Diff between two subsequent editions of an ebook alpha file

astlan-diff.py

#!/usr/bin/python3
# -*- coding: utf-8 -*-

import difflib
import epub
from bs4 import BeautifulSoup


def text_paras(book, href):
    soup = BeautifulSoup(book.read_item(href), 'lxml')
    return [x.get_text() for x in soup.find_all('p')]

book1 = epub.open_epub('/home/mikael/astlan/Apostles of Doom Alpha 1 - J. L. Langland.epub')
book2 = epub.open_epub('/home/mikael/astlan/Apostles of Doom Alpha 2 - J. L. Langland.epub')

for item in book1.opf.manifest.values():
    print(item.href)

    if item.media_type == 'application/xhtml+xml':
        paras1 = text_paras(book1, item.href)
        paras2 = text_paras(book2, item.href)

        s = difflib.SequenceMatcher(None, paras1, paras2)
        for opcode in s.get_opcodes():
            print("%6s a[%d:%d] b[%d:%d]" % opcode)

            if opcode[0] == 'insert':
                print('B: ', paras2[opcode[3]:opcode[4]])

            elif opcode[0] == 'replace':
                print('A: ', paras1[opcode[1]:opcode[2]])
                print('B: ', paras2[opcode[3]:opcode[4]])

            elif opcode[0] == 'delete':
                print('A: ', paras1[opcode[1]:opcode[2]])