Python script to remove watermark

remove_watermark.py

from pathlib import Path

from pypdf import PdfWriter
from pypdf.generic._data_structures import StreamObject

books_directory = Path("books")
export_directory = Path("export")
for input_filepath in books_directory.glob("*.pdf"):
    output_filepath = export_directory / input_filepath.name
    print("=====", output_filepath, "=====")
    writer = PdfWriter(clone_from=str(input_filepath))

    for page in writer.pages:
        contents = page._get_contents_as_bytes()

        watermark = contents.find(b'/Watermark')
        if watermark > -1:
            contents = contents[:watermark - 1]
            stream = StreamObject()
            stream.set_data(contents)
            page.replace_contents(stream)

    with open(output_filepath, "wb") as f:
        writer.write(f)