Automation & scripting

import zipfile
import re
from pathlib import Path

def docx_to_text_unzip_xml(docx_path: str) -> str:
    """Extract plain text from a .docx file by unzipping and parsing document.xml."""
    docx_path = Path(docx_path)
    if not docx_path.exists():
        raise FileNotFoundError(f"File not found: {docx_path}")

   …