n8n_Demo/scripts/organize_images.py

#!/usr/bin/env python3
"""
图片整理脚本
功能：
1. 统一图片命名格式
2. 更新Markdown文件中的图片引用
3. 生成图片映射文件
"""

import os
import re
import shutil
import json
from pathlib import Path
from typing import Dict, List, Tuple

class ImageOrganizer:
    def __init__(self, base_path: str):
        self.base_path = Path(base_path)
        self.image_mapping = {}  # 旧名称 -> 新名称的映射

    def clean_filename(self, filename: str, prefix: str = "", index: int = 1) -> str:
        """
        清理文件名，生成规范的命名
        规则：
        - Whisk_开头的文件 -> 设计图_01.jpg
        - 数字开头的文件 -> 展示图_01.jpg
        - 中文名保留但规范化
        """
        name = Path(filename).stem
        ext = Path(filename).suffix.lower()

        # 统一扩展名
        if ext == '.jpeg':
            ext = '.jpg'

        # 根据原始文件名特征分类
        if name.startswith('Whisk_'):
            # AI生成的设计图
            new_name = f"设计图_{index:02d}{ext}"
        elif name[0].isdigit():
            # 数字开头的展示图
            desc = name.split('.')[-1] if '.' in name else ""
            new_name = f"展示图_{index:02d}_{desc}{ext}" if desc else f"展示图_{index:02d}{ext}"
        elif name in ['博览会', '展会内部参观', '展馆布置图', '签到']:
            # 保留有意义的中文名
            new_name = f"{name}{ext}"
        else:
            # 其他情况
            new_name = f"{prefix}_{index:02d}{ext}" if prefix else f"图片_{index:02d}{ext}"

        return new_name

    def organize_images(self, order_class: str):
        """整理指定订单班的图片"""
        image_dir = self.base_path / order_class / "notion文稿" / "image"

        if not image_dir.exists():
            print(f"目录不存在: {image_dir}")
            return

        # 获取所有图片文件
        images = list(image_dir.glob("*.[jJ][pP][gG]")) + \
                list(image_dir.glob("*.[jJ][pP][eE][gG]")) + \
                list(image_dir.glob("*.[pP][nN][gG]"))

        if not images:
            print(f"没有找到图片: {image_dir}")
            return

        print(f"\n处理 {order_class} 的 {len(images)} 张图片...")

        # 分类计数器
        design_count = 0
        display_count = 0
        other_count = 0

        # 处理每张图片
        for img_path in sorted(images):
            old_name = img_path.name

            # 判断类型并生成新名称
            if 'Whisk' in old_name:
                design_count += 1
                new_name = self.clean_filename(old_name, "设计图", design_count)
            elif old_name[0].isdigit():
                display_count += 1
                new_name = self.clean_filename(old_name, "展示图", display_count)
            else:
                # 保留原有的中文名称
                new_name = self.clean_filename(old_name)

            # 如果名称有变化，记录映射关系
            if old_name != new_name:
                self.image_mapping[old_name] = new_name

                # 重命名文件
                new_path = img_path.parent / new_name
                if not new_path.exists():
                    shutil.move(str(img_path), str(new_path))
                    print(f"  重命名: {old_name} -> {new_name}")

    def update_markdown_references(self, order_class: str):
        """更新Markdown文件中的图片引用"""
        md_dir = self.base_path / order_class / "notion文稿"

        # 查找所有Markdown文件
        md_files = list(md_dir.glob("*.md"))

        for md_file in md_files:
            content = md_file.read_text(encoding='utf-8')
            original_content = content

            # 更新图片引用
            for old_name, new_name in self.image_mapping.items():
                # 匹配各种可能的图片引用格式
                patterns = [
                    f"!\\[([^\\]]*)\\]\\({re.escape(old_name)}\\)",  # ![alt](image.jpg)
                    f"!\\[([^\\]]*)\\]\\(\\./image/{re.escape(old_name)}\\)",  # ![alt](./image/image.jpg)
                    f"!\\[([^\\]]*)\\]\\(image/{re.escape(old_name)}\\)",  # ![alt](image/image.jpg)
                ]

                for pattern in patterns:
                    # 保持原有的路径结构，只替换文件名
                    if './image/' in pattern:
                        replacement = f"![\\1](./image/{new_name})"
                    elif 'image/' in pattern:
                        replacement = f"![\\1](image/{new_name})"
                    else:
                        replacement = f"![\\1]({new_name})"

                    content = re.sub(pattern, replacement, content)

