纯Python 实现 Word 文档转换 Markdown

楚疏笃2025-11-20 22:18
python 复制代码
# 读取 Word 文件
from datetime import time  # 这会导入datetime模块的time类
import uuid
import mammoth
from markdownify import markdownify


    # 转存 Word 文档内的图片
def convert_img(image):
    with image.open() as image_bytes:
        file_suffix = image.content_type.split("/")[1]
        # 使用UUID生成唯一文件名，避免时间戳冲突
        filename = f"{uuid.uuid4().hex}.{file_suffix}"
        path_file = f"./img/{filename}"

        # 确保img目录存在
        import os
        os.makedirs("./img", exist_ok=True)

        with open(path_file, 'wb') as f:
            f.write(image_bytes.read())

    return {"src": path_file}
with open(r"1导读.docx" ,"rb") as docx_file:
    # 转化 Word 文档为 HTML
    result = mammoth.convert_to_html(docx_file,convert_image=mammoth.images.img_element(convert_img))
    # 获取 HTML 内容
    html = result.value
    # 转化 HTML 为 Markdown
    md = markdownify(html,heading_style="ATX")
    print(md)
    with open("./docx_to_html.html",'w',encoding='utf-8') as html_file,open("./docx_to_md.md","w",encoding='utf-8') as md_file:
        html_file.write(html)
        md_file.write(md)
    messages = result.messages
这是原始数据test.docx