Как с помощью Python из файла Word удалить ненужные изображения и таблицы?

import os
import docx
 
from docx import Document
import ipywidgets as widgets
from IPython.display import display, clear_output
# from google.colab import files
import io
from PIL import Image
from fastapi import Path
from docx.enum.shape import WD_INLINE_SHAPE_TYPE
from docx.text.run import Run
from docx.oxml.ns import qn
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
from structlog import get_logger
 
logger = get_logger(__name__)
 
matplotlib.use('Agg')
 
path_str = os.getcwd()
 
 
class WordEditor:
 
    def __init__(self, file):
        self.file = file
        self.document = None
        self.tables = []
        self.images = []
 
    def load_file(self):
        if isinstance(self.file, str):
            with open(self.file, 'rb') as f:
                self.document = Document(f)
        else:
            self.document = Document(io.BytesIO(self.file))
        return self.document
 
    def get_empty_tables(self):
        for i, table in enumerate(self.document.tables):
            if all(not cell.text.strip() for row in table.rows for cell in row.cells):
                self.tables.append(table)
        return self.tables
 
    def get_images(self):
        """Extract images from both inline shapes and shapes in Word document"""
        images = []
 
        try:
            # Handle inline shapes (embedded images)
            for shape in self.document.inline_shapes:
                try:
                    if shape.type == WD_INLINE_SHAPE_TYPE.PICTURE:
                        rId = shape._inline.graphic.graphicData.pic.blipFill.blip.embed
                        image_part = self.document.part.related_parts[rId]
                        if image_part and hasattr(image_part, 'blob'):
                            images.append({
                                'image_data': image_part.blob,
                                'content_type': image_part.content_type
                            })
                except Exception as e:
                    logger.error(f"Error processing inline shape: {str(e)}")
 
            # Handle floating shapes
            for rel in self.document.part.rels.values():
                try:
                    if "image" in rel.target_part.content_type:
                        self.images.append(rel.target_part)
                except Exception as e:
                    logger.error(f"Error processing relation: {str(e)}")
 
        except Exception as e:
            logger.error(f"Error accessing document: {e}")
 
        logger.info(f"Found {len(images)} images in document")
        return self.images
 
    def remove_empty_tables(self):
        """Remove empty tables from document using the result of get_empty_tables."""
        removed_count = 0
        for table in self.tables:
            table._element.getparent().remove(table._element)
            removed_count += 1
        return removed_count
 
    def remove_images(self):
        """Remove all images from document use self.images."""
        removed_count = 0
        for image in self.images:
            del self.document.part.rels[image.rId]
            removed_count += 1
        return removed_count
 
    def save_new_document(self):
        """Save self.document with new name with prefix cleared_"""
        new_filename = os.path.join(path_str, "media/cleared_document.docx")
        self.document.save(new_filename)
        return new_filename
if __name__ == "__main__":
    print("path:", path_str)
    filename = os.path.join(path_str, "media/worddoc.docx")
    executor = WordEditor(file=filename)
    executor.load_file()
    executor.get_empty_tables()
    executor.get_images()
    executor.remove_empty_tables()
    executor.remove_images()
    executor.save_new_document()