pdf_to_image.py

"""

Dockerfile

FROM python:3.6

RUN apt-get install -y ghostscript \
  libmagickwand-dev
  
RUN pip install wand PyPDF2

"""
import io
from pathlib import Path

import PyPDF2
from wand.image import Image

IMAGE_TYPE = 'jpeg'
save_dir = 'my-save-dir'


pdf_bytes = io.BytesIO(raw)


def image_etl(pdf_bytes, save_path, resolution=200):
    pdf = PyPDF2.PdfFileReader(pdf_bytes)

    writer = PyPDF2.PdfFileWriter()
    writer.addPage(pdf.getPage(0))

    pdf_bytes = io.BytesIO()
    writer.write(pdf_bytes)
    pdf_bytes.seek(0)

    img = Image(file=pdf_bytes, resolution=resolution)
    img.convert(IMAGE_TYPE)

    with img.convert(IMAGE_TYPE) as converted:
        converted.save(filename=str(save_path))

    return img

try:
    image_etl(pdf_bytes, image_path)
except Exception as e:
    print("Failed converting pdf to image", e)