Splitting PDFs programmatically using a list of set ranges

demo.py

"""Demonstration of provided split utility.

Divides a PDF into several chunks and eliminates certain pages from each pdf.
"""

from splits import splits

INPUT_FILE = "./merged.pdf"
OUTPUT_DIRECTORY = "./out"
PAGE_SPLITS = "1-10,11-20,21-30,31-42,43-52,53-64,65-74,75-86,87-98,99-110,111-122,123-134,135-146,147-158,159-168,169-180,181-192,193-204,205-216,217-228,229-240,241-250,251-262,263-274,275-284,285-296,297-308,309-320,321-332,333-344,345-356,357-368,369-380,381-392,393-404,405-416"


def filter_pages_6_7(j: int, start: int, end: int) -> bool:
    """Filters out pages 6 and 7 for each PDF"""
    page_index = j - start + 2
    num_pages = end - start + 1
    return num_pages > 10 and page_index in (6, 7)


def main():
    splits(INPUT_FILE, PAGE_SPLITS, OUTPUT_DIRECTORY, filter_pages_6_7)


if __name__ == '__main__':
    main()

splits.py

"""Splits a PDF based on provided comma-separated page counts.

Below, the comma-separated splits may look like the following:

    1-10, 11-20, 21-30

The ranges overlap if desired.

Usage:
    split.py <input> <splits> [options]

Options:
    -o --out        Output directory [default: ./]
"""

from PyPDF2 import PdfFileWriter, PdfFileReader

import docopt

from typing import Callable

import os.path


def splits(input_filename: str, sections: str, out_directory: str,
          filter_pages: Callable[[int, int], bool]) -> None:
    """Splits the provided PDF given the provided comma-separated sections."""
    input1 = PdfFileReader(open(input_filename, "rb"))

    for i, section in enumerate(sections.split(',')):
        output = PdfFileWriter()
        print(' * [INFO] Starting packet %d' % i)

        start, end = map(int, section.strip().split('-'))
        for j in range(start - 1, end):
            if filter_pages(j, start, end):
                continue
            output.addPage(input1.getPage(j))

        os.makedirs(out_directory, exist_ok=True)
        output_filename = os.path.join(out_directory, "output-%d.pdf" % i)
        output_stream = open(output_filename, "wb")
        output.write(output_stream)


def main():
    arguments = docopt.docopt(__doc__, version='1.0')
    split(arguments['<input>'], arguments['<sections>'], arguments['--out'])


if __name__ == '__main__':
    main()