[开发工具]用python将pdf转docx

pip安装太慢：

pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple

CMD执行python脚本：进入对应脚本的路径

python test.py --pdf_file ?D:\pdf\test.pdf --docx_file D:\pdf\example.docx

pdf转docx脚本

# -*- coding: utf-8 -*-
"""
Created on Sat Aug  7 16:36:59 2021

@author: LaoHu
"""
import argparse
from pdf2docx import Converter

def main(pdf_file,docx_file):
    cv = Converter(pdf_file)
    cv.convert(docx_file, start=0, end=None)
    cv.close()
    
if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--pdf_file",type=str)
    parser.add_argument('--docx_file',type=str)
    args = parser.parse_args()
    main(args.pdf_file,args.docx_file)