extract image from pdf

extract_image_from_pdf.py

import os
from zipfile import ZipFile
import xml.etree.ElementTree as ET
from PIL import Image

pptx_path="pptx.pptx"
# Unzip the pptx file to explore its content
with ZipFile(pptx_path, 'r') as zip_ref:
    zip_ref.extractall("pptx_extracted")

# Path to the extracted folder
extracted_path = "pptx_extracted"
output_dir = "output"
# Function to extract images from ppt/media folder
def extract_images_from_pptx(extracted_path, output_dir):
    media_path = os.path.join(extracted_path, "ppt", "media")
    if os.path.exists(media_path):
        for media_file in os.listdir(media_path):
            if media_file.endswith(('.png', '.jpeg', '.jpg')):
                img = Image.open(os.path.join(media_path, media_file))
                img = img.convert("RGBA")  # Ensure transparency
                img.save(os.path.join(output_dir, media_file))

# Extract images
extract_images_from_pptx(extracted_path, output_dir)

# List the extracted images
extracted_images = os.listdir(output_dir)
#extracted_images