Python批量实现word中查找关键字的示例代码

#!/usr/bin/python
# -*- coding: UTF-8 -*-
"""
@author:Awen
@file:task_test.py
@time:2023/07/04
@function：Python实现在word中批量查找关键字，如果关键字在word中，则将文件移出到新建的文件夹中
"""
import os
import shutil
from docx import Document
from docx.opc.exceptions import PackageNotFoundError
def search_keyword_in_word(keyword, file_path):
    # 若报错，则跳过，有的文件无法读取成功
    try:
        document = Document(file_path)
        found_paragraphs = []
        for paragraph in document.paragraphs:
            if keyword in paragraph.text:
                found_paragraphs.append(paragraph.text)
        return found_paragraphs
    except PackageNotFoundError:
        print(f"文件 '{file_path}' 未找到。")
        pass
# 原文件夹路径
source_file_path = 'D:\Pycharmproject2023\code_test_project\shan_test\正样本终版\\'
#  搜索的关键字
keyword = '求职意向'
for filename in os.listdir(source_file_path):
    try:
        # 创建新文件夹，用于找到相应文件之后将其移入到该文件夹中
        new_directory = os.path.join(source_file_path, "data123")
        os.makedirs(new_directory, exist_ok=True)
        if filename.endswith('.docx'):
            print(filename)
            result = search_keyword_in_word(keyword, source_file_path+filename)
            for paragraph in result:
                print(paragraph)
                # 如果求职意向中包含java字样，则是任务目标文件
                if "java" in paragraph.lower():
                    new_file_path = os.path.join(new_directory, filename)
                    shutil.move(source_file_path+filename, new_file_path)
                    print(f"已移动文件: {filename}")
                    # # 删除原文件夹中的文件
                    # os.remove(source_file_path+filename)
                    # print(f"已删除文件: {filename}")
    except Exception as e:
        print(f"处理文件 '{filename}' 时出现错误: {str(e)}")
        pass