public/kcc
1
0
Fork 0
mirror of https://github.com/ciromattia/kcc synced 2026-07-04 03:55:28 +00:00
Code Issues Releases Wiki Activity
Files
c3f86e29c8708b6f7638ffc5cb2866a701985a97
kcc/kindlecomicconverter/comic2ebook.py
T
Aldijonas c3f86e29c8 Rename cover.jpg to !cover.jpg in CBZ (#1381) 
Change cover image filename from 'cover.jpg' to '!cover.jpg' in line 1907 for correct cover display when using CBZ file format
2026-07-02 16:41:37 -07:00

2048 lines
90 KiB
Python
Executable File
Raw Blame History

# -*- coding: utf-8 -*-
#
# Copyright (c) 2012-2014 Ciro Mattia Gonano <ciromattia@gmail.com>
# Copyright (c) 2013-2019 Pawel Jastrzebski <pawelj@iosphe.re>
#
# Permission to use, copy, modify, and/or distribute this software for
# any purpose with or without fee is hereby granted, provided that the
# above copyright notice and this permission notice appear in all
# copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL
# WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED
# WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE
# AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL
# DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA
# OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
# TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
# PERFORMANCE OF THIS SOFTWARE.
#
from collections import Counter
import os
import pathlib
import re
import shutil
import sys
import xml.etree.ElementTree as ET
from argparse import ArgumentParser
from time import perf_counter, strftime, gmtime
from copy import copy
from glob import glob, escape
from re import sub
from stat import S_IWRITE, S_IREAD, S_IEXEC
from typing import List
from zipfile import ZipFile, ZIP_STORED
from tempfile import mkdtemp, gettempdir
from shutil import move, copytree, rmtree
from multiprocessing import Pool, cpu_count
from uuid import uuid4
from natsort import os_sort_keygen, os_sorted
from slugify import slugify as slugify_ext
from PIL import Image, ImageFile, ImageOps
from pathlib import Path
from subprocess import STDOUT, PIPE, CalledProcessError
from psutil import virtual_memory, disk_usage
from html import escape as hescape
import pymupdf
from .shared import IMAGE_TYPES, getImageFileName, walkSort, walkLevel, sanitizeTrace, subprocess_run, dot_clean, get_contain_resolution
from .comicarchive import SEVENZIP, available_archive_tools
from . import comic2panel
from . import image
from . import comicarchive
from . import pdfjpgextract
from . import dualmetafix
from . import metadata
from . import kindle
from . import __version__
ImageFile.LOAD_TRUNCATED_IMAGES = True
OS_SORT_KEY = os_sort_keygen()
def main(argv=None):
global options
parser = makeParser()
args = parser.parse_args(argv)
options = copy(args)
if not argv or options.input == []:
parser.print_help()
return 0
if sys.platform.startswith('win'):
sources = [source for option in options.input for source in glob(escape(option))]
else:
sources = options.input
if len(sources) == 0:
print('No matching files found.')
return 1
if options.filefusion:
fusion_source_parent = str(Path(sources[0]).parent)
fusion_path = makeFusion(list(sources))
sources.clear()
sources.append(fusion_path)
for source in sources:
source = source.rstrip('\\').rstrip('/')
options = copy(args)
if options.filefusion and options.output is None:
options.output = fusion_source_parent
options = checkOptions(options)
print('Working on ' + source + '...')
