删除word文件元数据中的作者信息的脚本。

del_office_meta.py

from docx import Document
import sys
from pathlib import Path


def dump(obj):
    for attr in dir(obj):
        print("obj.%s = %r" % (attr, getattr(obj, attr)))


def delMeta(file):
    document = Document(file)
    cp = document.core_properties
    dump(cp)
    cp.author = ""
    cp.last_modified_by = ""
    print("after")
    dump(cp)
    basename = Path(file).stem
    document.save(basename + "_no_meta.docx")


if __name__ == '__main__':
    if len(sys.argv) != 2:
        print("usage: python {} xx.docx".format(sys.argv[0]))
        sys.exit()
    else:
        delMeta(sys.argv[1])