青空文庫のテキストファイルを結合するスクリプト

README.md

concatAozora

このスプリプトはshuyo/concatAozora.pyのforkです。

Kindle用に変換する方法

AozoraEpub3を使うと良い。 こんな感じに設定しておくと、目次も良い感じに生成される（細かいところは好みで）。

concatAozora.py

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

# How to use
# ./concatAozora.py -t title a.zip b.zip ... z.zip

import codecs, sys, os, zipfile

CODE = "shift_jis"

firstpage = True
g = codecs.open("output.txt", "wb", CODE)

files = sys.argv[1:]
option_title = True
if files[0] == "-t":
    title = files[1]
    files = files[2:]
    option_title = False

is_first_book = True
for filename in files:
    if not os.path.isfile(filename):
        continue

    if filename.lower().endswith(".zip"):
        z = zipfile.ZipFile(filename)
        targets = [x for x in z.namelist() if x.endswith(".txt")]
        if len(targets) == 0:
            sys.err.write("No .txt file in %s\n" % filename)
            continue
        f = codecs.iterdecode(z.open(targets[0]), CODE)
    else:
        f = codecs.open(filename, "rb", CODE)

    if is_first_book:
        if option_title:
            title = next(f)
        else:
            next(f)
        chapter = f.__next__().rstrip('\r\n')
        author = next(f)

    body = ""
    for s in f:
        if s.startswith("-------------------------------------------------------"):
            body = ""
        elif s.startswith("底本："):
            break
        else:
            s = s.replace("［＃小見出し］", "［＃ここから太字］")
            s = s.replace("［＃小見出し終わり］", "［＃ここで太字終わり］")
            s = s.replace("小見出し", "太字")
            s = s.replace("中見出し", "小見出し")
            s = s.replace("大見出し", "中見出し")
            body += s

    if firstpage:
        g.write(title)
        g.write("\n")
        g.write(author)
        g.write("\n")
        firstpage = False

    g.write("\n［＃改ページ］\n")
    g.write(chapter + "［＃「" + chapter + "」は大見出し］")
    g.write("\n")
    g.write(body)

    f.close()

g.close()