docx2txt

import docx2txt import os # Assuming 'my_document.docx' exists in the current directory # and 'extracted_images' is a directory for image output. # If 'my_document.docx' does not exist, create a dummy one for testing. if not os.path.exists('my_document.docx'): print("Please create a dummy 'my_document.docx' file for this example.") # Example: Create a simple dummy docx (requires python-docx library) # from docx import Document # document = Document() # document.add_paragraph('This is a test document for docx2txt.') # document.save('my_document.docx') # Extract text text = docx2txt.process("my_document.docx") print("Extracted Text:\n", text) # Extract text and images to a specified directory image_dir = 'extracted_images' if not os.path.exists(image_dir): os.makedirs(image_dir) text_with_images = docx2txt.process("my_document.docx", image_dir) print(f"\nExtracted Text (images saved to {image_dir}):\n", text_with_images)