무거운 PDF를 Pythonista로 가볍고 분할한 이야기

📃 종이 자료에 인쇄

🐍 Python으로 해결

# -*- coding: utf-8 -*-

import os
import appex

from PIL import Image
from PyPDF2 import PdfFileWriter, PdfFileReader

div = 6

def imageWriter(page0):
    xObject = page0['/Resources']['/XObject'].getObject()
    for obj in xObject:
        if xObject[obj]['/Subtype'] == '/Image':
            size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
            data = xObject[obj].getData()
            if xObject[obj]['/ColorSpace'] == '/DeviceRGB':
                mode = "RGB"
            else:
                mode = "P"
            if xObject[obj]['/Filter'] == '/FlateDecode':
                img = Image.frombytes(mode, size, data)
                img.save(obj[1:] + ".png")
            elif xObject[obj]['/Filter'] == '/DCTDecode':
                with open(obj[1:] + ".jpg", "wb") as img:
                    img.write(data)
            elif xObject[obj]['/Filter'] == '/JPXDecode':
                with open(obj[1:] + ".jp2", "wb") as img:
                    img.write(data)

def main():
    src = appex.get_file_path() 
    src = PdfFileReader(src, 'rb')
    items = [range(i, min(i + div, src.numPages)) for i in range(0, src.numPages, div)]

    if not os.path.exists('pdf'): 
        os.mkdir('pdf')

    for i, lst in enumerate(items):
        dst = PdfFileWriter()
        for j in lst:
            dst.addPage(src.getPage(j))
            with open('pdf/%03d.pdf' % i, 'wb') as out:
                dst.removeLinks()
                dst.write(out)

if __name__ == '__main__':
    main()

요약