A program to extract ISBN from an EPUB document

ISBN-of-EPUB.py

import argparse
import re
from zipfile import ZipFile


def get_id_by_tag(text: str):
	i1 = text.find('unique-identifier="')
	i2 = text.find('"', i1 + 19)
	id_start = text.find(">", text.find(text[i1 + 19:i2], i2)) + 1
	return text[id_start:text.find("<", id_start)]


def get_id_by_structure(text: str, structure: str = 'ISBN'):
	if structure == 'ISBN':
		try:
			# ISBN is 13 digits since 2007 and was 10 digits before
			return next(filter(lambda s: True if len(s) in [10, 13] else False, re.sub('[^0-9]', ' ', text).split()))
		except StopIteration:
			raise ValueError("Error: Document does not contain an ISBN")


if __name__ == '__main__':
	parser = argparse.ArgumentParser()
	parser.add_argument("file_path", help="EPUB file path")
	args = parser.parse_args()
	with ZipFile(args.file_path) as z:
		text = z.read(next(filter(lambda n: n.endswith('.opf'), z.namelist()))).decode('utf-8')
		print("ID by ISBN structure:", get_id_by_structure(text))
		print("ID by identifier tag:", get_id_by_tag(text))