Crop, split and collate PDFs using pyPdf

collate.py

import argparse

from pyPdf import PdfFileWriter, PdfFileReader


def create_parsers():

    p = argparse.ArgumentParser(
        prog='crop',
        description='"%(prog)s" crop pdfs',
    )

    p.add_argument(
        '-i', '--input',
        type=str,
        nargs='*',
        required=True,
        help='Input pdf',
    )

    p.add_argument(
        '-o', '--output',
        type=str,
        required=True,
        help='Output pdf',
    )

    return p


if __name__ == '__main__':
    
    p = create_parsers()
    args = p.parse_args()

    input_filename = args.input
    output_filename = args.output

    if len(input_filename) < 2:
        raise("Input must contain more than one document")

    for i in range(len(input_filename)-1):
        left_pdf  = PdfFileReader(file(input_filename[i], "rb"))
        right_pdf = PdfFileReader(file(input_filename[i+1], "rb"))
        output = PdfFileWriter()

        # get the first page from each pdf
        left_page = left_pdf.pages[0]
        right_page = right_pdf.pages[0]

        page = output.addBlankPage(
            width=left_page.mediaBox.getWidth() + right_page.mediaBox.getWidth(),
            height=max(left_page.mediaBox.getHeight(), right_page.mediaBox.getHeight()),
        )

        # draw the pages on that new page
        page.mergeTranslatedPage(left_page, 0, 0)
        page.mergeTranslatedPage(right_page, left_page.mediaBox.getWidth(), 0)

        # write to file
        outputStream = file(output_filename, "wb")
        output.write(outputStream)
        outputStream.close()

crop.py

#!/usr/bin/python

import argparse
from pyPdf import PdfFileWriter, PdfFileReader


def create_parsers():

    p = argparse.ArgumentParser(
        prog='crop',
        description='"%(prog)s" crop pdfs',
    )

    p.add_argument(
        '-i', '--input',
        type=str,
        required=True,
        help='Input pdf',
    )

    p.add_argument(
        '-o', '--output',
        type=str,
        required=True,
        help='Output pdf',
    )

    p.add_argument(
        '-b', '--bbox',
        type=float,
        nargs='*',
        required=True,
        help='Bounding box [y0 y1 x0 x1]',
    )

    return p


if __name__ == '__main__':
    
    p = create_parsers()
    args = p.parse_args()

    input_filename = args.input
    output_filename = args.output
    bounding_box = args.bbox

    input1 = PdfFileReader(file(input_filename, "rb"))
    output = PdfFileWriter()

    numPages = input1.getNumPages()
    print "document has %s pages." % numPages

    for i in range(numPages):
        page = input1.getPage(i)
        print page.mediaBox.getUpperRight_x(), page.mediaBox.getUpperRight_y()
        page.trimBox.lowerLeft = (bounding_box[0], bounding_box[2])
        page.trimBox.upperRight = (bounding_box[1], bounding_box[3])
        page.cropBox.lowerLeft = (bounding_box[0], bounding_box[2])
        page.cropBox.upperRight = (bounding_box[1], bounding_box[3])
        output.addPage(page)

    outputStream = file(output_filename, "wb")
    output.write(outputStream)
    outputStream.close()

split.py

#!/usr/bin/python

import os
import argparse
from pyPdf import PdfFileWriter, PdfFileReader


def create_parsers():

    p = argparse.ArgumentParser(
        prog='crop',
        description='"%(prog)s" split pdfs',
    )

    p.add_argument(
        '-i', '--input',
        type=str,
        required=True,
        help='Input pdf',
    )

    return p

if __name__ == '__main__':
    
	p = create_parsers()
	args = p.parse_args()

	input_filename = args.input
	output_filename = os.path.splitext(input_filename)[0]
	output_extension = os.path.splitext(input_filename)[-1]

	inputpdf = PdfFileReader(open(input_filename, "rb"))

	for i in xrange(inputpdf.numPages):
		output = PdfFileWriter()
		output.addPage(inputpdf.getPage(i))

		with open(output_filename + str(i) + output_extension, "wb") as outputStream:
			output.write(outputStream)