misc/readDocx.py


1
2
3
4
5
6
7
8
9
10
11
12

#! usr/bin/env python3

# readDocx.py

import docx

def getText(filename):
    doc = docx.Document(filename)
    fullText = []
    for para in doc.paragraphs:
        fullText.append(para.text)
    return '\n'.join(fullText)