Python实现将JSON转换为CSV格式

pip install Spire.XLS.Free

import json
from spire.xls import *
from spire.xls.common import *

def simple_json_to_csv(json_path: str, csv_path: str) -> None:
    """
    简单结构JSON转CSV（无嵌套）
    :param json_path: 输入JSON文件路径
    :param csv_path: 输出CSV文件路径
    """
    try:
        # 1. 读取并解析JSON数据
        with open(json_path, 'r', encoding='utf-8') as f:
            json_data = json.load(f)
        
        # 校验数据格式（必须是包含字典的列表）
        if not isinstance(json_data, list) or not all(isinstance(item, dict) for item in json_data):
            raise ValueError("JSON数据需为「包含字典的列表」格式")
        
        # 2. 提取表头（去重）
        headers = []
        for item in json_data:
            for key in item.keys():
                if key not in headers:
                    headers.append(key)
        
        # 3. 初始化Excel工作簿和工作表
        workbook = Workbook()
        worksheet = workbook.Worksheets[0]
        
        # 4. 写入表头（第一行）
        for col_idx, header in enumerate(headers, start=1):
            worksheet.Range[1, col_idx].Text = header
        
        # 5. 写入数据行（从第二行开始）
        for row_idx, item in enumerate(json_data, start=2):
            for col_idx, header in enumerate(headers, start=1):
                # 处理空值，避免KeyError
                cell_value = item.get(header, "")
                worksheet.Range[row_idx, col_idx].Text = str(cell_value)
        
        # 6. 保存为CSV并释放资源
        worksheet.SaveToFile(csv_path, ",", Encoding.get_UTF8())
        workbook.Dispose()
        print(f"转换完成！CSV文件路径：{csv_path}")
    
    except Exception as e:
        print(f"转换失败：{str(e)}")

# 测试调用
if __name__ == "__main__":
    # 示例test.json内容：
    # [{"name":"张三","age":25,"city":"北京"},{"name":"李四","age":30,"city":"上海"}]
    simple_json_to_csv("test.json", "simple_result.csv")

import json
from spire.xls import *
from spire.xls.common import *

def flatten_dict(nested_dict: dict, parent_key: str = '', sep: str = '_') -> dict:
    """
    递归扁平化嵌套字典
    :param nested_dict: 待扁平化的嵌套字典
    :param parent_key: 父键名（递归使用）
    :param sep: 键名分隔符（如info_age）
    :return: 扁平化后的单层字典
    """
    items = []
    for k, v in nested_dict.items():
        new_key = f"{parent_key}{sep}{k}" if parent_key else k
        if isinstance(v, dict):
            # 递归处理嵌套层级
            items.extend(flatten_dict(v, new_key, sep).items())
        else:
            items.append((new_key, v))
    return dict(items)

def nested_json_to_csv(json_path: str, csv_path: str) -> None:
    """
    嵌套结构JSON转CSV
    :param json_path: 输入JSON文件路径
    :param csv_path: 输出CSV文件路径
    """
    try:
        # 1. 读取并解析JSON
        with open(json_path, 'r', encoding='utf-8') as f:
            json_data = json.load(f)
        
        # 2. 扁平化所有嵌套字典
        flattened_data = []
        for item in json_data:
            flattened_item = flatten_dict(item)
            flattened_data.append(flattened_item)
        
        # 3. 提取表头（扁平化后的键）
        headers = []
        for item in flattened_data:
            for key in item.keys():
                if key not in headers:
                    headers.append(key)
        
        # 4. 初始化工作簿并写入数据（同基础场景）
        workbook = Workbook()
        worksheet = workbook.Worksheets[0]
        
        # 写入表头
        for col_idx, header in enumerate(headers, start=1):
            worksheet.Range[1, col_idx].Text = header
        
        # 写入扁平化数据
        for row_idx, item in enumerate(flattened_data, start=2):
            for col_idx, header in enumerate(headers, start=1):
                cell_value = item.get(header, "")
                worksheet.Range[row_idx, col_idx].Text = str(cell_value)
        
        # 保存并释放资源
        worksheet.SaveToFile(csv_path, ",", Encoding.get_UTF8())
        workbook.Dispose()
        print(f"嵌套JSON转换完成！CSV文件路径：{csv_path}")
    
    except Exception as e:
        print(f"转换失败：{str(e)}")

# 测试调用
if __name__ == "__main__":
    # 示例nested_test.json内容：
    # [{"name":"张三","info":{"age":25,"job":{"title":"工程师"}}},{"name":"李四","info":{"age":30,"job":{"title":"产品经理"}}}]
    nested_json_to_csv("nested_test.json", "nested_result.csv")

cell_value = str(cell_value).replace('\n', ' ').replace('\r', ' ').replace('\t', ' ')