Process a scan of double slides per page to single slide per page

process_signaux_et_systemes_polycop

#!/usr/bin/env python3
from PyPDF2 import PdfFileWriter, PdfFileReader
import argparse
import copy

parser = argparse.ArgumentParser()
parser.add_argument('original',
                    help='input PDF.',
                    metavar='INPUTFILE',)
parser.add_argument('output',
                    help='output PDF.',
                    metavar='OUTPUTFILE')

parser.add_argument('--start',
                    help='First page to add to output.',
                    metavar='START',
                    type=int)
parser.add_argument('--end',
                    help='Last page to add to output.',
                    metavar='END',
                    type=int)
args = parser.parse_args()


src = PdfFileReader(open(args.original, 'rb'))
out = PdfFileWriter()

if args.end:
    end = args.end
else:
    end = src.getNumPages()

for i in range(args.start - 1, end, 2):
    # upper slide
    page = copy.copy(src.getPage(i))
    dim = (
        page.mediaBox.getLowerLeft_x(),
        (page.mediaBox.getLowerLeft_y() + page.mediaBox.getUpperRight_y())/2
    )
    page.mediaBox.lowerLeft = dim
    out.addPage(page)

    # lower slide
    page = copy.copy(src.getPage(i))
    dim = (
        page.mediaBox.getUpperRight_x(),
        (page.mediaBox.getLowerLeft_y() + page.mediaBox.getUpperRight_y())/2
    )
    page.mediaBox.upperRight = dim
    out.addPage(page)

out.write(open(args.output, 'wb'))