makeBook(source)
return 0
def buildHTML(path, imgfile, imgfilepath, imgfile2=None):
key = pathlib.Path(imgfilepath).name
filename = getImageFileName(imgfile)
deviceres = options.profileData[1]
if not options.noprocessing and "Rotated" in options.imgMetadata[key]:
rotatedPage = True
else:
rotatedPage = False
if not options.noprocessing and "BlackBackground" in options.imgMetadata[key]:
additionalStyle = 'background-color:#000000;'
else:
additionalStyle = ''
postfix = ''
backref = 1
head = path
while True:
head, tail = os.path.split(head)
if tail == 'Images':
htmlpath = os.path.join(head, 'Text', postfix)
break
postfix = tail + "/" + postfix
backref += 1
if not os.path.exists(htmlpath):
os.makedirs(htmlpath)
htmlfile = os.path.join(htmlpath, filename[0] + '.xhtml')
imgsize = Image.open(os.path.join(head, "Images", postfix, imgfile)).size
imgsizeframe = list(imgsize)
imgsize2 = (0, 0)
if imgfile2:
imgsize2 = Image.open(os.path.join(head, "Images", postfix, imgfile2)).size
imgsizeframe[1] += imgsize2[1]
if options.hq:
imgsizeframe = (int(imgsizeframe[0] // 1.5), int(imgsizeframe[1] // 1.5))
f = open(htmlfile, "w", encoding='UTF-8')
f.writelines(["<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
"<!DOCTYPE html>\n",
"<html xmlns=\"http://www.w3.org/1999/xhtml\" xmlns:epub=\"http://www.idpf.org/2007/ops\">\n",
"<head>\n",
"<title>", hescape(filename[0]), "</title>\n",
"<link href=\"", "../" * (backref - 1), "style.css\" type=\"text/css\" rel=\"stylesheet\"/>\n",
"<meta name=\"viewport\" "
"content=\"width=" + str(imgsizeframe[0]) + ", height=" + str(imgsizeframe[1]) + "\"/>\n"
"</head>\n",
"<body style=\"" + additionalStyle + "\">\n",
"<div style=\"text-align:center;\">\n",
])
if options.iskindle:
# this display none div fixes formatting issues with virtual panel mode, for some reason
f.write('<div style="display:none;">.</div>\n')
f.write(f'<img width="{imgsize[0]}" height="{imgsize[1]}" src="{"../" * backref}Images/{postfix}{imgfile}"/>\n')
if imgfile2:
f.write(f'<img style="top: 1920px" width="{imgsize2[0]}" height="{imgsize2[1]}" src="{"../" * backref}Images/{postfix}{imgfile2}"/>\n')
f.write("</div>\n")
if options.iskindle and options.panelview:
if options.autoscale:
size = (getPanelViewResolution(imgsize, deviceres))
else:
if options.hq:
size = imgsize
else:
size = (int(imgsize[0] * 1.5), int(imgsize[1] * 1.5))
if size[0] - deviceres[0] < deviceres[0] * 0.01:
noHorizontalPV = True
else:
noHorizontalPV = False
if size[1] - deviceres[1] < deviceres[1] * 0.01:
noVerticalPV = True
else:
noVerticalPV = False
x, y = getPanelViewSize(deviceres, size)
boxStyles = {"PV-TL": "position:absolute;left:0;top:0;",
"PV-TR": "position:absolute;right:0;top:0;",
"PV-BL": "position:absolute;left:0;bottom:0;",
"PV-BR": "position:absolute;right:0;bottom:0;",
"PV-T": "position:absolute;top:0;left:" + x + "%;",
"PV-B": "position:absolute;bottom:0;left:" + x + "%;",
"PV-L": "position:absolute;left:0;top:" + y + "%;",
"PV-R": "position:absolute;right:0;top:" + y + "%;"}
f.write("<div id=\"PV\">\n")
if not noHorizontalPV and not noVerticalPV:
if rotatedPage:
if options.righttoleft:
