multiple .doc to .docx file conversion using python

Question

I want to convert all the .doc files from a particular folder to .docx file.

I tried using the following code,

import subprocess
import os
for filename in os.listdir(os.getcwd()):
    if filename.endswith('.doc'):
        print filename
        subprocess.call(['soffice', '--headless', '--convert-to', 'docx', filename])

But it gives me an error: OSError: [Errno 2] No such file or directory

Answer 1

Here is a solution that worked for me. The other solutions proposed did not work on my Windows 10 machine using Python 3.

from glob import glob
import re
import os
import win32com.client as win32
from win32com.client import constants

# Create list of paths to .doc files
paths = glob('C:\\path\\to\\doc\\files\\**\\*.doc', recursive=True)

def save_as_docx(path):
    # Opening MS Word
    word = win32.gencache.EnsureDispatch('Word.Application')
    doc = word.Documents.Open(path)
    doc.Activate ()

    # Rename path with .docx
    new_file_abs = os.path.abspath(path)
    new_file_abs = re.sub(r'\.\w+$', '.docx', new_file_abs)

    # Save and Close
    word.ActiveDocument.SaveAs(
        new_file_abs, FileFormat=constants.wdFormatXMLDocument
    )
    doc.Close(False)

for path in paths:
    save_as_docx(path)