2024-05-19
Kindle書籍のPDF化 (半自動化)
過去記事:
あくまで私的利用が目的です. 久々に環境構築したらいくつかハマったのでメモ.
テスト環境
Windows 11 on MacBook Air M1 Parallels
Python 3.12.3
環境構築
Kindle
v1.40.1 (新しいバージョンだとazwとは違う形式になり, 対応できないため)
1.35あたりから, Kindleアプリを何度か再起動すると1.40.1になる.
自分のアカウントでログイン
[ツール] -> [オプション] -> [一般] で「更新がある場合は自動的にインストールする」のチェックを外す
Calibre
6.29.0
7系だと
ebook-convertが上手くいかなかった
DeDRM v10.0.3
Calibreで[環境設定] -> [プラグイン] -> [ファイルからプラグインを読み込む] -> DeDRM v10.0.3の中のDeDRM_plugin.zipを選択して [開く] -> セキュリテリスクは [はい] -> [calibreを今すぐ再起動]
ImageMagick
ImageMagick 6.8.9-5 Q16 x64 2014-06-26
もっと新しいのでも大丈夫なはず
本質的には不要だが, 表紙画像のアスペクト比を取得 (
identify) するために使用
Python
Python 3.12.3
本質的には不要だが, 半自動化で利用するために使用
pythonで実行できるようにPATHを通しておく
Code
convert.bat
convert.bat を作成
cd %~dp0python convertKindleToPDFInDir.pypauseexit
convertKindleToPDFInDir.py
convertKindleToPDFInDir.pyを作成
xxxxxxxxxximport subprocessimport sysimport xml.etree.ElementTree as ETimport osimport globimport datetime
def command(cmd): try: result = subprocess.run(cmd, shell=True, check=True, encoding="utf8", stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True) for line in result.stdout.splitlines(): yield line except subprocess.CalledProcessError: printLog("ERROR: Command was failed!!") printShortLog("ERROR: Command was failed!!") # print('Command [' + cmd + '] was failed.', file=sys.stderr) printLog('Command [' + cmd + '] was failed.') # sys.exit(1)
def getCoverRatio(dirName): coverName = dirName + "cover.jpg" cmd = 'identify -format "%w,%h" "' + coverName + '"' coverH = 200 for result in command(cmd): # print(result) whTemp = result.split(',') # print(whTemp) whTempF = [float(s) for s in whTemp] # print(whTempF) ar = whTempF[1]/whTempF[0] # print(ar) coverH = int(200*ar) # print(coverH) return coverH
def getBookInfo(dirName): metafileName = dirName + 'metadata.opf' tree = ET.parse(metafileName) root = tree.getroot() author = "" title = "" for child in root: # print(child.tag) # print(child.attrib) if "metadata" in child.tag: # print("aaaaaa") for grandChild in child: # print(grandChild.tag) if "title" in grandChild.tag: # print(grandChild.text) title = replaceFC(grandChild.text) if "creator" in grandChild.tag: # print(grandChild.text) author = replaceFC(grandChild.text) return author, title
# Forbidden Charactordef replaceFC(s): return s.replace('/', '-').replace(':', '-').replace('\\', '-').replace('*', '-').replace('?', '-').replace('"', '-').replace("'", '-').replace('<', '-').replace('>', '-').replace('|', '-')
def convertToPDF(inputName, outputName, coverH, author, title, margin): # outputName = author + "_" + title + ".pdf" # css = ' --extra-css "vertical.css"' css = '' # cmd = 'ebook-convert "'+inputName+'" "'+outputName+'" --input-profile default --custom-size 200x'+str(coverH)+ css +' --unit millimeter --preserve-cover-aspect-ratio --pdf-serif-family "游ゴシック" --pdf-sans-family "游ゴシック" --pdf-mono-family "游ゴシック" --pdf-standard-font serif --pdf-default-font-size 18 --pdf-mono-font-size 14 --pdf-page-margin-bottom '+margin+' --pdf-page-margin-left '+margin+' --pdf-page-margin-right '+margin+' --pdf-page-margin-top '+margin+' --pdf-footer-template "<footer style=\"width:30px;height:20px;transform:rotate(-90deg);\"><span style=\"font-size:10px;\">_PAGENUM_</span></footer>"' # cmd = 'ebook-convert "'+inputName+'" "'+outputName+'" --input-profile default --custom-size 200x'+str(coverH)+ css +' --unit millimeter --preserve-cover-aspect-ratio --pdf-serif-family "游ゴシック" --pdf-sans-family "游ゴシック" --pdf-mono-family "游ゴシック" --pdf-standard-font serif --pdf-default-font-size 18 --pdf-mono-font-size 14 --pdf-page-margin-bottom '+margin+' --pdf-page-margin-left '+margin+' --pdf-page-margin-right '+margin+' --pdf-page-margin-top '+margin+' --pdf-page-numbers' cmd = 'ebook-convert "'+inputName+'" "'+outputName+'" --input-profile default --custom-size 200x'+str(coverH)+ css +' --unit millimeter --preserve-cover-aspect-ratio --pdf-serif-family "游ゴシック" --pdf-sans-family "游ゴシック" --pdf-mono-family "游ゴシック" --pdf-standard-font serif --pdf-default-font-size 20 --pdf-mono-font-size 16 --pdf-page-margin-bottom '+margin+' --pdf-page-margin-left '+margin+' --pdf-page-margin-right '+margin+' --pdf-page-margin-top '+margin printLog(cmd) for result in command(cmd): # print(result) printLog(result)
def decideMargin(inputName): size = os.path.getsize(inputName) printLog(size) margin = '40.0' if size >= 20*10**6: printLog("filesize: large!!") margin = '-1.0' else: printLog("filesize: normal") return margin
