pdf_splitter.py

import os
import pdfplumber
from reportlab.pdfgen import canvas
import shutil

# Check if "io" folder exists
if not os.path.exists("io"):
    os.makedirs("io")
    print("The 'io' directory has been created. Please place your input PDF file in the 'io' directory and run the program again.")
    exit()

# List files in "io" directory
files = os.listdir("io")
pdf_files = [f for f in files if f.endswith('.pdf')]

if len(pdf_files) == 0:
    print("No PDF files found in the 'io' directory. Please add a PDF file and run the program again.")
    exit()
elif len(pdf_files) == 1:
    input_pdf_path = os.path.join("io", pdf_files[0])
    use_file = input(f"Found one PDF file: {pdf_files[0]}. Do you want to use this file? (y/n): ")
    if use_file.lower() != 'y':
        print("Please place the desired PDF file in the 'io' directory and run the program again.")
        exit()
else:
    file_name = input("Enter the PDF file name in the 'io' directory: ")
    if not file_name.endswith('.pdf'):
        file_name += '.pdf'
    input_pdf_path = os.path.join("io", file_name)

output_pdf_path = input_pdf_path.replace(".pdf", "_split.pdf")

# Parameters
split_height = 841.89  # Height for A4 size in points
page_width = 595.28    # Width of A4 size in points

# Create "tmp" directory if not exists
tmp_dir = "tmp"
if not os.path.exists(tmp_dir):
    os.makedirs(tmp_dir)

# Open the PDF with pdfplumber
with pdfplumber.open(input_pdf_path) as pdf:
    page = pdf.pages[0]  # Assuming the PDF has only one long page
    full_height = page.height

    # Calculate the number of splits needed
    num_splits = int(full_height // split_height) + 1

    # Create a new PDF to save the split pages
    c = canvas.Canvas(output_pdf_path, pagesize=(page_width, split_height))

    for i in range(num_splits):
        # Define the crop box for each section
        top = full_height - (i * split_height)
        bottom = max(top - split_height, 0)

        # Extract the cropped image
        cropped_page = page.within_bbox((0, bottom, page_width, top))

        # Render the cropped image onto the canvas
        img_path = os.path.join(tmp_dir, f"temp_page_{i}.png")
        cropped_image = cropped_page.to_image(resolution=300)
        cropped_image.save(img_path)  # Save the cropped section as an image with higher resolution

    # Flip the order of the pages
    for i in range(num_splits - 1, -1, -1):
        img_path = os.path.join(tmp_dir, f"temp_page_{i}.png")
        c.drawImage(img_path, 0, 0, width=page_width, height=split_height)
        c.showPage()

    # Save the final PDF
    c.save()

# Clean up the "tmp" directory
shutil.rmtree(tmp_dir)

print("PDF split and saved successfully!")

requirements.txt

pdfplumber
reportlab