Created
June 6, 2024 03:45
-
-
Save sujaldev/bb0fb7393969413490f5b00431b85330 to your computer and use it in GitHub Desktop.
Removes watermark from PDF
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # "Borrowed" from https://github.com/pymupdf/PyMuPDF/discussions/1855 | |
| import sys | |
| import argparse | |
| from pathlib import Path | |
| import pymupdf | |
| parser = argparse.ArgumentParser( | |
| prog="watermark-remover", | |
| description="Remove watermark from PDF" | |
| ) | |
| parser.add_argument("input") | |
| parser.add_argument("output") | |
| args = parser.parse_args() | |
| inputfile = Path(args.input).resolve() | |
| outputfile = Path(args.output).resolve() | |
| doc = pymupdf.open(inputfile) | |
| for page in doc: | |
| page.clean_contents() | |
| xref = page.get_contents()[0] | |
| cont = bytearray(page.read_contents()) | |
| if cont.find(b"/Subtype/Watermark") > 0: | |
| print("Watermark detected.") | |
| while True: | |
| start = cont.find(b"/Artifact") # start of definition | |
| if start < 0: break | |
| end = cont.find(b"EMC", start) # end of definition | |
| cont[start - 2 : end + 3] = b"" # remove the full definition source "q ... EMC" | |
| doc.update_stream(xref, cont) # replace the original source | |
| doc.ez_save(outputfile) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment