pywin32 pywin32 docx文档转html页面 word doc docx 提取文字 图片 html 结构

https://blog.csdn.net/X21214054/article/details/78873338

# python docx文档转html页面 - 程序猿tx - 博客园 https://www.cnblogs.com/taixiang/p/9978456.html
# Usage — PyDocX dev documentation https://pydocx.readthedocs.io/en/latest/usage.html

pywin32 · PyPI https://pypi.org/project/pywin32/

from win32com import client as wc

f = files
# https://docs.microsoft.com/zh-cn/office/dev/add-ins/reference/requirement-sets/office-add-in-requirement-sets?view=office-js

for f in files:
    i=10
    try:
        word = wc.Dispatch('Word.Application')
        doc = word.Documents.Open(f)
        nf = f.replace('.doc', '.html')
        doc.SaveAs(nf, i, False, '', True, '', False, False, False, False)  # 创建或覆盖
        doc.Close()
        word.Quit()
        del word, doc  # 否则只有一个文件创建
    except Exception as e:
        print(i, e)