Extract all Images from PDF (PyMuPDF, Pillow)

extractImagesPDF.py

#!/usr/bin/env python3

# [Extract all Images from PDF in Python](https://aliarefwriorr.medium.com/extract-all-images-from-pdf-in-python-cda3dc195abd)

import io
import fitz
import os
import PIL.Image
import requests

def downloadPDF(url: str, filename: str):
    print(f'downloading {url}...')
    with open(filename, mode='wb') as pdf:
        pdf.write(requests.get(url).content)

def extract_images(pdf: fitz.Document, page: int, imgDir: str = 'img'):
    imageList = pdf[page].get_images()
    os.makedirs(imgDir, exist_ok=True)
    if imageList:
        print(page)
        for idx, img in enumerate(imageList, start=1):
            data = pdf.extract_image(img[0])
            with PIL.Image.open(io.BytesIO(data.get('image'))) as image:
                image.save(f'{imgDir}/{page}-{idx}.{data.get("ext")}', mode='wb')

def main(url: str = 'https://cds.cern.ch/record/357153/files/HCAL_TDR1997.pdf'):
    filename = url.split('/')[-1]
    downloadPDF(url=url, filename=filename)
    pdf = fitz.open(filename)
    for page in range(pdf.page_count):
        extract_images(pdf, page)

if __name__ == '__main__':
    main()

extractImagesPDF.sh

#!/usr/bin/env bash

python3 -m venv pymupdf
source pymupdf/bin/activate
python3 -m pip install PyMuPDF Pillow
python3 -m extractImagesPDF

Thanks a lot for this script. Does it have a license? I want to create derivative changes by creating a bigger python program.

I would suggest you contact the author of the linked article (Extract all Images from PDF in Python) since the code derives from there.

Thank you, I will contact him