order = [1, 3, 2, 4]
else:
order = [2, 4, 1, 3]
else:
if options.righttoleft:
order = [2, 1, 4, 3]
else:
order = [1, 2, 3, 4]
boxes = ["PV-TL", "PV-TR", "PV-BL", "PV-BR"]
elif noHorizontalPV and not noVerticalPV:
if rotatedPage:
if options.righttoleft:
order = [1, 2]
else:
order = [2, 1]
else:
order = [1, 2]
boxes = ["PV-T", "PV-B"]
elif not noHorizontalPV and noVerticalPV:
if rotatedPage:
order = [1, 2]
else:
if options.righttoleft:
order = [2, 1]
else:
order = [1, 2]
boxes = ["PV-L", "PV-R"]
else:
order = []
boxes = []
for i in range(0, len(boxes)):
f.writelines(["<div id=\"" + boxes[i] + "\">\n",
"<a style=\"display:inline-block;width:100%;height:100%;\" class=\"app-amzn-magnify\" "
"data-app-amzn-magnify='{\"targetId\":\"" + boxes[i] +
"-P\", \"ordinal\":" + str(order[i]) + "}'></a>\n",
"</div>\n"])
f.write("</div>\n")
for box in boxes:
f.writelines(["<div class=\"PV-P\" id=\"" + box + "-P\" style=\"" + additionalStyle + "\">\n",
"<img style=\"" + boxStyles[box] + "\" src=\"", "../" * backref, "Images/", postfix,
imgfile, "\" width=\"" + str(size[0]) + "\" height=\"" + str(size[1]) + "\"/>\n",
"</div>\n"])
f.writelines(["</body>\n",
"</html>\n"])
f.close()
return path, imgfile
def buildNCX(dstdir, title, chapters, chapternames):
ncxfile = os.path.join(dstdir, 'OEBPS', 'toc.ncx')
f = open(ncxfile, "w", encoding='UTF-8')
f.writelines(["<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
f"<ncx version=\"2005-1\" xml:lang=\"{options.language}\" xmlns=\"http://www.daisy.org/z3986/2005/ncx/\">\n",
"<head>\n",
"<meta name=\"dtb:uid\" content=\"urn:uuid:", options.uuid, "\"/>\n",
"<meta name=\"dtb:depth\" content=\"1\"/>\n",
"<meta name=\"dtb:totalPageCount\" content=\"0\"/>\n",
"<meta name=\"dtb:maxPageNumber\" content=\"0\"/>\n",
"<meta name=\"generated\" content=\"true\"/>\n",
"</head>\n",
"<docTitle><text>", hescape(title), "</text></docTitle>\n",
"<navMap>\n"])
for chapter in chapters:
folder = chapter[0].replace(os.path.join(dstdir, 'OEBPS'), '').lstrip('/').lstrip('\\\\')
filename = getImageFileName(os.path.join(folder, chapter[1]))
navID = folder.replace('/', '_').replace('\\', '_')
if options.comicinfo_chapters:
title = chapternames[chapter[1]]
navID = filename[0].replace('/', '_').replace('\\', '_')
elif os.path.basename(folder) != "Text":
title = chapternames[os.path.basename(folder)]
f.write("<navPoint id=\"" + navID + "\"><navLabel><text>" +
hescape(title) + "</text></navLabel><content src=\"" + filename[0].replace("\\", "/") +
".xhtml\"/></navPoint>\n")
f.write("</navMap>\n</ncx>")
f.close()
def buildNAV(dstdir, title, chapters, chapternames):
navfile = os.path.join(dstdir, 'OEBPS', 'nav.xhtml')
f = open(navfile, "w", encoding='UTF-8')
f.writelines(["<?xml version=\"1.0\" encoding=\"utf-8\"?>\n",
"<!DOCTYPE html>\n",
"<html xmlns=\"http://www.w3.org/1999/xhtml\" xmlns:epub=\"http://www.idpf.org/2007/ops\">\n",
"<head>\n",
"<title>" + hescape(title) + "</title>\n",
"<meta charset=\"utf-8\"/>\n",
"</head>\n",
"<body>\n",
"<nav xmlns:epub=\"http://www.idpf.org/2007/ops\" epub:type=\"toc\" id=\"toc\">\n",
"<ol>\n"])
for chapter in chapters:
