Chunks a PDF into chunks with a specific chunk_size n pages and n overlap per chunk

chunk_pdf_with_overlap.py

#!/usr/bin/env python3

# ------------------------------------------------------------------
# Script Name:   chunk_pdf_with_overlap.py
# Description:   This script processes one PDF file and chunks it into
#                chunks of chunk_size=n pages with a overlap of 
#                overlap=n
# Website:       https://gist.github.com/alsiesta
# Version:       1.0
# Usage:         py chunk_pdf_with_overlap.py <input_pdf> <output_prefix>
# Example:       py countcharacter_in_pdf_range.py mydocument.pdf mydocprefix
# Use Gist:      curl -s https://gist.githubusercontent.com/alsiesta/6ad888bece95198157f395553b462f85/raw/chunk_pdf_with_overlap.py | py - 2BSales.pdf gistdoc
# ------------------------------------------------------------------

import sys
from PyPDF2 import PdfReader, PdfWriter

# Define chunk size and overlap
chunk_size = 5  # Number of pages in each chunk
overlap = 1     # Number of overlapping pages

def chunk_pdf_with_overlap(input_pdf, chunk_size, overlap, output_prefix):
    reader = PdfReader(input_pdf)
    total_pages = len(reader.pages)

    start_page = 0
    chunk_number = 1

    while start_page < total_pages:
        end_page = min(start_page + chunk_size - 1, total_pages - 1)

        writer = PdfWriter()
        for i in range(start_page, end_page + 1):
            writer.add_page(reader.pages[i])

        output_pdf = f"{output_prefix}_chunk_{chunk_number}.pdf"
        with open(output_pdf, "wb") as out_file:
            writer.write(out_file)

        start_page = start_page + chunk_size - overlap
        chunk_number += 1


if __name__ == "__main__":
    input_pdf = sys.argv[1]
    output_prefix = sys.argv[2]



    chunk_pdf_with_overlap(input_pdf, chunk_size, overlap, output_prefix)