Code snippet to remove duplicate pages from a PDF File

pdfClean.py

#!/usr/bin/env python

"""pdfClean.py: Remove duplicate pages from a PDF File."""

import os
import PyPDF2
import numpy as np
from tqdm import trange, tqdm

__author__ = 'Paulson K Antony'
__copyright__ = 'Copyright 2021, randomProjects'
__credits__ = ['Paulson K Antony']
__license__ = 'GPL'
__version__ = '3.0'

def extract_unique_page_numbers(array):
  return {i: (array == i).nonzero()[0][0] for i in np.unique(array)}

#Replace input.pdf with file name of the input
pdf_reader = PyPDF2.PdfFileReader('input.pdf')
pdf_writer = PyPDF2.PdfFileWriter()
numPages = pdf_reader.getNumPages()

file = []

print('Extracting page number:')
for i in trange(numPages):
    #print(i)
    current_page = pdf_reader.getPage(i)
    file.append(current_page.extractText())
    
print('\n')

file = np.array(file, dtype=object)

uniquePages = list(extract_unique_page_numbers(file).values())
uniquePages.sort()

print('Writing unique pages to output: ')
#print(uniquePages)

for i in trange(len(uniquePages)):
    pdfPage = pdf_reader.getPage(uniquePages[i])
    pdf_writer.addPage(pdfPage)
    #print(f'Added page:', uniquePages[i])

#Replace output.pdf with file name of the output    
pdf_output = "output.pdf"

with open(pdf_output, 'wb') as f:
    pdf_writer.write(f)
    
print('OUTPUT GENERATED SUCCESSFULLY!')