Last active
August 26, 2024 07:42
-
-
Save wecacuee/f1e92d421312b7c7c1907667f4f3a318 to your computer and use it in GitHub Desktop.
Anonymize pdf annotations and metadata
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
| #!/usr/bin/env python | |
| try: | |
| import fitz | |
| except ImportError as e: | |
| import subprocess | |
| print('Trying to install pip install PyMuPDF') | |
| subprocess.call("pip install PyMuPDF".split()) | |
| print('Try pip install PyMuPDF') | |
| raise | |
| import sys | |
| if len(sys.argv) < 2: | |
| raise ValueError("Please provide a pdf to anonymize") | |
| if len(sys.argv) < 3: | |
| outfilename = filename.replace('.pdf', '.anon.pdf') | |
| else: | |
| outfilename = sys.argv[2] | |
| filename = sys.argv[1] | |
| doc = fitz.open(filename) | |
| metadata = doc.metadata | |
| for k, v in metadata.items(): | |
| if k not in ['format']: # retain some metadata | |
| metadata[k] = '' | |
| doc.set_metadata(metadata) | |
| for page in doc: | |
| for annot in page.annots(): | |
| info = annot.info | |
| info['title'] = '' | |
| annot.set_info(info) | |
| annot.update() | |
| doc.save(outfilename) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
On Linux (Fedora) script is not working as expected.
frontendandfritzhad to be installed manually.