Agent-n8n/scripts/fix_wenlu_images.py

#!/usr/bin/env python3
"""
直接处理文旅订单班的图片整理
"""

import os
import shutil
import re
from pathlib import Path

def main():
    """主函数"""
    base_dir = Path("/Users/xiaoqi/Documents/Dev/Project/2025-09-08_n8nDEMO演示/data/订单班文档资料/文旅")
    notion_dir = base_dir / "notion文稿"
    image_dir = notion_dir / "image"

    print("=" * 60)
    print("开始处理文旅订单班图片")
    print("=" * 60)

    # 定义图片重命名映射
    rename_mapping = {
        # Whisk系列 -> 设计图系列
        "Whisk_03282ab7e5.jpg": "设计图_01.jpg",
        "Whisk_15f65339bb.jpg": "设计图_02.jpg",
        "Whisk_192cdc54bc.jpg": "设计图_03.jpg",
        "Whisk_1c05424f7f.jpg": "设计图_04.jpg",
        "Whisk_27184afa6e.jpg": "设计图_05.jpg",
        "Whisk_2a9b622636.jpg": "设计图_06.jpg",
        "Whisk_4aabd94ef3.jpg": "设计图_07.jpg",
        "Whisk_5c4b912ea7.jpg": "设计图_08.jpg",
        "Whisk_8236005bb2.jpg": "设计图_09.jpg",
        "Whisk_9e8c1f44ac.jpg": "设计图_10.jpg",
        "Whisk_be64a7b61f.jpg": "设计图_11.jpg",
        "Whisk_c478fe089d.jpg": "设计图_12.jpg",
        "Whisk_dcc81c5212.jpg": "设计图_13.jpg",
        "Whisk_e2ffe75dbc.jpg": "设计图_14.jpg",
        "Whisk_e2ffe75dbc 1.jpg": "设计图_15.jpg",
        "Whisk_e8f83d1a37.jpg": "设计图_16.jpg",
        "Whisk_f3f954649c.jpg": "设计图_17.jpg",

        # 数字开头的文件 -> 场景图系列
        "2.试驾小景.jpg": "场景图_01.jpg",
        "3.小米汽车.jpg": "场景图_02.jpg",

        # 中文名保留但规范化
        "博览会.jpg": "场景图_03.jpg",
        "展会内部参观.jpg": "场景图_04.jpg",
        "展馆布置图.jpeg": "场景图_05.jpg",  # 注意是jpeg
        "签到.jpg": "场景图_06.jpg"
    }

    # 处理图片重命名
    print("\n📝 开始重命名图片...")
    renamed_count = 0

    for old_name, new_name in rename_mapping.items():
        old_path = image_dir / old_name
        new_path = image_dir / new_name

        if old_path.exists():
            try:
                # 如果是jpeg转jpg
                if old_name.endswith('.jpeg'):
                    # 复制并转换格式
                    shutil.copy2(old_path, new_path)
                    old_path.unlink()  # 删除原文件
                else:
                    # 直接重命名
                    shutil.move(str(old_path), str(new_path))

                renamed_count += 1
                print(f"  ✓ {old_name} → {new_name}")
            except Exception as e:
                print(f"  ✗ 失败 {old_name}: {e}")
        else:
            print(f"  ⚠ 文件不存在: {old_name}")

    print(f"\n✅ 重命名完成: {renamed_count}/{len(rename_mapping)} 个文件")

    # 更新Markdown文件中的引用
    print("\n📝 更新Markdown文件...")
    md_files = list(notion_dir.glob("*.md"))

    for md_file in md_files:
        print(f"  处理: {md_file.name}")
        try:
            content = md_file.read_text(encoding='utf-8')
            original_content = content

            # 替换所有图片引用
            for old_name, new_name in rename_mapping.items():
                # 处理各种可能的引用格式
                # 1. ![xxx](old_name)
                content = content.replace(f"]({old_name})", f"](./image/{new_name})")
                # 2. ![xxx](./image/old_name)
                content = content.replace(f"](./image/{old_name})", f"](./image/{new_name})")
                # 3. ![xxx](image/old_name)
                content = content.replace(f"](image/{old_name})", f"](./image/{new_name})")
                # 4. 直接的文件名引用
                content = re.sub(
                    f"(?<![/])\\b{re.escape(old_name)}\\b",
                    f"./image/{new_name}",
                    content
                )

            # 确保所有图片引用都指向./image/目录
            # 修正可能的错误路径
            content = re.sub(
                r'!\[([^\]]*)\]\((?!\.?/image/)([^)]+\.(jpg|jpeg|png))\)',
                r'![\1](./image/\2)',
                content,
                flags=re.IGNORECASE
            )

            if content != original_content:
                md_file.write_text(content, encoding='utf-8')
                print(f"    ✓ 已更新")
            else:
                print(f"    - 无需更新")

        except Exception as e:
            print(f"    ✗ 失败: {e}")

    # 创建图片索引
    print("\n📝 创建图片索引...")
    create_index(image_dir)

    print("\n" + "=" * 60)
    print("✅ 文旅订单班图片整理完成！")
    print("=" * 60)

def create_index(image_dir: Path):
    """创建图片索引文件"""
    images = sorted(image_dir.glob("*.jpg"))

    if not images:
        return

    # 分类
    categories = {
        "设计图": [],
        "场景图": [],
        "其他": []
    }

    for img in images:
        name = img.name
        if name.startswith("设计图"):
            categories["设计图"].append(name)
        elif name.startswith("场景图"):
            categories["场景图"].append(name)
        else:
            categories["其他"].append(name)

    # 生成索引内容
    content = "# 文旅订单班 - 图片资源索引\n\n"
    content += f"**图片总数**: {len(images)} 张\n"
    content += f"**更新时间**: 2025-09-28\n\n"

    for cat, files in categories.items():
        if files:
            content += f"## {cat} ({len(files)}张)\n\n"
            for file in files:
                content += f"- {file}\n"
            content += "\n"

    content += """## 使用说明

在Markdown中引用图片：
```markdown
![图片描述](./image/设计图_01.jpg)
```

图片分类：
- **设计图**: Whisk AI生成的展会设计效果图
- **场景图**: 实际展会场景照片
"""

    # 保存索引
    index_file = image_dir.parent / "图片索引.md"
    index_file.write_text(content, encoding='utf-8')
    print(f"  ✓ 索引已创建: {index_file.name}")

if __name__ == "__main__":
    main()