folder = chapter[0].replace(os.path.join(dstdir, 'OEBPS'), '').lstrip('/').lstrip('\\\\')
filename = getImageFileName(os.path.join(folder, chapter[1]))
if options.comicinfo_chapters:
title = chapternames[chapter[1]]
elif os.path.basename(folder) != "Text":
title = chapternames[os.path.basename(folder)]
f.write("<li><a href=\"" + filename[0].replace("\\", "/") + ".xhtml\">" + hescape(title) + "</a></li>\n")
f.writelines(["</ol>\n",
"</nav>\n",
"<nav epub:type=\"page-list\">\n",
"<ol>\n"])
for chapter in chapters:
folder = chapter[0].replace(os.path.join(dstdir, 'OEBPS'), '').lstrip('/').lstrip('\\\\')
filename = getImageFileName(os.path.join(folder, chapter[1]))
if options.comicinfo_chapters:
title = chapternames[chapter[1]]
elif os.path.basename(folder) != "Text":
title = chapternames[os.path.basename(folder)]
f.write("<li><a href=\"" + filename[0].replace("\\", "/") + ".xhtml\">" + hescape(title) + "</a></li>\n")
f.write("</ol>\n</nav>\n</body>\n</html>")
f.close()
def buildOPF(dstdir, title, filelist, originalpath, cover=None):
opffile = os.path.join(dstdir, 'OEBPS', 'content.opf')
deviceres = options.profileData[1]
if options.vertical4panel:
writingmode = "vertical"
else:
writingmode = "horizontal"
if options.invertdirection:
if options.righttoleft:
writingmode += "-lr"
else:
writingmode += "-rl"
else:
if options.righttoleft:
writingmode += "-rl"
else:
writingmode += "-lr"
f = open(opffile, "w", encoding='UTF-8')
f.writelines(["<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
"<package version=\"3.0\" unique-identifier=\"BookID\" ",
"xmlns=\"http://www.idpf.org/2007/opf\">\n",
"<metadata xmlns:opf=\"http://www.idpf.org/2007/opf\" ",
"xmlns:dc=\"http://purl.org/dc/elements/1.1/\">\n",
"<dc:title>", hescape(title), "</dc:title>\n",
f"<dc:language>{options.language}</dc:language>\n",
"<dc:identifier id=\"BookID\">urn:uuid:", options.uuid, "</dc:identifier>\n",
"<dc:contributor id=\"contributor\">KindleComicConverter-" + __version__ + "</dc:contributor>\n"])
if len(options.summary) > 0:
f.writelines(["<dc:description>", hescape(options.summary), "</dc:description>\n"])
for author in options.authors:
f.writelines(["<dc:creator>", hescape(author), "</dc:creator>\n"])
if not options.iskindle and options.series:
f.writelines(['<meta property="belongs-to-collection" id="c02">', hescape(options.series), "</meta>\n"])
f.writelines(['<meta refines="#c02" property="collection-type">', "series", "</meta>\n"])
if options.volume and options.number:
f.writelines(['<meta refines="#c02" property="group-position">', hescape(f"{options.volume}.{options.number}"), "</meta>\n"])
elif options.volume:
f.writelines(['<meta refines="#c02" property="group-position">', hescape(options.volume), "</meta>\n"])
elif options.number:
f.writelines(['<meta refines="#c02" property="group-position">', hescape(options.number), "</meta>\n"])
f.write("<meta property=\"dcterms:modified\">" + strftime("%Y-%m-%dT%H:%M:%SZ", gmtime()) + "</meta>\n")
if cover:
f.write("<meta name=\"cover\" content=\"cover\"/>\n")
if options.iskindle and options.profile != 'Custom':
f.writelines(["<meta name=\"fixed-layout\" content=\"true\"/>\n",
