n8n_Demo/scripts/convert_food_to_json.py

#!/usr/bin/env python3
"""
将食品订单班的Markdown文档转换为JSON格式
"""

import json
import re
from pathlib import Path

def parse_markdown_to_json():
    """解析Markdown文档并转换为JSON"""
    
    # 路径设置
    base_path = Path("/Users/xiaoqi/Documents/Dev/Project/2025-09-08_n8nDEMO演示")
    md_file = base_path / "data/订单班文档资料/食品/notion文稿/中高端个性化轻食店铺经营方案 278d463fce51805081f7cfdc7280f4a4.md"
    
    # 读取Markdown文件
    with open(md_file, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # 数据结构
    data = {
        "title": "中高端个性化轻食店铺经营方案",
        "category": "食品",
        "description": "一个针对年轻消费群体的中高端轻食品牌经营方案",
        "sections": [],
        "images": []
    }
    
    # 提取所有图片
    images = re.findall(r'!\[([^\]]*)\]\(([^)]+)\)', content)
    for alt, path in images:
        # 清理路径
        clean_path = path.replace('./image/', '')
        data["images"].append({
            "alt": alt,
            "src": f"images/food/{clean_path}"
        })
    
    # 按章节解析内容
    sections_pattern = r'^# ([^#\n]+)\n((?:(?!^#).*\n?)*)'
    sections = re.findall(sections_pattern, content, re.MULTILINE)
    
    for section_title, section_content in sections:
        if section_title.strip() == "中高端个性化轻食店铺经营方案":
            continue
            
        section_data = {
            "title": section_title.strip(),
            "content": [],
            "subsections": []
        }
        
        # 解析二级标题
        subsections_pattern = r'^## ([^#\n]+)\n((?:(?!^##).*\n?)*)'
        subsections = re.findall(subsections_pattern, section_content, re.MULTILINE)
        
        for subsection_title, subsection_content in subsections:
            subsection_data = {
                "title": subsection_title.strip(),
                "content": []
            }
            
            # 清理内容
            lines = subsection_content.strip().split('\n')
            for line in lines:
                line = line.strip()
                if line and not line.startswith('!['):
                    # 处理列表项
                    if line.startswith('- '):
                        subsection_data["content"].append({
                            "type": "list-item",
                            "text": line[2:].strip()
                        })
                    elif line.startswith('**') and line.endswith('**'):
                        subsection_data["content"].append({
                            "type": "bold",
                            "text": line[2:-2].strip()
                        })
                    else:
                        subsection_data["content"].append({
                            "type": "text",
                            "text": line
                        })
            
            section_data["subsections"].append(subsection_data)
        
        # 如果没有二级标题，直接解析内容
        if not subsections:
            lines = section_content.strip().split('\n')
            for line in lines:
                line = line.strip()
                if line and not line.startswith('![') and not line.startswith('##'):
                    section_data["content"].append({
                        "type": "text",
                        "text": line
                    })
        
        data["sections"].append(section_data)
    
    # 添加关键指标
    data["highlights"] = {
        "target": "年轻白领、健身爱好者、追求品质生活的群体",
        "investment": "50-100万元",
        "location": "商业区、写字楼密集区",
        "features": [
            "健康营养的轻食产品",
            "个性化定制服务",
            "舒适的就餐环境",
            "线上线下融合运营"
        ],
        "advantages": [
            "市场需求旺盛",
            "毛利率较高",
            "品牌差异化明显",
            "复购率高"
        ]
    }
    
    return data

def main():
    """主函数"""
    print("开始转换食品订单班数据...")
    
    # 转换数据
    data = parse_markdown_to_json()
    
    # 保存JSON文件
    output_dir = Path("/Users/xiaoqi/Documents/Dev/Project/2025-09-08_n8nDEMO演示/web_frontend/data")
    output_dir.mkdir(exist_ok=True)
    
    output_file = output_dir / "food_order_data.json"
    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)
    
    print(f"✅ 数据已保存到: {output_file}")
    print(f"   - 章节数: {len(data['sections'])}")
    print(f"   - 图片数: {len(data['images'])}")

if __name__ == "__main__":
    main()