json_files(directory):
    # 遍历指定目录及其子目录下的所有文件
    for root, dirs, files in os.walk(directory):
        for file in files:
            res = []
            # 检查文件扩展名是否为.json
            if file.endswith('.json'):
                # 构建文件的完整路径
                file_path = os.path.join(root, file)
                # 打开并读取JSON文件
                with open(file_path, 'r', encoding='utf-8') as f:
                    try:
                        data = json.load(f)
                        print(f"File: {file_path}")
                        # 打印文件名
                        file_name = file.replace('.json', '')
                        print(f"File name: {file_name}")
                        # print(json.dumps(data, ensure_ascii=False, indent=4))

                        for item in data:
                            print(item['instruction'])
                            res.append(item['instruction'])

                        print(res)

                        # 指定JSON文件的名称和路径
                        json_file_path = f"{file_name}_new.json"

                        # 将数组写入到JSON文件中
                        with open(json_file_path, 'w', encoding='utf-8') as json_file:
                            json.dump(res, json_file, ensure_ascii=False, indent=4)

                        print("-" * 40)
                    except json.JSONDecodeError as e:
                        print(f"Error decoding JSON from {file_path}: {e}")


# 指定要遍历的文件夹路径
directory_path = '/Users/qinyingjie/Documents/python-workspace/web/chapter08-file/11-test/subject'
read_json_files(directory=directory_path)