dsProject/dsRagAnything/Test/Ocr/T3_DocxToMd.py

import subprocess
docx_file='./Docx/《动能定理》巩固练习.docx'
temp_markdown='./Res/《动能定理》巩固练习.md'

# 1、先用Pandoc转换，得到图片
subprocess.run(['pandoc', docx_file, '-f', 'docx', '-t', 'markdown', '-o', temp_markdown,
                    '--extract-media=./Res/Images/'])
# 2、把docx转为图片，然后OCR