用Python拆分PDF图纸并自动命名

import os
import re
import sys
import logging
from pathlib import Path
from collections import defaultdict

# 检查并导入所需库
try:
    import pdfplumber
    from pypdf import PdfReader, PdfWriter
except ImportError:
    print("请先安装依赖库：在命令行中运行以下命令")
    print("pip install pypdf pdfplumber")
    sys.exit(1)

# 配置日志
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

# ====== 请确认下面的路径是否正确 ======
input_pdf = r"C:\Users\ting9\Desktop\Python文件夹\图纸.pdf"
# =======================================

def extract_part_number(page_text: str, page_num: int) -> str | None:
    """
    从页面文本中提取零件图号
    支持"零件图号："或"零件图号 "（冒号或空格）后的内容
    """
    # 匹配"零件图号"后面跟冒号或空格，再跟图号
    match = re.search(r'零件图号[：:\s]+([A-Z0-9\-_\.]+)', page_text, re.IGNORECASE)
    if match:
        return match.group(1)
    
    return None

def main():
    # 检查输入文件是否存在
    if not os.path.exists(input_pdf):
        logger.error(f"文件不存在：{input_pdf}")
        sys.exit(1)
    
    # 输出文件夹
    output_dir = Path(input_pdf).parent / "拆分PDF"
    output_dir.mkdir(exist_ok=True)
    logger.info(f"输出目录：{output_dir}")
    
    try:
        logger.info("正在扫描所有页面，提取图号...")
        part_to_pages = defaultdict(list)
        unknown_pages = []
        
        with pdfplumber.open(input_pdf) as pdf_plumb:
            total_pages = len(pdf_plumb.pages)
            logger.info(f"共检测到 {total_pages} 页，开始扫描...")
            
            for page_num in range(total_pages):
                plumb_page = pdf_plumb.pages[page_num]
                page_text = plumb_page.extract_text() or ""
                
                # 提取图号
                part_number = extract_part_number(page_text, page_num + 1)
                
                if part_number:
                    safe_name = re.sub(r'[\\/*?:"<>|]', '_', part_number)
                    part_to_pages[safe_name].append(page_num)
                    logger.info(f"第 {page_num+1} 页提取到图号：'{part_number}'")
                else:
                    unknown_pages.append(page_num)
        
        # ---------- 输出统计信息 ----------
        logger.info("=" * 60)
        logger.info("图号统计：")
        for part_number, page_list in part_to_pages.items():
            pages_str = ", ".join(str(p+1) for p in sorted(page_list))
            logger.info(f"  {part_number}: {len(page_list)} 页 (页码: {pages_str})")
        logger.info(f"未识别页面: {len(unknown_pages)} 页")
        logger.info("=" * 60)
        
        # ---------- 第二步：按图号分组写入PDF ----------
        pdf_reader = PdfReader(input_pdf)
        used_filenames = set()
        
        # 处理已识别图号的页面
        for part_number, page_list in part_to_pages.items():
            original_name = part_number
            safe_name = original_name
            suffix = 1
            while safe_name in used_filenames:
                safe_name = f"{original_name}_{suffix}"
                suffix += 1
            used_filenames.add(safe_name)
            
            writer = PdfWriter()
            for page_num in sorted(page_list):
                writer.add_page(pdf_reader.pages[page_num])
            
            output_path = output_dir / f"{safe_name}.pdf"
            with open(output_path, "wb") as out_f:
                writer.write(out_f)
            
            logger.info(f"已保存 '{part_number}'，共 {len(page_list)} 页")
        
        # 处理未识别图号的页面
        for page_num in sorted(unknown_pages):
            safe_name = f"未识别_{page_num + 1:03d}"
            original_name = safe_name
            suffix = 1
            while safe_name in used_filenames:
                safe_name = f"{original_name}_{suffix}"
                suffix += 1
            used_filenames.add(safe_name)
            
            writer = PdfWriter()
            writer.add_page(pdf_reader.pages[page_num])
            
            output_path = output_dir / f"{safe_name}.pdf"
            with open(output_path, "wb") as out_f:
                writer.write(out_f)
            
            logger.info(f"已保存未识别页面（原第 {page_num + 1} 页）")
        
        logger.info(f"拆分完成！文件保存在：{output_dir}")
    
    except Exception as e:
        logger.exception(f"处理PDF时发生错误：{e}")
        sys.exit(1)

if __name__ == "__main__":
    main()    main()