Created
September 8, 2025 13:43
-
-
Save dragon-dxw/c7b42a887e5258a3d205e1b9f5a6a551 to your computer and use it in GitHub Desktop.
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
| from zipfile import ZipFile | |
| import lxml.etree | |
| import sys | |
| REDACTION_STRING = "" | |
| namespaces = { | |
| "cp": "http://schemas.openxmlformats.org/package/2006/metadata/core-properties", | |
| "dc": "http://purl.org/dc/elements/1.1/", | |
| "w15": "http://schemas.microsoft.com/office/word/2012/wordml", | |
| "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main", | |
| } | |
| forbidden_attributes = ["w15:author", "w15:userId", "w:author"] | |
| forbidden_tags = ["cp:lastModifiedBy", "dc:creator"] | |
| filename=sys.argv[1] | |
| with ZipFile(filename+".out.docx", "w") as archive_output, ZipFile(filename, "r") as archive_input: | |
| for archive_filename in archive_input.namelist(): | |
| with archive_input.open(archive_filename, "r") as f: | |
| xml = f.read() | |
| root = lxml.etree.fromstring(xml) | |
| for attribute in forbidden_attributes: | |
| attribute_namespace, _, attribute_name = attribute.partition(":") | |
| for node in root.xpath(f"//*[@{attribute}]", namespaces=namespaces): | |
| node.attrib[f"{{{namespaces[attribute_namespace]}}}{attribute_name}"] = REDACTION_STRING | |
| for tag in forbidden_tags: | |
| for node in root.xpath(f"//{tag}", namespaces=namespaces): | |
| node.text = REDACTION_STRING | |
| output_xml = lxml.etree.tostring(root) | |
| archive_output.writestr(archive_filename, output_xml) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment