Created
February 28, 2026 08:47
-
-
Save Romern/eaa2647c4553ea8c9fdd1dbe4dd0cb85 to your computer and use it in GitHub Desktop.
Remove pre-rendered versions of images and subdocuments in LibreOffice Documents
This file contains hidden or 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
| import zipfile | |
| import re | |
| import sys | |
| """ | |
| <draw:image xlink:href="Pictures/1000000100000538000005385B1FE860.png" xlink:type="simple" xlink:show="embed" xlink:actuate="onLoad" draw:mime-type="image/png"/> | |
| <draw:image xlink:href="./ObjectReplacements/Object 1" xlink:type="simple" xlink:show="embed" xlink:actuate="onLoad"/> | |
| """ | |
| regex = re.compile('<draw:image[^>]*(png|ObjectReplacements)[^>]*>') | |
| def remove_pattern_from_zip(input_zip, output_zip): | |
| with zipfile.ZipFile(input_zip, 'r') as zip_in: | |
| with zipfile.ZipFile(output_zip, 'w') as zip_out: | |
| for item in zip_in.infolist(): | |
| if 'ObjectReplacements' in item.filename or '.png' in item.filename: | |
| continue | |
| content = zip_in.read(item.filename) | |
| if item.filename.endswith('.xml'): | |
| text_content = content.decode('utf-8') | |
| modified_content = regex.sub('', text_content) | |
| zip_out.writestr(item, modified_content.encode('utf-8')) | |
| else: | |
| zip_out.writestr(item, content) | |
| if __name__ == "__main__": | |
| if len(sys.argv) != 3: | |
| print("Usage: python remove_thumbnails.py <input_zip> <output_zip>") | |
| sys.exit(1) | |
| input_file = sys.argv[1] | |
| output_file = sys.argv[2] | |
| remove_pattern_from_zip(input_file, output_file) | |
| print(f"Processed zip saved to: {output_file}") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment