import fitz
import io
import tkinter as tk
from tkinter import filedialog
from PIL import Image, ImageTk
import pydicom
import os
import matplotlib.pyplot as plt
from pathlib import Path
 
 
def select_pdf_file():
    """Load images from a PDF file"""
    global images
 
    if file := filedialog.askopenfilename(filetypes=[("PDF", "*.pdf")]):
        images = []
        with fitz.open(file) as doc:
            for page in doc:
                for xref, *_ in page.get_images():
                    image = doc.extract_image(xref)
                    images.append(Image.open(io.BytesIO(image["image"])))
        show_image(0)
def show_image(index):
    """Display selected image"""
    global img_index
 
    canvas.delete("all")
    size = (canvas.winfo_width(), canvas.winfo_height())
    if images:
        img_index = index % len(images)
        image = images[img_index].copy()  # Keep original image
        image.thumbnail(size)
        image = ImageTk.PhotoImage(image)
        canvas.create_image(
            size[0] / 2, size[1] / 2, anchor=tk.CENTER, image=image
        )
        canvas.image = image
    else:
        canvas.create_text(
            size[0] / 2, size[1] / 2, anchor=tk.CENTER, text="No Images",
            fill="white", font=('Helvetica 15 bold')
        )
images = []
img_index = 0
root = tk.Tk()
canvas = tk.Canvas(root, bg="black")
canvas.bind("<Configure>", lambda event: show_image(img_index))
canvas.pack(padx=10, pady=10, side=tk.TOP, expand=True, fill=tk.BOTH)
 
bbar = tk.Frame(root)
bbar.pack(side=tk.TOP, fill=tk.X, padx=10, pady=(0, 10))
button = tk.Button(bbar, text="<<", command=lambda: show_image(img_index-1))
button.pack(side=tk.LEFT)
button = tk.Button(bbar, text="Select PDF", command=select_pdf_file)
button.pack(side=tk.LEFT, expand=True, fill=tk.X)

button = tk.Button(bbar, text=">>", command=lambda: show_image(img_index+1))
button.pack(side=tk.LEFT)

root.mainloop()

path2pdf = '/home/pedro/pdfs/pdfs/doc3.pdf'
savepath = '/home/pedro/pdfExtractedPages/pdf2jpg/'
reader = PdfReader(path2pdf)
page = reader.pages[0]
count = 0
for image_file_object in page.images:
    with open(savepath + str(count) + image_file_object.name, "wb") as fp:
        fp.write(image_file_object.data)
        count += 1

(Oct-07-2023, 02:48 PM)Pedroski55 Wrote: I would say, your source pdf file only contains 2 images, because this also only gives me 2 images.

path2pdf = '/home/pedro/pdfs/pdfs/doc3.pdf'
savepath = '/home/pedro/pdfExtractedPages/pdf2jpg/'
reader = PdfReader(path2pdf)
page = reader.pages[0]
count = 0
for image_file_object in page.images:
    with open(savepath + str(count) + image_file_object.name, "wb") as fp:
        fp.write(image_file_object.data)
        count += 1

Make a pdf which definitely contains 3 images and try that!

(Oct-08-2023, 07:14 AM)cybertooth Wrote: while this pdf was made using 3 images

(Oct-08-2023, 08:18 AM)DPaul Wrote: Surely, if it's a pdf made of photocopies with pictures on them, it can't isolate them ?

Output:
montage -mode concatenate b.jpg b.jpg m.jpg

(Oct-08-2023, 08:27 AM)Gribouillis Wrote: For example the following image is a single image, it was created with the linux command