Python transformer to convert a bytes array containing PDF data into a string

pdf_string_transformer.py

import datetime
import os

from PyPDF2 import PdfReader

def PdfTextTransformer(pdf_binary, tmp_path):
  print("Reading PDF")

  filename = datetime.datetime.now().strftime("%Y%m%d%H%M%S")

  pdf_string = None

  print("Saving PDF", tmp_path+'/'+filename+'.pdf')

  with open(tmp_path+'/'+filename+'.pdf', 'wb') as f:
      f.write(pdf_binary)

  print("Parsing PDF")

  pdf_reader = PdfReader(tmp_path+'/'+filename+'.pdf')

  num_pages_pdf = len(pdf_reader.pages)
    
  for x in range(0, num_pages_pdf-1):
    page_object = pdf_reader.pages[x]
    
    text = page_object.extract_text()
    pdf_string += text
  
  print("Removing PDF", tmp_path+'/'+filename+'.pdf')

  os.remove(tmp_path+'/'+filename+'.pdf')

  return pdf_string