The code i am using to extract the images is def extract_images_from_pdfs(pdf_list): import fitz # PyMuPDF output_dir = "C:/Users/""/"""/image" os.makedirs(output_dir, exist_ok=True) for pdf_path in pdf_list: pdf_name = os.path.splitext(os.path.basename(pdf_path))[0] # Open the PDF pdf_document = fitz.open(pdf_path) # Track the count of images extracted per page image_count = 0 for page_num, page in enumerate(pdf_document): # Get the images on this page image_list = page.get_images(full=True) if not image_list: print(f"No images found on page {page_num+1} of {pdf_name}") continue # Process each image for img_index, img in enumerate(image_list): xref = img[0] base_image = pdf_document.extract_image(xref) if base_image: image_bytes = base_image["image"] image_ext = base_image["ext"] # Convert bytes to image image = Image.open(io.BytesIO(image_bytes)) # Save the image image_name = f"{pdf_name}_image_{image_count}.{image_ext}" image_path = os.path.join(output_dir, image_name) image.save(image_path) image_count += 1 pdf_document.close() print(f"Extracted {image_count} images from {pdf_name}") extract_images_from_pdfs(files_list) The input (files_list) is just a list containing all the names of my pdf's When i should get something like Could it be that the images on the PDF are encrypted / accessible and is there a work around for this. Any help is greatly appreciated. testingpdfexampaper.tiiny.site This is the URL for the PDF Continue reading...
