记录一个将pdf转为word的脚本

• 用到的模块是python的pdf2doc

pip install pdf2doc

• 实现方式也很简单，直接贴代码了

import os
from pdf2docx import Converter


def pdf_docx():
    # 定义需要转换的PDF的根目录
    pdf_path = r'D:\2024\2024_python_project\pdf'
    # 定义转换为Doc文档的根目录
    doc_path = r'D:\2024\2024_python_project\docs'

    # 遍历PDF根目录获取所有pdf文件
    for file in os.listdir(pdf_path):
        # 获取文件后缀
        suff_name = os.path.splitext(file)[1]
        # 非pdf格式（后缀不为pdf）的文件不进行转换
        if suff_name != '.pdf':
            continue
        # 获取pdf文件名称
        file_name = os.path.splitext(file)[0]
        # pdf文件路径
        pdf_name = pdf_path + '\\' + file
        # 要转换的docx文件路径
        docx_name = doc_path + '\\' + file_name + '.docx'
        # 将PDF文件转换为Doc
        cv = Converter(pdf_name)
        cv.convert(docx_name)
        cv.close()


if __name__ == '__main__':
    pdf_docx()

• 根据pdf页数的不同，转换时间也会不同，如图

  [INFO] Start to convert XXX.pdf  # PDF路径
  [INFO] [1/4] Opening document...
  [INFO] [2/4] Analyzing document...
  [INFO] [3/4] Parsing pages...
  [INFO] (1/5) Page 1
  [INFO] (2/5) Page 2
  [INFO] (3/5) Page 3
  [INFO] (4/5) Page 4
  [INFO] (5/5) Page 5
  [INFO] [4/4] Creating pages...
  [INFO] (1/5) Page 1
  [INFO] (2/5) Page 2
  [INFO] (3/5) Page 3
  [INFO] (4/5) Page 4
  [INFO] (5/5) Page 5
  [INFO] Terminated in 2.60s.
  
  Process finished with exit code 0