单个或批量实现-提取PDF文档中的合同号和姓名并按“合同号_姓名”格式重命名文件。

第一、单个PDF文件命名格式：

提取PDF文档中的合同号和姓名并按"合同号_姓名"格式重命名文件

python 复制代码

import pdfplumber
import re
import os


def extract_contract_info(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            text = page.extract_text()
            # 匹配合同编号（只取前12位）
            contract_match = re.search(r'合同编号[:：]\s*([A-Za-z0-9]{12})', text)
            # 匹配借款人（直到换行或括号，并去除所有空格）
            borrower_match = re.search(r'借款人[:：]\s*([^\n（()]+)', text)

            if contract_match and borrower_match:
                contract_number = contract_match.group(1)
                borrower_name = borrower_match.group(1).replace(" ", "")  # 删除所有空格
                return contract_number, borrower_name
    return None, None


def rename_pdf_file(pdf_path):
    contract_number, borrower_name = extract_contract_info(pdf_path)

    if contract_number and borrower_name:
        dir_name = os.path.dirname(pdf_path)
        new_filename = f"{contract_number}_{borrower_name}.pdf"
        new_filepath = os.path.join(dir_name, new_filename)

        # 避免文件名冲突（自动添加序号）
        counter = 1
        while os.path.exists(new_filepath):
            new_filename = f"{contract_number}_{borrower_name}_{counter}.pdf"
            new_filepath = os.path.join(dir_name, new_filename)
            counter += 1

        os.rename(pdf_path, new_filepath)
        print(f"文件已重命名为: {new_filename}")
    else:
        print("未能提取合同信息，无法重命名")


# 使用示例
pdf_path = r'D:\xmfile\案件杂货表\部门\鲍晓文\《个人借款额度合同》XZ_20201224.pdf'
rename_pdf_file(pdf_path)

第二、批量实现PDF文件命名格式：

提取PDF文档中的合同号和姓名并按"合同号_姓名"格式重命名文件

python 复制代码

import pdfplumber
import re
import os
from typing import Tuple, Optional


def validate_pdf(filepath: str) -> bool:
    """验证文件是否为有效的PDF"""
    try:
        with pdfplumber.open(filepath) as pdf:
            if len(pdf.pages) == 0:
                return False
            return True
    except:
        return False


def clean_borrower_name(name: str) -> str:
    """清洗借款人姓名"""
    # 去除前后空格、特殊字符和标点
    name = re.sub(r'[^\w\u4e00-\u9fa5]', '', name.strip())
    # 去除身份证号、电话等可能跟随的信息
    name = re.sub(r'[\dXx]{15,}', '', name)
    return name


def extract_contract_info(pdf_path: str) -> Tuple[Optional[str], Optional[str]]:
    """提取合同编号和借款人信息"""
    if not validate_pdf(pdf_path):
        return None, None

    try:
        with pdfplumber.open(pdf_path) as pdf:
            full_text = "\n".join([page.extract_text() or "" for page in pdf.pages])

            # 更精确的合同编号匹配（考虑多种格式）
            contract_match = re.search(
                r'(合同编号|合同号|编号)[:：]?\s*([A-Za-z0-9]{10,15})',
                full_text,
                re.IGNORECASE
            )

            # 更精确的借款人匹配（考虑多种表述方式）
            borrower_match = re.search(
                r'(借款人|借款方|甲方)[:：]?\s*([^\n（）()]{2,20}?)(?=[\n（）()]|身份证|联系方式|$)',
                full_text,
                re.IGNORECASE
            )

            if contract_match and borrower_match:
                contract_number = contract_match.group(2)[:12]  # 仍只取前12位
                raw_borrower_name = borrower_match.group(2)
                borrower_name = clean_borrower_name(raw_borrower_name)

                if len(borrower_name) >= 2:  # 姓名至少2个字符
                    return contract_number, borrower_name
    except Exception as e:
        print(f"⚠️ 处理 {os.path.basename(pdf_path)} 时发生错误: {str(e)}")

    return None, None


def rename_pdf_file(pdf_path: str) -> None:
    """重命名PDF文件"""
    original_name = os.path.basename(pdf_path)
    contract_number, borrower_name = extract_contract_info(pdf_path)

    if contract_number and borrower_name:
        dir_name = os.path.dirname(pdf_path)
        base_name = f"{contract_number}_{borrower_name}"
        extension = ".pdf"

        # 处理文件名冲突
        counter = 0
        while True:
            new_name = f"{base_name}{f'_{counter}' if counter else ''}{extension}"
            new_path = os.path.join(dir_name, new_name)

            if not os.path.exists(new_path):
                try:
                    os.rename(pdf_path, new_path)
                    print(f"✅ 成功: {original_name} → {new_name}")
                    break
                except Exception as e:
                    print(f"❌ 重命名失败: {original_name} → {new_name} | 错误: {str(e)}")
                    break
            counter += 1
    else:
        print(f"⚠️ 跳过: {original_name} (未提取到有效信息)")


def batch_rename_pdfs_in_subfolders(root_dir: str) -> None:
    """批量处理子文件夹中的PDF文件"""
    if not os.path.isdir(root_dir):
        print(f"❌ 错误: 目录不存在 {root_dir}")
        return

    processed_files = 0
    skipped_files = 0
    error_files = 0

    for person_dir in os.listdir(root_dir):
        person_dir_path = os.path.join(root_dir, person_dir)

        if not os.path.isdir(person_dir_path):
            continue

        print(f"\n🔍 正在处理: {person_dir}")

        for filename in os.listdir(person_dir_path):
            if filename.lower().endswith('.pdf'):
                pdf_path = os.path.join(person_dir_path, filename)
                try:
                    rename_pdf_file(pdf_path)
                    processed_files += 1
                except Exception as e:
                    print(f"❌ 处理 {filename} 时出错: {str(e)}")
                    error_files += 1
            else:
                skipped_files += 1

    print(f"\n📊 处理完成: 共处理 {processed_files} 个文件, 跳过 {skipped_files} 个, 错误 {error_files} 个")


if __name__ == "__main__":
    # 使用示例
    department_dir = r'D:\xmfile\案件杂货表\部门'

    # 输入验证
    while not os.path.exists(department_dir):
        print(f"目录不存在: {department_dir}")
        department_dir = input("请输入正确的目录路径: ")

    batch_rename_pdfs_in_subfolders(department_dir)