Python将word文件转化为HTML文件和markdown文件

一、使用的主要模块

• mammoth
• markdownify
• time
• pathlib
• os

二、代码

2.1 将word转变为HTML

def wordToHtml(filename):
    with open(filename+".docx", "rb") as docx_file:
        result = mammoth.convert_to_html(docx_file)
        with open(filename+".html", "w") as html_file:
            html_file.write(result.value)
# 支持word中存在图片

2.2 将word转变为MD

def wordToMd(filename):
    with open(filename+".docx", "rb") as docx_file:
        result = mammoth.convert_to_markdown(docx_file)
        with open(filename+".md", "w") as markdown_file:
            markdown_file.write(result.value)
# 不支持word中存在图片

2.3 支持word中有图片转为MD

def MD(filename):
    with open(filename+".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")
        with open("./docx_to_md.md", "w",encoding='utf-8') as md_file:
            # html_file.write(html)
            md_file.write(md)
        messages = result.messages

# 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]
        # word中图片转为的目录,如果不存在则新建
        my_img = Path("./img")
        if my_img.is_dir()==0:
            os.makedirs("img")
        path_file = "./img/{}.{}".format(str(time.time()),file_suffix)
        with open(path_file, 'wb') as f:
            f.write(image_bytes.read())
    return {"src":path_file}