Python 遍历目录读取word文本日期

• 基于工作需求，现需要统计几千份word文件中日期进行存档
• 可利用Python脚本模块遍历目录下所有word文件，查找其中日期，以文件名-日期格式导出到txt文本中
• 先明确相关需求

1. 需读取doc/docx格式，利用python-docx和win32com.client库分别处理docx和doc格式文件
2. 文档中日期格式为xx年xx月xx日，利用正则表达式进行匹配日期
3. 输出为txt文本

import os
import re
import win32com.client
from docx import Document

def find_dates(text):
    pattern = r'\b\d{1,4}年\d{1,2}月\d{1,2}日\b'
    return re.findall(pattern, text)

def process_word_files(directory):
    results = []
    for filename in os.listdir(directory):
        if filename.endswith('.docx'):
            doc = Document(os.path.join(directory, filename))
            text = ' '.join(paragraph.text for paragraph in doc.paragraphs)
            dates = find_dates(text)
            for date in dates:
                results.append(f'{filename}-{date}')
        elif filename.endswith('.doc'):
            word = win32com.client.DispatchEx('Word.Application')
            word.Visible = False 
            doc = word.Documents.Open(os.path.join(directory, filename))
            text = doc.Content.Text
            dates = find_dates(text)
            for date in dates:
                results.append(f'{filename}-{date}')
            doc.Close(False)
            word.Quit()
    return results

def save_to_txt(results, output_filename):
    with open(output_filename, 'w') as f:
        for line in results:
            f.write(line + '\n')
directory = r'C:\\Users\\user\\Desktop\\1\\2023' 
output_filename = 'output.txt'  
results = process_word_files(directory)
save_to_txt(results, output_filename)

• 为了更方便，我们可以使用pandas库将结果保存在Excel中
• 如果文件较多，由于读取doc旧版格式会打开word后台，以上代码实际运行后，会出现内存占满问题
• 以下代码进行了改进，在处理完每个文件后关闭后台

import os
import re
import win32com.client
import pandas as pd
from docx import Document

def find_dates(text):
    pattern = r'\b\d{1,4}年\d{1,2}月\d{1,2}日\b'
    return re.findall(pattern, text)

def process_word_files(directory):
    results = []
    for filename in os.listdir(directory):
        if filename.endswith('.docx'):
            doc = Document(os.path.join(directory, filename))
            text = ' '.join(paragraph.text for paragraph in doc.paragraphs)
            dates = find_dates(text)
            for date in dates:
                results.append({'filename': filename, 'date': date})
        elif filename.endswith('.doc'):
            word = win32com.client.DispatchEx('Word.Application')
            word.Visible = False
            doc = word.Documents.Open(os.path.join(directory, filename))
            text = doc.Content.Text
            dates = find_dates(text)
            for date in dates:
                results.append({'filename': filename, 'date': date})
            doc.Close(False)
            word.Quit() 
    return results

def save_to_excel(results, output_filename):
    df = pd.DataFrame(results)
    df.to_excel(output_filename, index=False)

directory = r'C:\\Users\\user\\Desktop\\word\\data'
output_filename = 'output.xlsx'
results = process_word_files(directory)
save_to_excel(results, output_filename)

• 请注意安装相关Python库

pip install python-docx win32com.client pandas openpyxl pyarrow