python实现批量docx转txt

import os
from pdf2docx import Converter
from win32com import client as wc
"""这里需要安转包pywin32com"""

# 读取pdf文件文本内容
def DocxToTxt(inputFinallyPath, outputFinallyPath):
    wordhandle = wc.Dispatch("Word.Application")
    wordhandle.Visible = 0  # 后台运行，不显示
    wordhandle.DisplayAlerts = 0  # 不警告
    doc = wordhandle.Documents.Open(inputFinallyPath)
    doc.SaveAs(outputFinallyPath, 4)  # txt=4, html=10, docx=16， pdf=17
    doc.Close


if __name__ == '__main__':

		# 输入路径
        inputPath = r'D:\pythonproject\pdf_to_txt\input'
    	#输出路径，最好采用绝对路径
        outputPath = r'D:\pythonproject\pdf_to_txt\output'
      
        # 将文件夹的文件列举出来
        pdfList = os.listdir(inputPath)
        # 批量读取存储
        pdf_num = 1
        for li in pdfList:
            print(li)
            inputFinallyPath = inputPath + '/' + li
            li = li.replace('.docx', '.txt')
            outputFinallyPath = outputPath + '/' + li
            DocxToTxt(inputFinallyPath, outputFinallyPath)
            print('第 %d 篇docx已转换为txt' % pdf_num)
            pdf_num = pdf_num + 1
        print('共计%d篇docx文章已完全转换为txt' pdf_num-1))