])
if not options.kfx_resolution:
f.writelines([
"<meta name=\"original-resolution\" content=\"",
str(deviceres[0]) + "x" + str(deviceres[1]) + "\"/>\n",
])
else:
x, y = options.kfx_resolution
f.writelines([
"<meta name=\"original-resolution\" content=\"",
str(x) + "x" + str(y) + "\"/>\n",
])
f.writelines([
"<meta name=\"book-type\" content=\"comic\"/>\n",
"<meta name=\"primary-writing-mode\" content=\"" + writingmode + "\"/>\n",
"<meta name=\"zero-gutter\" content=\"true\"/>\n",
"<meta name=\"zero-margin\" content=\"true\"/>\n",
"<meta name=\"ke-border-color\" content=\"#FFFFFF\"/>\n",
"<meta name=\"ke-border-width\" content=\"0\"/>\n",
"<meta name=\"orientation-lock\" content=\"none\"/>\n"])
if options.kfx:
f.writelines(["<meta name=\"region-mag\" content=\"false\"/>\n"])
else:
f.writelines(["<meta name=\"region-mag\" content=\"true\"/>\n"])
f.writelines([
"<meta property=\"rendition:spread\">landscape</meta>\n",
"<meta property=\"rendition:layout\">pre-paginated</meta>\n"
])
f.writelines(["</metadata>\n<manifest>\n<item id=\"ncx\" href=\"toc.ncx\" ",
"media-type=\"application/x-dtbncx+xml\"/>\n",
"<item id=\"nav\" href=\"nav.xhtml\" ",
"properties=\"nav\" media-type=\"application/xhtml+xml\"/>\n"])
if cover is not None:
mt = 'image/jpeg'
f.write("<item id=\"cover\" href=\"Images/cover.jpg" + "\" media-type=\"" + mt +
"\" properties=\"cover-image\"/>\n")
reflist = []
for path in filelist:
folder = path[0].replace(os.path.join(dstdir, 'OEBPS'), '').lstrip('/').lstrip('\\\\').replace("\\", "/")
filename = getImageFileName(path[1])
uniqueid = os.path.join(folder, filename[0]).replace('/', '_').replace('\\', '_')
reflist.append(uniqueid)
f.write("<item id=\"page_" + str(uniqueid) + "\" href=\"" +
folder.replace('Images', 'Text') + "/" + filename[0] +
".xhtml\" media-type=\"application/xhtml+xml\"/>\n")
if '.png' == filename[1]:
mt = 'image/png'
elif '.gif' == filename[1]:
mt = 'image/gif'
elif '.webp' == filename[1]:
mt = 'image/webp'
else:
mt = 'image/jpeg'
f.write("<item id=\"img_" + str(uniqueid) + "\" href=\"" + folder + "/" + path[1] + "\" media-type=\"" +
mt + "\"/>\n")
if 'above' in path[1]:
bottom = path[1].replace('above', 'below')
uniqueid = uniqueid.replace('above', 'below')
f.write("<item id=\"img_" + str(uniqueid) + "\" href=\"" + folder + "/" + bottom + "\" media-type=\"" + mt + "\"/>\n")
f.write("<item id=\"css\" href=\"Text/style.css\" media-type=\"text/css\"/>\n")
def pageSpreadProperty(pageside):
if options.iskindle:
return "linear=\"yes\" properties=\"page-spread-%s\"" % pageside
elif options.isKobo:
return "properties=\"rendition:page-spread-%s\"" % pageside
else:
return ""
if options.invertdirection:
if options.righttoleft:
f.write("</manifest>\n<spine page-progression-direction=\"ltr\" toc=\"ncx\">\n")
pageside = "left"
else:
f.write("</manifest>\n<spine page-progression-direction=\"rtl\" toc=\"ncx\">\n")
pageside = "right"
else:
if options.righttoleft:
f.write("</manifest>\n<spine page-progression-direction=\"rtl\" toc=\"ncx\">\n")
pageside = "right"
else:
f.write("</manifest>\n<spine page-progression-direction=\"ltr\" toc=\"ncx\">\n")
