A python script to merge all PDFs in a directory into one, with a title page with the file name for each pdf file

pdf_merger.py

import os
from PyPDF2 import PdfMerger, PdfReader
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import LETTER
from io import BytesIO

def create_title_page(title: str) -> BytesIO:
    """Create a single-page PDF with the title text centered."""
    buffer = BytesIO()
    c = canvas.Canvas(buffer, pagesize=LETTER)
    width, height = LETTER
    c.setFont("Helvetica-Bold", 24)
    c.drawCentredString(width / 2, height / 2, title)
    c.showPage()
    c.save()
    buffer.seek(0)
    return buffer

def merge_pdfs_with_titles(input_dir: str, output_path: str):
    merger = PdfMerger()

    # Get all PDF files in the directory, sorted by name
    pdf_files = sorted(f for f in os.listdir(input_dir) if f.lower().endswith('.pdf'))

    for pdf_file in pdf_files:
        title = os.path.splitext(pdf_file)[0]
        title_pdf = create_title_page(title)

        # Add title page
        merger.append(PdfReader(title_pdf))

        # Add original PDF
        pdf_path = os.path.join(input_dir, pdf_file)
        merger.append(pdf_path)

    # Write to output file
    with open(output_path, 'wb') as fout:
        merger.write(fout)
    print(f"Merged PDF saved as: {output_path}")

# Example usage
if __name__ == "__main__":
    input_directory = "."  # Change this to your actual folder path
    output_file = "merged_output.pdf"
    merge_pdfs_with_titles(input_directory, output_file)

You need to start by installing required libraries:

pip install PyPDF2 reportlab