Python to achieve PDF to Word method explained

pip install PyMuPDF==1.18.17

pip install pdf2docx==0.5.1

# Importing the Converter class from the pdf2docx module.
from pdf2docx import Converter

def pdfToWord(pdf_file_path=None, word_file_path=None):
    """
    It takes a pdf file path and a word file path as input, and converts the pdf file to a word file.

    :param pdf_file_path: The path to the PDF file you want to convert
    :param word_file_path: The path to the word file that you want to create
    """
    # Creating a Converter object.
    converter_ = Converter(pdf_file_path)
    # The `convert` method takes the path to the word file that you want to create, and the start and end pages of the PDF
    # file that you want to convert.
    converter_.convert(word_file_path, start=0, end=None)
    converter_.close()

# A special variable in Python that evaluates to `True` if the module is being run directly by the Python interpreter, and
# `False` if it has been imported by another module.
if __name__ == '__main__':
    pdfToWord('D:/test-data-work/test_pdf.pdf', 'D:/test-data-work/test_pdf.docx')

# Parsing Page 2: 2/5...Ignore Line "∑" due to overlap
# Ignore Line "∑" due to overlap
# Ignore Line "ç" due to overlap
# Ignore Line "Ａ" due to overlap
# Ignore Line "ｉ ＝１" due to overlap
# Ignore Line "æ" due to overlap
# Parsing Page 5: 5/5...
# Creating Page 5: 5/5...
# --------------------------------------------------
# Terminated in 3.2503201s.

from pdf2docx import Converter
import PySimpleGUI as sg
 
 
def pdf2word(file_path):
    file_name = file_path.split('.')[0]
    doc_file = f'{file_name}.docx'
    p2w = Converter(file_path)
    (doc_file, start=0, end=None)
    ()
    return doc_file
 
 
def main():
    # Selection of topics
    ('DarkAmber')
 
    layout = [
        [('pdfToword', font=('Microsoft Black', 12)),
         ('', key='filename', size=(50, 1), font=('Microsoft Black', 10))],
        [(size=(80, 10), font=('Microsoft Black', 10))],
        [('Select file', key='file', target='filename'), ('Start conversion'), ('Exit')]]
    # Create windows
    window = ("Zhang Crouching Tiger", layout, font=("Microsoft Black.", 15), default_element_size=(50, 1))
    # Event loop
    while True:
        # Window read with two return values (1. event; 2. value)
        event, values = ()
        print(event, values)
 
        if event == "Begin conversion.":
 
            if values['file'] and values['file'].split('.')[1] == 'pdf':
                filename = pdf2word(values['file'])
                print('Number of documents: 1')
                print('\n' + 'Conversion successful!' + '\n')
                print('File save location:', filename)
            elif values['file'] and values['file'].split(';')[0].split('.')[1] == 'pdf':
                print('Number of documents ：{}'.format(len(values['file'].split(';'))))
                for f in values['file'].split(';'):
                    filename = pdf2word(f)
                    print('\n' + 'Conversion successful!' + '\n')
                    print('File save location:', filename)
            else:
                print('Please choose the pdf format file oh!')
        if event in (None, 'Exit'):
            break
 
    ()
main()

#-*- coding: UTF-8 -*- 
#!/usr/bin/python
#-*- coding: utf-8 -*-
import sys
import importlib
(sys)
from  import PDFParser,PDFDocument
from  import PDFResourceManager, PDFPageInterpreter
from  import PDFPageAggregator
from  import *
from  import PDFTextExtractionNotAllowed
import os
# Setting up the working directory folder
(r'c:/users/dicey/desktop/codes/pdf-docx')
# Parse pdf file function
def parse(pdf_path):
 fp = open('', 'rb') # Open in binary read mode
 # Use the file object to create a pdf document analyzer
 parser = PDFParser(fp)
 # Create a PDF document
 doc = PDFDocument()
 # Connection Analyzer with Document Objects
 parser.set_document(doc)
 doc.set_parser(parser)
 # Provide initialization passwords
 # If there's no password, create an empty string #
 ()
 # Detect whether the document provides txt conversion, do not provide on the ignore
 if not doc.is_extractable:
  raise PDFTextExtractionNotAllowed
 else:
  # Create PDf Explorer to manage shared resources
  rsrcmgr = PDFResourceManager()
  # Create a PDF device object
  laparams = LAParams()
  device = PDFPageAggregator(rsrcmgr, laparams=laparams)
  # Create a PDF interpreter object
  interpreter = PDFPageInterpreter(rsrcmgr, device)
  # Used to count the number of objects such as pages, images, curves, figures, horizontal text boxes, etc.
  num_page, num_image, num_curve, num_figure, num_TextBoxHorizontal = 0, 0, 0, 0, 0
  # Loop over the list, processing the contents of one page at a time
  for page in doc.get_pages(): # doc.get_pages() get list of pages
   num_page += 1 # Add one to the page
   interpreter.process_page(page)
   # Accept the LTPage object for this page
   layout = device.get_result()
   for x in layout:
    if isinstance(x,LTImage): # Picture objects
     num_image += 1
    if isinstance(x,LTCurve): # Curve objects
     num_curve += 1
    if isinstance(x,LTFigure): # figure objects
     num_figure += 1
    if isinstance(x, LTTextBoxHorizontal): # Get text content
     num_TextBoxHorizontal += 1 # Horizontal text box objects add one
     # Save text content
     with open(r'', 'a',encoding='utf-8') as f: # Generate the file name and path of the doc file
      results = x.get_text()
      (results)
      ('\n')
  print('Number of objects: \n','Number of pages: %s\n'%num_page,'Number of pictures: %s\n'%num_image,'Number of curves: %s\n'%num_curve,'Horizontal text box: %s\n'
    %num_TextBoxHorizontal)

if __name__ == '__main__':
 pdf_path = r'' #pdf file path and file name
 parse(pdf_path)