Extraction et modification d'un docx avec python :

import zipfile
import os
import shutil

input_filename='exemple.docx'
output_filename='exemple-output.docx'

# Extraction du .docx
sourceFile = zipfile.ZipFile(input_filename)
tmp_dir="tmp-docx"
os.mkdir(tmp_dir)
sourceFile.extractall(tmp_dir)

##
# ici l'on modifie 'word/document.xml'
##

# Création du .docx
filenames = sourceFile.namelist()
with zipfile.ZipFile(output_filename, "w", compression=zipfile.ZIP_DEFLATED) as docx:
    for filename in filenames:
        docx.write(os.path.join(tmp_dir,filename), filename)

shutil.rmtree(tmp_dir)

— Permalink