Agent-n8n/scripts/fix_all_markdown_paths.py

#!/usr/bin/env python3
"""
修复所有订单班Markdown文件中的图片路径问题
- 移除URL编码的子目录
- 确保所有图片路径都正确指向./image/目录下的新文件名
"""

import os
import re
from pathlib import Path
from urllib.parse import unquote

def fix_all_markdown_paths():
    """修复所有订单班的Markdown图片路径"""
    base_path = Path("/Users/xiaoqi/Documents/Dev/Project/2025-09-08_n8nDEMO演示/data/订单班文档资料")
    
    # 订单班列表（排除已处理的食品和文旅）
    order_classes = [
        "财经商贸", "智能开发", "智能制造",
        "视觉设计", "交通物流", "土木", "大健康", "能源",
        "化工", "环保"
    ]
    
    print("=" * 60)
    print("修复所有订单班Markdown文件中的图片路径")
    print("=" * 60)
    
    for order_class in order_classes:
        order_dir = base_path / order_class
        if not order_dir.exists():
            continue
            
        notion_dir = order_dir / "notion文稿"
        if not notion_dir.exists():
            continue
            
        image_dir = notion_dir / "image"
        if not image_dir.exists():
            continue
            
        # 获取所有图片文件
        images = list(image_dir.glob("*.jpg"))
        if not images:
            continue
            
        # 查找所有MD文件
        md_files = list(notion_dir.glob("*.md"))
        if not md_files:
            continue
            
        print(f"\n处理 {order_class}...")
        
        for md_file in md_files:
            try:
                content = md_file.read_text(encoding='utf-8')
                original_content = content
                
                # 1. 移除URL编码的子目录路径
                # 匹配 ![xxx](./image/任何子目录/文件名)
                content = re.sub(
                    r'!\[([^\]]*)\]\(./image/[^/\)]+/([^\)]+\.(jpg|jpeg|png|gif))\)',
                    r'![\1](./image/\2)',
                    content,
                    flags=re.IGNORECASE
                )
                
                # 2. 修复错误的图片扩展名（如果原来是jpeg/png，现在都是jpg）
                for img in images:
                    img_name = img.name
                    # 尝试匹配各种可能的原始名称
                    base_name = img_name.replace('.jpg', '')
                    
                    # 替换各种可能的引用
                    patterns = [
                        f'{base_name}.jpeg',
                        f'{base_name}.png',
                        f'{base_name}.gif',
                        f'{base_name}.JPG',
                        f'{base_name}.JPEG',
                        f'{base_name}.PNG'
                    ]
                    
                    for pattern in patterns:
                        content = content.replace(f'](./image/{pattern})', f'](./image/{img_name})')
                        content = content.replace(f']({pattern})', f'](./image/{img_name})')
                
                # 3. 确保所有图片路径都正确格式化
                # 修正只有文件名的情况
                for img in images:
                    img_name = img.name
                    # 匹配 ![xxx](图片名) 改为 ![xxx](./image/图片名)
                    content = re.sub(
                        f'!\\[([^\\]]*)\\]\\({img_name}\\)',
                        f'![\\1](./image/{img_name})',
                        content
                    )
                
                # 保存修改
                if content != original_content:
                    # 创建备份
                    backup_file = md_file.with_suffix('.md.bak2')
                    if not backup_file.exists():
                        md_file.read_text(encoding='utf-8')
                        with open(backup_file, 'w', encoding='utf-8') as f:
                            f.write(original_content)
                    
                    md_file.write_text(content, encoding='utf-8')
                    print(f"  ✓ 修复: {md_file.name}")
                else:
                    print(f"  - 无需修复: {md_file.name}")
                    
            except Exception as e:
                print(f"  ✗ 失败 {md_file.name}: {e}")
    
    print("\n" + "=" * 60)
    print("✅ 所有Markdown路径修复完成！")
    print("=" * 60)

if __name__ == "__main__":
    fix_all_markdown_paths()