Python批量提取 Word 文本
import os
from docx import Document
folder = './文档'
for f in os.listdir(folder):
if f.endswith('.docx'):
doc = Document(os.path.join(folder, f))
text = '\n'.join(p.text for p in doc.paragraphs)
with open(f'{os.path.splitext(f)[0]}.txt', 'w', encoding='utf-8') as w:
w.write(text)
print("提取完成")
from docx import Document
folder = './文档'
for f in os.listdir(folder):
if f.endswith('.docx'):
doc = Document(os.path.join(folder, f))
text = '\n'.join(p.text for p in doc.paragraphs)
with open(f'{os.path.splitext(f)[0]}.txt', 'w', encoding='utf-8') as w:
w.write(text)
print("提取完成")
更新时间：2026-09-14 13:13:12