            # 如果内容有变化，保存文件
            if content != original_content:
                md_file.write_text(content, encoding='utf-8')
                print(f"  更新Markdown: {md_file.name}")

    def update_html_references(self):
        """更新HTML文件中的图片引用"""
        # 更新web_result中的HTML文件
        web_result_path = self.base_path.parent.parent / "web_frontend" / "web_result"

        if not web_result_path.exists():
            return

        html_files = list(web_result_path.glob("*.html")) + \
                     list((web_result_path / "pages").glob("*.html"))

        for html_file in html_files:
            content = html_file.read_text(encoding='utf-8')
            original_content = content

            # 更新图片引用
            for old_name, new_name in self.image_mapping.items():
                # 匹配HTML中的图片引用
                patterns = [
                    f'src="([^"]*)/image/{re.escape(old_name)}"',
                    f"src='([^']*)/image/{re.escape(old_name)}'",
                    f'url\\(([^)]*)/image/{re.escape(old_name)}\\)',
                ]

                for pattern in patterns:
                    content = re.sub(
                        pattern,
                        lambda m: f'{pattern.split("(")[0].split("=")[0]}="{m.group(1)}/image/{new_name}"' if "src" in pattern else f'url({m.group(1)}/image/{new_name})',
                        content
                    )

            if content != original_content:
                html_file.write_text(content, encoding='utf-8')
                print(f"  更新HTML: {html_file.name}")

    def save_mapping(self, order_class: str):
        """保存图片映射关系"""
        if not self.image_mapping:
            return

        mapping_file = self.base_path / order_class / "图片映射.json"

        with open(mapping_file, 'w', encoding='utf-8') as f:
            json.dump(self.image_mapping, f, ensure_ascii=False, indent=2)

        print(f"  保存映射文件: {mapping_file}")

    def create_image_index(self, order_class: str):
        """创建图片索引文档"""
        image_dir = self.base_path / order_class / "notion文稿" / "image"

        if not image_dir.exists():
            return

        images = sorted(image_dir.glob("*.[jJ][pP][gG]")) + \
                sorted(image_dir.glob("*.[pP][nN][gG]"))

        if not images:
            return

        index_content = f"# {order_class} - 图片索引\n\n"
        index_content += f"总计：{len(images)} 张图片\n\n"

        # 按类别分组
        design_images = [img for img in images if "设计图" in img.name]
        display_images = [img for img in images if "展示图" in img.name]
        other_images = [img for img in images if img not in design_images and img not in display_images]

        if design_images:
            index_content += "## 设计图\n"
            for img in design_images:
                index_content += f"- {img.name}\n"
            index_content += "\n"

        if display_images:
            index_content += "## 展示图\n"
            for img in display_images:
                index_content += f"- {img.name}\n"
            index_content += "\n"

        if other_images:
            index_content += "## 其他图片\n"
            for img in other_images:
                index_content += f"- {img.name}\n"
            index_content += "\n"

        # 保存索引文件
        index_file = self.base_path / order_class / "notion文稿" / "图片索引.md"
        index_file.write_text(index_content, encoding='utf-8')
        print(f"  创建图片索引: {index_file}")

def main():
    # 设置基础路径
    base_path = "/Users/xiaoqi/Documents/Dev/Project/2025-09-08_n8nDEMO演示/doc/订单班文档资料"

    # 订单班列表
    order_classes = [
        "文旅", "财经商贸", "食品", "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"
    ]

    organizer = ImageOrganizer(base_path)

    # 处理每个订单班
    for order_class in order_classes:
        print(f"\n{'='*50}")
        print(f"处理订单班: {order_class}")
        print(f"{'='*50}")

        organizer.image_mapping = {}  # 重置映射

        # 1. 整理图片
        organizer.organize_images(order_class)

        # 2. 更新Markdown引用
        if organizer.image_mapping:
            organizer.update_markdown_references(order_class)

            # 3. 保存映射关系
            organizer.save_mapping(order_class)

        # 4. 创建图片索引
        organizer.create_image_index(order_class)

    print("\n✅ 所有订单班图片整理完成！")

if __name__ == "__main__":
    main()