def replaceSB(s): s2 = s.replace('[', 'abcdefg123456789L').replace(']', 'abcdefg123456789R') return s2.replace('abcdefg123456789L', '[[]').replace('abcdefg123456789R', '[]]')
def getInputFilename(dirName): # print(dirName) # print(replaceSB(dirName)) filename = "" # for file in glob.glob(dirName + "*"): # print(file) for file in glob.glob(replaceSB(dirName) + "*.azw*"): printLog(file) filename = file return filename
def getDirnames(rootDir): dirs = [] for file in glob.glob(rootDir + "*/*"): # print(file) dirName = file.replace('\\','/') + '/' # print(dirName) if os.path.isdir(dirName): dirs.append(dirName) # else: # print("Not Directory") printLog(len(dirs)) return dirs
def convertToPDFIn(inputDirName, outputDirName, coverExists, metafileExists): dirName = inputDirName # print(dirName) inputName = getInputFilename(dirName) # print("aaaa") # print(inputName) coverH = 284 if coverExists: coverH = getCoverRatio(dirName)
author, title = "___NoMeta", datetime.datetime.now().strftime("%Y-%m-%d-%H-%M-%S") if metafileExists: author, title = getBookInfo(dirName) printLog([author, title])
# outputName = dirName + author + "_" + title + ".pdf" outputName = outputDirName + author + "_" + title + ".pdf" margin = decideMargin(inputName) convertToPDF(inputName, outputName, coverH, author, title, margin)
def checkTargetExists(dirName): azw3Exists = False for file in glob.glob(replaceSB(dirName) + "*.azw*"): azw3Exists = True metafileName = dirName + 'metadata.opf' metafileExists = os.path.isfile(metafileName) coverName = dirName + 'cover.jpg' coverExists = os.path.isfile(coverName) allExists = azw3Exists and coverExists and metafileExists if allExists: printLog("All Exists") else: printLog("Not Found... : azw3=" + str(azw3Exists) + ", cover=" + str(coverExists) + ", meta=" + str(metafileExists)) # shouldPass = azw3Exists and coverExists return azw3Exists, coverExists, metafileExists
def getShortLogFilename(): timeStr = initialTime.strftime("%Y-%m-%d-%H-%M-%S") filename = "log/"+timeStr+"_short.txt" return filename
def getLogFilename(): timeStr = initialTime.strftime("%Y-%m-%d-%H-%M-%S") filename = "log/"+timeStr+".txt" return filename
def makeLogFile(): # now = datetime.datetime.now() # nowStr = now.strftime("%Y-%m-%d-%H-%M-%S") # filename = "log"+nowStr+".txt" os.makedirs("log", exist_ok=True) f = open(getLogFilename(), "a", encoding="utf-8") f.write(getLogFilename()+"\n") f.close() f = open(getShortLogFilename(), "a", encoding="utf-8") f.write(getShortLogFilename()+"\n") f.write("datetime, azw(3), cover, meta, directory\n") f.close() # return filename
def printLog(log): s = log if type(log) == list: s = " ".join(map(str,log)) else: s = str(log) print(s) f = open(getLogFilename(), "a", encoding="utf-8") f.write(s+"\n") f.close()
def printShortLog(log): s = log if type(log) == list: s = ", ".join(map(str,log)) else: s = str(log) f = open(getShortLogFilename(), "a", encoding="utf-8") f.write(s+"\n") f.close()
def main(): makeLogFile() rootDir = "C:/Users/[User Name]/CalibreToConvert/" outputDirName = rootDir + "_output/" os.makedirs(outputDirName, exist_ok=True) inputDirNames = getDirnames(rootDir) allNum = len(inputDirNames) count = 0 for idn in inputDirNames: count += 1 currentLabel = str(count) + "/" + str(allNum) printLog("# START ("+currentLabel+") ########################################################") now = datetime.datetime.now() printLog(now) printLog(idn) azw3Exists, coverExists, metafileExists = checkTargetExists(idn) printShortLog([now, azw3Exists, coverExists, metafileExists, idn]) if azw3Exists: convertToPDFIn(idn, outputDirName, coverExists, metafileExists) printLog("# END ("+currentLabel+") ##########################################################\n\n\n")
if __name__ == "__main__": initialTime = datetime.datetime.now() main()
実行
Kindleアプリで本をDL.
xxxxxxxxxxC:\Users\[User Name]\Documents\My Kindle ContentにDLされてる.
calibreで上記にアクセスし, 当該の本を追加
xxxxxxxxxxC:\Users\[User Name]\calibreライブラリにCalibre用としてコピーされる. フォルダ構成は
[著者]/[タイトル]x
C:/Users/[User Name]/CalibreToConvert/などの作業用フォルダを作成し, そこに上記の [著者]フォルダごとコピー
convertKindleToPDFInDir.pyの中のmain関数内のrootDirを, 上記の作業用フォルダC:/Users/[User Name]/CalibreToConvert/を指定するように変更convert.batをダブルクリックxxxxxxxxxxC:/Users/[User Name]/CalibreToConvert/_output/フォルダに変換済みのpdfが作成される. 完了.
