python提取docx中带下划线的内容

# -*- coding: utf-8 -*-
"""
Created on Thu Aug 11 11:29:35 2022

@author: koneko
"""

from docx import Document

doc = Document(r"test.docx")

runs = doc.paragraphs[0].runs

block_with_underline = []

for run in runs:
    print(run.text)
    print(run.underline)
    if run.underline==True:
        block_with_underline.append(run.text)
        
    
for block in block_with_underline:
    print(block)
    

posted @ 2022-08-11 11:44  裏表異体  阅读(691)  评论(0编辑  收藏  举报