#-------------------------------------------------------------------------------
# Name:        Convert Doc and DocX to PDF
# Purpose:
#
# Author:      Fantanaru Neculai
#
# Created:     18/03/2022
# Copyright:   (c) Fantanaru Neculai 2022
#-------------------------------------------------------------------------------
# pip install pywin32
# pip install docx2txt
import docx2txt
from win32com import client
import os
files_from_folder = r"c:\\doc"
directory = os.fsencode(files_from_folder)
amount = 1
word = client.DispatchEx("Word.Application")
word.Visible = True
for file in os.listdir(directory):
   filename = os.fsdecode(file)
   print(filename)
   if filename.endswith('docx'):
       text = docx2txt.process(os.path.join(files_from_folder, filename))
       print(f'{filename} transfered ({amount})')
       amount += 1
       new_filename = filename.split('.')[0] + '.txt'
       try:
           with open(os.path.join(files_from_folder + r'\txt_files', new_filename), 'w', encoding='utf-8') as t:
               t.write(text)
       except:
           os.mkdir(files_from_folder + r'\txt_files')
           with open(os.path.join(files_from_folder + r'\txt_files', new_filename), 'w', encoding='utf-8') as t:
               t.write(text)
   elif filename.endswith('doc'):
       doc = word.Documents.Open(os.path.join(files_from_folder, filename))
       text = doc.Range().Text
       doc.Close()
       print(f'{filename} transfered ({amount})')
       amount += 1
       new_filename = filename.split('.')[0] + '.txt'
       try:
           with open(os.path.join(files_from_folder + r'\txt_files', new_filename), 'w', encoding='utf-8') as t:
               t.write(text)
       except:
           os.mkdir(files_from_folder + r'\txt_files')
           with open(os.path.join(files_from_folder + r'\txt_files', new_filename), 'w', encoding='utf-8') as t:
               t.write(text)
word.Quit()