pdf_manager.py

import os
from pathlib import Path
from PyPDF2 import PdfReader, PdfWriter, PdfMerger


# ==========================================
# PDF Manager Configuration
# ==========================================

INPUT_FOLDER = Path("pdfs/input")
OUTPUT_FOLDER = Path("pdfs/output")


# ==========================================
# Create Required Folders
# ==========================================

def create_folders():
    INPUT_FOLDER.mkdir(parents=True, exist_ok=True)
    OUTPUT_FOLDER.mkdir(parents=True, exist_ok=True)


# ==========================================
# List PDF Files
# ==========================================

def list_pdfs():
    create_folders()

    pdf_files = list(INPUT_FOLDER.glob("*.pdf"))

    if not pdf_files:
        return []

    return pdf_files


# ==========================================
# Get PDF Information
# ==========================================

def get_pdf_info(file_path):
    try:
        reader = PdfReader(file_path)

        return {
            "name": Path(file_path).name,
            "pages": len(reader.pages),
            "size": round(
                os.path.getsize(file_path) / 1024,
                2
            )
        }

    except Exception as e:
        return {
            "error": str(e)
        }


# ==========================================
# Merge PDFs
# ==========================================

def merge_pdfs(pdf_files, output_name):
    create_folders()

    merger = PdfMerger()

    try:
        for pdf in pdf_files:
            merger.append(str(pdf))

        output_path = OUTPUT_FOLDER / output_name

        merger.write(str(output_path))
        merger.close()

        return output_path

    except Exception as e:
        merger.close()
        raise Exception(
            f"Failed to merge PDFs: {e}"
        )


# ==========================================
# Split PDF
# ==========================================

def split_pdf(file_path):
    create_folders()

    reader = PdfReader(file_path)

    pdf_name = Path(file_path).stem

    split_folder = (
        OUTPUT_FOLDER / f"{pdf_name}_pages"
    )

    split_folder.mkdir(
        parents=True,
        exist_ok=True
    )

    created_files = []

    for page_number, page in enumerate(
        reader.pages,
        start=1
    ):

        writer = PdfWriter()

        writer.add_page(page)

        output_path = (
            split_folder
            / f"{pdf_name}_page_{page_number}.pdf"
        )

        with open(output_path, "wb") as output_file:
            writer.write(output_file)

        created_files.append(output_path)

    return created_files


# ==========================================
# Extract Pages
# ==========================================

def extract_pages(
    file_path,
    start_page,
    end_page,
    output_name
):
    create_folders()

    reader = PdfReader(file_path)
    writer = PdfWriter()

    total_pages = len(reader.pages)

    if start_page < 1 or end_page > total_pages:
        raise ValueError(
            f"Page range must be between "
            f"1 and {total_pages}."
        )

    if start_page > end_page:
        raise ValueError(
            "Starting page cannot be greater "
            "than ending page."
        )

    for page_number in range(
        start_page - 1,
        end_page
    ):
        writer.add_page(
            reader.pages[page_number]
        )

    output_path = OUTPUT_FOLDER / output_name

    with open(output_path, "wb") as output_file:
        writer.write(output_file)

    return output_path


# ==========================================
# Rename PDF
# ==========================================

def rename_pdf(file_path, new_name):
    file_path = Path(file_path)

    if not new_name.lower().endswith(".pdf"):
        new_name += ".pdf"

    new_path = file_path.parent / new_name

    file_path.rename(new_path)

    return new_path


# ==========================================
# Delete PDF
# ==========================================

def delete_pdf(file_path):
    file_path = Path(file_path)

    if file_path.exists():
        file_path.unlink()
        return True

    return False