XObject PDf helper

xobject_pdf.py

import re
from io import BytesIO
from PIL import Image
from pdfrw.objects import PdfName
from pdfrw.findobjs import find_objects
from pdfrw import PdfReader, PdfWriter


original = "/tmp/expanded.pdf"
nuevo_file = "/tmp/nuevo.pdf"
regex = "\(data/res/(?P<image_filename>.*)\)"
regex_number = "img_(?P<number>.*).jpg"

reader = PdfReader(original, password="C9CD86F5401F4C808AE9CF2260A483C8")                                                                                                 

xobjects = list(find_objects(reader, valid_types=(PdfName.XObject,), valid_subtypes=(PdfName.Image,)))

def new_pdf(xobjects):
    for xobject in xobjects:
        if '/F' in xobject:
            #print(xobject)
            m = re.match(regex, xobject['/F'])
            if m:
                filename = m.groupdict()['image_filename']
                print(filename)

                image = Image.open(f"/tmp/images/{filename}")
                rgb_image = image
                if image.format != "JPEG" or image.mode == "L":
                    rgb_image = image.convert("RGB")
                xobject.stream = rgb_image.tobytes().decode('latin1')

    nuevo = PdfWriter(nuevo_file, trailer=reader)
    nuevo.write()

new_pdf(xobjects)