Ms Word Document Processing

import os
from pathlib import Path
from docling.backend.msword_backend import MsWordDocumentBackend
from docling.datamodel.base_models  import InputFormat
from docling.datamodel.document     import InputDocument
from docling.document_converter     import DocumentConverter

def process_word_document(input_file: str, output_dir: str = "output") -> None:
    """
    Process a Word document and extract its content and structure.
    
    Args:
        input_file (str): Path to the input Word document
        output_dir (str): Directory to save processed outputs
    """
    # Create output directory if it doesn't exist
    os.makedirs(output_dir, exist_ok=True)
    
    # Setup input path
    in_path = Path(input_file)
    if not in_path.exists():
        raise FileNotFoundError(f"Input file not found: {input_file}")
    
    try:
        # Initialize input document
        in_doc = InputDocument(
            path_or_stream=in_path,
            format=InputFormat.DOCX,
            backend=MsWordDocumentBackend
        )
        
        # Setup backend and convert
        backend = MsWordDocumentBackend(in_doc=in_doc, path_or_stream=in_path)
        doc     = backend.convert()
        
        # Extract and save text content
        text_output = Path(output_dir) / f"{in_path.stem}_content.txt"
        with open(text_output, 'w', encoding='utf-8') as f:
            f.write(doc.get_text())
        
        # Extract document structure
        print(f"\nDocument Structure:")
        print("-" * 20)
        print(f"Title: {doc.title}")
        print(f"Sections: {len(doc.sections)}")
        print(f"Paragraphs: {len(doc.paragraphs)}")
        
        # Process tables if any
        if doc.tables:
            print(f"\nTables found: {len(doc.tables)}")
            tables_output = Path(output_dir) / f"{in_path.stem}_tables.txt"
            with open(tables_output, 'w', encoding='utf-8') as f:
                for i, table in enumerate(doc.tables, 1):
                    f.write(f"\nTable {i}:\n")
                    f.write(str(table))
                    f.write("\n" + "-"*50 + "\n")
        
        print(f"\nProcessing complete! Outputs saved in: {output_dir}")
        
    except Exception as e:
        print(f"Error processing document: {str(e)}")

def main():
    # Example usage
    sample_doc = "word_sample.docx"
    process_word_document(sample_doc)

if __name__ == "__main__":
    main() 

Word Document Processor

Key Features

• Creates a reusable function process_word_document() that handles Word document processing
• Includes proper error handling and file checks
• Creates an output directory for processed files
• Extracts and saves:
  • Document text content
  • Document structure information
  • Tables (if present)
• Provides informative console output about the document structure

Usage Instructions

Setup Steps

• Save it to a file (e.g., word_processor.py)
• Make sure you have the docling library installed: pip install docling
• Place your Word document in the same directory (or provide the full path)
• Run the script: python word_processor.py

Output Files

The script creates an output directory containing:

• {filename}_content.txt: The extracted text content
• {filename}_tables.txt: Extracted tables (if any exist in the document)

Future Enhancements

• Support for other document formats
• More detailed content extraction
• Custom output formatting options
• Batch processing of multiple documents

© Kevin Luzbetak