fabriquedoc-backend/convert_pdf.py

"""     
    Fabrique à documents
    Copyright (C) 2023  François Pelletier

    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU Affero General Public License as published
    by the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.

    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU Affero General Public License for more details.

    You should have received a copy of the GNU Affero General Public License
    along with this program.  If not, see <https://www.gnu.org/licenses/>. 
"""


import os

from wand.color import Color
from wand.image import Image


def convert_pdf(filename, filetype, output_path, resolution=300):
    """ Convert a PDF into images.

        All the pages will give a single png file with format:
        {pdf_filename}-{page_number}.png

        The function removes the alpha channel from the image and
        replace it with a white background.
    """
    all_pages = Image(filename=filename, resolution=resolution)
    for i, page in enumerate(all_pages.sequence):
        with Image(page) as img:
            img.format = filetype
            img.background_color = Color('white')
            img.alpha_channel = 'remove'

            image_filename = os.path.splitext(os.path.basename(filename))[0]
            image_filename = f'{image_filename}-{i:03}.{filetype}'
            image_filename = os.path.join(output_path, image_filename)

            img.save(filename=image_filename)