Splits a Eurika math pdf into separate lessons

eurika_math_pdf_splitter.py

import os
import re
import PyPDF2


def split_eurika_book(pdf_path, page_list, *, name_format='G{grade} - M{module} L{lesson}.pdf'):
    """Splits a PDF of a Eurika Math book into separate sections based on
    a list of page numbers provided.
    """
    pattern = re.compile(r'[gG](\d+).[mM](\d+)')
    match = pattern.search(pdf_path)
    grade, module = match.groups()

    with open(pdf_path, 'rb') as pdf_orig_fp:
        pdf_reader = PyPDF2.PdfFileReader(pdf_orig_fp)
        page_list.append(pdf_reader.numPages + 1)

        pairwise = zip(page_list, page_list[1:])
        for lesson, (start, stop) in enumerate(pairwise, start=1):
            filename = name_format.format(grade=grade, module=module, lesson=lesson)
            with open(filename, 'wb') as pdf_new_fp:
                pdf_writer = PyPDF2.PdfFileWriter()
                for page_num in range(start, stop):
                    page = pdf_reader.getPage(page_num - 1)
                    pdf_writer.addPage(page)
                pdf_writer.write(pdf_new_fp)

if __name__ == '__main__':
    # Unfortunately PyPDF2.extractText() returns an empty string on the Eurika books
    # therefore the page numbers for each lesson must be provided manually.
    grade6 = '/Users/meding/Downloads/Eurika/Math 6/g6_m1_student_wkbook_v1_3_1.pdf'
    pages6 = [2, 6, 11, 14, 19, 26, 31, 36, 43, 49, 55, 61, 65, 72, 78, 81, 86, 92, 98, 104]

    split_eurika_book(grade6, pages6)