gctools/pdf/pdf_watermark.py

import PyPDF2
import plac
from pathlib import Path
from doc2pdf import doc2pdf


def add_watermark(input_file):
    watermark_file = 'c:/tools/template/Briefbogen_GC_Jahnstr_GmbH.pdf'
    output_file = Path(input_file).parent.joinpath("mit_Briefpapier", Path(input_file).name)
    if not output_file.parent.exists():
        output_file.parent.mkdir()

    with open(input_file, "rb") as filehandle_input:
        # read content of the original file
        pdf = PyPDF2.PdfFileReader(filehandle_input)

        with open(watermark_file, "rb") as filehandle_watermark:
            # read content of the watermark
            watermark = PyPDF2.PdfFileReader(filehandle_watermark)
            # get first page of the watermark PDF
            first_page_watermark = watermark.getPage(0)

            # create a pdf writer object for the output file
            pdf_writer = PyPDF2.PdfFileWriter()

            # get first page of the original PDF
            for i in range(pdf.getNumPages()):
                current_page = pdf.getPage(i)

                # merge the two pages
                current_page.mergePage(first_page_watermark)

                # add page
                pdf_writer.addPage(current_page)

            with open(output_file, "wb") as filehandle_output:
                # write the watermarked file to the new file
                pdf_writer.write(filehandle_output)


def add_watermark_to_folder(base_dir):
    for filename in Path(base_dir).glob('*.doc'):
        doc2pdf(str(filename))

    for filename in Path(base_dir).glob('*.pdf'):
        add_watermark(str(filename))
        print(filename.name)


if __name__ == '__main__':
    plac.call(add_watermark_to_folder)
    # add_watermark_to_folder(str(Path(__file__).parent) + '/data/')