#!/usr/bin/env python3 """ 安全的图片分析脚本 - 只分析不修改 先运行这个脚本查看会做哪些修改，确认无误后再执行实际修改 """ import os import re from pathlib import Path from typing import Dict, List, Tuple import json def analyze_order_images(): """分析所有订单班的图片情况""" 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 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" ] print("=" * 80) print("图片资源分析报告") print("=" * 80) print(f"基础路径: {base_path}") print("") total_images = 0 total_to_rename = 0 total_to_convert = 0 reports = [] for order_class in order_classes: order_dir = base_path / order_class if not order_dir.exists(): print(f"⚠️ {order_class}: 目录不存在") continue notion_dir = order_dir / "notion文稿" if not notion_dir.exists(): print(f"⚠️ {order_class}: notion文稿目录不存在") continue # 分析这个订单班 report = analyze_single_order(order_class, notion_dir) reports.append(report) total_images += report['total_images'] total_to_rename += report['to_rename'] total_to_convert += report['to_convert'] # 打印单个订单班报告 print_order_report(report) # 打印总结 print("\n" + "=" * 80) print("📊 总体统计") print("=" * 80) print(f"订单班总数: {len(order_classes)}") print(f"有效订单班: {len(reports)}") print(f"图片总数: {total_images}") print(f"需要重命名: {total_to_rename}") print(f"需要转格式: {total_to_convert}") # 保存详细报告 report_file = base_path.parent.parent / "scripts" / "image_analysis_report.json" with open(report_file, 'w', encoding='utf-8') as f: json.dump(reports, f, ensure_ascii=False, indent=2, default=str) print(f"\n📝 详细报告已保存到: {report_file}") return reports def analyze_single_order(order_class: str, notion_dir: Path) -> Dict: """分析单个订单班的图片""" image_dir = notion_dir / "image" # 收集所有图片 all_images = [] # 在notion文稿根目录查找散落的图片 root_images = [] for ext in ['jpg', 'jpeg', 'png', 'gif', 'bmp', 'webp']: root_images.extend(notion_dir.glob(f"*.{ext}")) root_images.extend(notion_dir.glob(f"*.{ext.upper()}")) # 在image子目录查找图片 sub_images = [] if image_dir.exists(): for ext in ['jpg', 'jpeg', 'png', 'gif', 'bmp', 'webp']: sub_images.extend(image_dir.glob(f"*.{ext}")) sub_images.extend(image_dir.glob(f"*.{ext.upper()}")) all_images = list(set(root_images + sub_images)) # 分析需要的修改 rename_list = [] convert_list = [] move_list = [] # 分类计数器 counters = { "设计图": 0, "展示图": 0, "效果图": 0, "流程图": 0, "场景图": 0, "图片": 0 } for img_path in sorted(all_images): old_name = img_path.name new_name = generate_new_name(old_name, order_class, counters.copy()) # 检查是否需要移动到image目录 if img_path.parent != image_dir: move_list.append({ 'from': str(img_path.relative_to(notion_dir)), 'to': f"image/{new_name}" }) # 检查是否需要重命名 if old_name != new_name: rename_list.append({ 'old': old_name, 'new': new_name }) # 检查是否需要转换格式 if not old_name.lower().endswith('.jpg'): convert_list.append({ 'file': old_name, 'from_format': Path(old_name).suffix, 'to_format': '.jpg' }) # 分析MD文件 md_files = list(notion_dir.glob("*.md")) md_references = [] for md_file in md_files: try: content = md_file.read_text(encoding='utf-8') # 查找所有图片引用 patterns = [ r'!\[([^\]]*)\]\(([^)]+)\)', # Markdown格式 r']+src=["\']([^"\']+)["\']', # HTML格式 ] for pattern in patterns: matches = re.findall(pattern, content) for match in matches: img_ref = match[-1] if isinstance(match, tuple) else match md_references.append({ 'md_file': md_file.name, 'reference': img_ref }) except: pass return { 'order_class': order_class, 'total_images': len(all_images), 'root_images': len(root_images), 'sub_images': len(sub_images), 'to_rename': len(rename_list), 'to_convert': len(convert_list), 'to_move': len(move_list), 'md_files': len(md_files), 'md_references': len(md_references), 'rename_list': rename_list[:5], # 只显示前5个 'convert_list': convert_list[:5], # 只显示前5个 'move_list': move_list[:5], # 只显示前5个 } def generate_new_name(filename: str, order_class: str, counters: Dict[str, int]) -> str: """生成新的标准化文件名""" name = Path(filename).stem.lower() # 特殊处理文旅订单班的Whisk图片 if order_class == "文旅" and 'whisk' in name: counters["设计图"] += 1 return f"设计图_{counters['设计图']:02d}.jpg" # 根据文件名特征分类 if any(kw in name for kw in ['设计', 'design', 'whisk', 'cad', '3d', '三维', '渲染']): counters["设计图"] += 1 return f"设计图_{counters['设计图']:02d}.jpg" elif any(kw in name for kw in ['展示', 'display', 'show', '展台', '展位']): counters["展示图"] += 1 return f"展示图_{counters['展示图']:02d}.jpg" elif any(kw in name for kw in ['效果', 'effect', 'render']): counters["效果图"] += 1 return f"效果图_{counters['效果图']:02d}.jpg" elif any(kw in name for kw in ['流程', 'flow', 'process', '步骤']): counters["流程图"] += 1 return f"流程图_{counters['流程图']:02d}.jpg" elif any(kw in name for kw in ['场景', 'scene', '展会', '博览', '会场', '签到', '试驾']): counters["场景图"] += 1 return f"场景图_{counters['场景图']:02d}.jpg" elif name[0:1].isdigit(): # 数字开头 counters["展示图"] += 1 return f"展示图_{counters['展示图']:02d}.jpg" else: counters["图片"] += 1 return f"图片_{counters['图片']:02d}.jpg" def print_order_report(report: Dict): """打印单个订单班的分析报告""" print(f"\n{'='*50}") print(f"📁 {report['order_class']}订单班") print(f"{'='*50}") print(f" 图片总数: {report['total_images']}") print(f" ├── 根目录: {report['root_images']} 张") print(f" └── image目录: {report['sub_images']} 张") print(f" 需要移动: {report['to_move']} 张") print(f" 需要重命名: {report['to_rename']} 张") print(f" 需要转格式: {report['to_convert']} 张") print(f" MD文件: {report['md_files']} 个") print(f" 图片引用: {report['md_references']} 处") if report['rename_list']: print(f"\n 📝 重命名示例 (前{len(report['rename_list'])}个):") for item in report['rename_list']: print(f" {item['old']} → {item['new']}") if report['move_list']: print(f"\n 📦 需要移动到image目录:") for item in report['move_list']: print(f" {item['from']} → {item['to']}") if __name__ == "__main__": print("🔍 开始分析图片资源...") print("⚠️ 本脚本只分析，不会修改任何文件") print("") analyze_order_images() print("\n" + "="*80) print("✅ 分析完成！") print("") print("下一步：") print("1. 查看生成的 image_analysis_report.json 详细报告") print("2. 确认修改计划无误") print("3. 运行实际修改脚本（带备份功能）")