PDF/reduce_pdf_size.py

import fitz  # PyMuPDF
import os

def extract_images_from_pdf(input_pdf: str, output_dir: str = "extracted_images"):
	"""
	Extract all images from a PDF and save them as individual image files.

	Args:
		input_pdf (str): Path to the PDF file.
		output_dir (str): Directory to save extracted images. Default is 'extracted_images'.

	Returns:
		List of saved image file paths.
	"""
	# Ensure output directory exists
	os.makedirs(output_dir, exist_ok=True)

	# Open the PDF
	pdf = fitz.open(input_pdf)
	saved_images = []

	print(f"Extracting images from: {input_pdf}")

	for page_num in range(len(pdf)):
		page = pdf[page_num]
		images = page.get_images(full=True)

		for img_index, img in enumerate(images):
			xref = img[0]
			base_image = pdf.extract_image(xref)
			image_bytes = base_image["image"]
			image_ext = base_image["ext"]
			image_filename = f"page{page_num+1}_img{img_index+1}.{image_ext}"

			output_path = os.path.join(output_dir, image_filename)
			with open(output_path, "wb") as img_file:
				img_file.write(image_bytes)

			saved_images.append(output_path)
			print(f"Saved: {output_path}")

	pdf.close()

	if saved_images:
		print(f"✅ Extracted {len(saved_images)} images to: {output_dir}")
	else:
		print("⚠️ No images found in the PDF.")

	return saved_images

# Example usage
extract_images_from_pdf("../CaptionCreator/media/Jebin passport.pdf")