Update Python code - the PyPDF2 library has deprecated objects used in Python code

Question

I have been able to use the Python code in a Linux based OS, but when I tried to run it the same code on a Windows based OS, I got deprecation messages.

My question is: How can the code be updated to overcome the deprecation issues?

1. The Python code used was:

import PyPDF2
import openpyxl

def pdf_to_text(pdf_file):
    text = ""
    with open(pdf_file, "rb") as file:
        pdf_reader = PyPDF2.PdfFileReader(file)
        for page_num in range(pdf_reader.getNumPages()):
            page = pdf_reader.getPage(page_num)
            text += page.extractText()
            return text

def save_text_to_excel(text, excel_file):
    workbook = openpyxl.Workbook()
    sheet = workbook.active
    lines = text.split("\n")
    for row_num, line in enumerate(lines, 1):
        sheet.cell(row=row_num, column=1, value=line)
        workbook.save(excel_file)

if __name__ == "__main__":
    pdf_file = "PDF_File_name.pdf"
    excel_file = "output.xlsx"

pdf_text = pdf_to_text(pdf_file)
save_text_to_excel(pdf_text, excel_file)

Output: "PyPDF2.errors.DeprecationError: PdfFileReader is deprecated and was removed in PyPDF2 3.0.0. Use PdfReader instead."

2. So I updated to this Python code:

import PyPDF2
import openpyxl

def pdf_to_text(pdf_file):
    text = ""
    with open(pdf_file, "rb") as file:
        pdf_reader = PyPDF2.PdfReader(file)
        for page_num in range(pdf_reader.getNumPages()):
            page = pdf_reader.getPage(page_num)
            text += page.extractText()
            return text

def save_text_to_excel(text, excel_file):
    workbook = openpyxl.Workbook()
    sheet = workbook.active
    lines = text.split("\n")
    for row_num, line in enumerate(lines, 1):
        sheet.cell(row=row_num, column=1, value=line)
        workbook.save(excel_file)

if __name__ == "__main__":
    pdf_file = "PDF_File_name.pdf"
    excel_file = "output.xlsx"

pdf_text = pdf_to_text(pdf_file)
save_text_to_excel(pdf_text, excel_file)

Output: "PyPDF2.errors.DeprecationError: reader.getNumPages is deprecated and was removed in PyPDF2 3.0.0. Use len(reader.pages) instead."

3. I next updated Python code based on recommendation from https://pypdf2.readthedocs.io/en/latest/user/migration-1-to-2.html which states to update:

reader.getNumPages() / reader.numPages ➔ len(reader.pages)

import PyPDF2
import openpyxl

def pdf_to_text(pdf_file):
    text = ""
    with open(pdf_file, "rb") as file:
        pdf_reader = PyPDF2.PdfReader(file)
        for page_num in range(pdf_reader.len(reader.pages)):
            page = pdf_reader.getPage(page_num)
            text += page.extractText()
            return text

def save_text_to_excel(text, excel_file):
    workbook = openpyxl.Workbook()
    sheet = workbook.active
    lines = text.split("\n")
    for row_num, line in enumerate(lines, 1):
        sheet.cell(row=row_num, column=1, value=line)
        workbook.save(excel_file)

if __name__ == "__main__":
    pdf_file = "PDF_File_name.pdf"
    excel_file = "output.xlsx"

pdf_text = pdf_to_text(pdf_file)
save_text_to_excel(pdf_text, excel_file)

Output: "AttributeError: 'PdfReader' object has no attribute 'len'"

4. I updated the code based on comments by 'Abdul Aziz Barkat': Typo: pdf_reader.len(reader.pages) compare that to len(reader.pages) as stated in the deprecation message... You have to write len(pdf_reader.pages), len is a builtin function in Python.

import PyPDF2
import openpyxl

def pdf_to_text(pdf_file):
    text = ""
    with open(pdf_file, "rb") as file:
        pdf_reader = PyPDF2.PdfReader(file)
        for page_num in range(len(pdf_reader.pages)):
            page = pdf_reader.getPage(page_num)
            text += page.extractText()
            return text

def save_text_to_excel(text, excel_file):
    workbook = openpyxl.Workbook()
    sheet = workbook.active
    lines = text.split("\n")
    for row_num, line in enumerate(lines, 1):
        sheet.cell(row=row_num, column=1, value=line)
        workbook.save(excel_file)

if __name__ == "__main__":
    pdf_file = "computers.pdf"
    excel_file = "output.xlsx"

pdf_text = pdf_to_text(pdf_file)
save_text_to_excel(pdf_text, excel_file)

Output: "PyPDF2.errors.DeprecationError: reader.getPage(pageNumber) is deprecated and was removed in PyPDF2 3.0.0. Use reader.pages[page_number] instead."

Answer 1

Thanks (Abdul and Musabbir) for the feedback, I have updated the code as suggested, also using the Migration Guide to update the deprecated elements: https://pypdf2.readthedocs.io/en/3.x/user/migration-1-to-2.html

This code now runs on Python 3x using a Windows OS:

import openpyxl
import PyPDF2

def pdf_to_text(pdf_file):
    text = ""
    with open(pdf_file, "rb") as file:
        pdf_reader = PyPDF2.PdfReader(file)
        for page_num in range(len(pdf_reader.pages)):
            page = pdf_reader.pages[page_num]
            text += page.extract_text()
        return text

def save_text_to_excel(text, excel_file):
    workbook = openpyxl.Workbook()
    sheet = workbook.active
    lines = text.split("\n")
    for row_num, line in enumerate(lines, 1):
        sheet.cell(row=row_num, column=1, value=line)
        workbook.save(excel_file)

if __name__ == "__main__":
    pdf_file = "PDF-file-name.pdf"
    excel_file = "output.xlsx"
    pdf_text = pdf_to_text(pdf_file)
    save_text_to_excel(pdf_text, excel_file)

Answer 2

The way you're trying to use the methods to read pdf has been deprecated in the new version. Follow the PdfFileReader class documentation to know more. Here's your corrected code:

import openpyxl
from PyPDF2 import PdfFileReader

def pdf_to_text(pdf_file):
    text = ""
    with open(pdf_file, "rb") as file:
        pdf_reader = PdfFileReader(file)
        print(pdf_reader.numPages)
        for page_num in range(pdf_reader.numPages):
            page = pdf_reader.getPage(page_num)
            text += page.extractText()
        return text

def save_text_to_excel(text, excel_file):
    workbook = openpyxl.Workbook()
    sheet = workbook.active
    lines = text.split("\n")
    for row_num, line in enumerate(lines, 1):
        sheet.cell(row=row_num, column=1, value=line)
        workbook.save(excel_file)

if __name__ == "__main__":
    pdf_file = "test.pdf"
    excel_file = "output.xlsx"
    pdf_text = pdf_to_text(pdf_file)
    print(pdf_text)
    save_text_to_excel(pdf_text, excel_file)