kindle本→PDF

import os
import re
import sys
import tempfile
import shutil
import zipfile
from pathlib import Path
from bs4 import BeautifulSoup

def get_first_html(files):
    """最初に参照するhtml, xhtmlを探す"""
    html_path = find_list(".html", files)
    if html_path is None:
        htmls = find_list(".xhtml", files)
        html_path = htmls[0] if htmls is not None else None

    return html_path

def get_title_from_html(html):
    """htmlファイルから <meta name="DC.title" content="title"> を抽出"""
    content = html.read_text(encoding="utf-8")
    soup = BeautifulSoup(content, "html.parser")
    tag = soup.find("meta", attrs={"name": "DC.title"})
    title = tag.get("content") if tag else "None title"
    return sanitize_filename(title)

def sanitize_filename(filename):
    """ファイル名に使えない文字を置換する"""
    table = str.maketrans({
        '/': '／',
        '\\': '￥',
    })
    return filename.translate(table)

def analyze_html(html):
    """htmlから次ページのhrefと現在ページのimgを抽出"""
    content = html.read_text(encoding="utf-8")
    soup = BeautifulSoup(content, "html.parser")

    # <a href="---" class="calibreANext">
    next_a = soup.find("a", class_="calibreANext")
    next_href = next_a.get("href") if next_a else None

    # <img src="---">
    img = soup.find("img")
    img_src = img.get("src") if img else None

    return next_href, img_src

def find_list(x, lists):
    """listsからxを含む項目lを取り出す"""
    for l in lists:
        if x in str(l):
            return l
    return None

def convert2cbz(input_path, output_ext="cbz"):
    """変換本体"""
    with tempfile.TemporaryDirectory() as tmpdir:
        tmpdir = Path(tmpdir)

        # 解凍
        with zipfile.ZipFile(input_path, 'r') as zip_ref:
            zip_ref.extractall(tmpdir)

        # ファイルリストを取得
        files = list(tmpdir.glob("**/*"))

        # HTMLからタイトル抽出
        first_html = get_first_html(files)
        output_title = get_title_from_html(first_html)

        # HTMLのnext pageを辿ってimgをoutput_listに追加
        output_list = []
        prefix, midstr = "image", "-"
        cnt = 1 # 連番用カウンター
        cnt_len = len(str(len(files))) # 連番桁数=ファイル数の桁数
        next_html, img_name = analyze_html(first_html)
        while True:
            # get current html_path, img_path & next_html name
            html_path = find_list(next_html, files)
            next_html, img_name = analyze_html(html_path)
            ext = os.path.splitext(img_name)[1]
            img_path = find_list(img_name, files)

            # set new_path for img
            postfix = str(cnt)
            postfix = postfix.zfill(cnt_len)
            new_name = prefix + midstr + postfix + ext
            new_path = tmpdir / new_name

            # copy & rename img file
            shutil.copy(img_path, new_path)
            output_list.append(new_path)
            if next_html is None:
                break
            cnt += 1

        # cover（表紙）は別枠で追加
        for f in files:
            if "cover" in f.name.lower():
                cover_path = tmpdir / os.path.basename(f)
                shutil.copy(f, cover_path)
                output_list.insert(0, cover_path)

        # zip/cbz作成
        output_path = f"{output_title}.{output_ext}"
        with zipfile.ZipFile(output_path, 'w', zipfile.ZIP_DEFLATED) as out_zip:
            for f in output_list:
                out_zip.write(f, f.name)

        print(f"✅ 出力完了: {output_path}")

# 実行部
if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("usage: python conv_kindle_cbz.py <input.epub|zip> [cbz|zip]")
        sys.exit(1)

    input_file = sys.argv[1]
    ext = sys.argv[2] if len(sys.argv) > 2 else "cbz"

    if not os.path.isfile(input_file):
        print(f"指定されたファイル {input_file} が見つかりません。")
        sys.exit(1)

    convert2cbz(input_file, ext)

%localappdata%\Amazon\Kindle\application

KRFKeyExtractor.exe Kindle.DMP "C:\asdf" kindlekey.file 

cmd /K cd /d "%localappdata%\Amazon\Kindle\application"

del kindlekey.file
del Kindle.DMP

%localappdata%\Amazon\Kindle\application

KRFKeyExtractor.exe Kindle.DMP "C:\asdf" kindlekey.file