pageside = "left"
if originalpath.lower().endswith('.pdf') or originalpath.lower().endswith('.epub'):
if pageside == "right":
pageside = "left"
else:
pageside = "right"
if options.spreadshift:
if pageside == "right":
pageside = "left"
else:
pageside = "right"
# initial spread order forwards
page_spread_property_list = []
for entry in reflist:
if options.righttoleft:
if "-kcc-a" in entry or "-kcc-d" in entry:
page_spread_property_list.append("center")
pageside = "right"
elif "-kcc-b" in entry:
page_spread_property_list.append("right")
pageside = "right"
elif "-kcc-c" in entry:
page_spread_property_list.append("left")
pageside = "right"
else:
page_spread_property_list.append(pageside)
if pageside == "right":
pageside = "left"
else:
pageside = "right"
else:
if "-kcc-a" in entry or "-kcc-d" in entry:
page_spread_property_list.append("center")
pageside = "left"
elif "-kcc-b" in entry:
page_spread_property_list.append("left")
pageside = "left"
elif "-kcc-c" in entry:
page_spread_property_list.append("right")
pageside = "left"
else:
page_spread_property_list.append(pageside)
if pageside == "right":
pageside = "left"
else:
pageside = "right"
# fix spread orders backward
spread_seen = False
for i in range(len(reflist) -1, -1, -1):
entry = reflist[i]
if "-kcc-x" not in entry:
spread_seen = True
if options.righttoleft:
pageside = "left"
else:
pageside = "right"
elif spread_seen:
page_spread_property_list[i] = pageside
if pageside == "right":
pageside = "left"
else:
pageside = "right"
for entry, prop in zip(reflist, page_spread_property_list):
if options.onepagelandscape:
prop = 'center'
f.write(f'<itemref idref="page_{entry}" {pageSpreadProperty(prop)}/>\n')
f.write("</spine>\n</package>\n")
f.close()
os.mkdir(os.path.join(dstdir, 'META-INF'))
f = open(os.path.join(dstdir, 'META-INF', 'container.xml'), 'w', encoding='UTF-8')
f.writelines(["<?xml version=\"1.0\"?>\n",
"<container version=\"1.0\" xmlns=\"urn:oasis:names:tc:opendocument:xmlns:container\">\n",
"<rootfiles>\n",
"<rootfile full-path=\"OEBPS/content.opf\" media-type=\"application/oebps-package+xml\"/>\n",
"</rootfiles>\n",
"</container>"])
f.close()
def buildEPUB(path, chapternames, tomenumber, ischunked, cover: image.Cover, originalpath, job_progress='', len_tomes=0):
filelist = []
chapterlist = []
os.mkdir(os.path.join(path, 'OEBPS', 'Text'))
f = open(os.path.join(path, 'OEBPS', 'Text', 'style.css'), 'w', encoding='UTF-8')
f.writelines(["@page {\n",
"margin: 0;\n",
"}\n",
"body {\n",
"display: block;\n",
"margin: 0;\n",
"padding: 0;\n",
"}\n",
])
if options.kindle_scribe_azw3:
f.writelines([
"img {\n",
"display: block;\n",
"}\n",
])
if options.iskindle and options.panelview:
f.writelines(["#PV {\n",
"position: absolute;\n",
"width: 100%;\n",
"height: 100%;\n",
"top: 0;\n",
"left: 0;\n",
"}\n",
"#PV-T {\n",
"top: 0;\n",
"width: 100%;\n",
"height: 50%;\n",
"}\n",
"#PV-B {\n",
"bottom: 0;\n",
"width: 100%;\n",
"height: 50%;\n",
"}\n",
"#PV-L {\n",
"left: 0;\n",
"width: 49.5%;\n",
"height: 100%;\n",
"float: left;\n",
"}\n",
"#PV-R {\n",
"right: 0;\n",
"width: 49.5%;\n",
"height: 100%;\n",
"float: right;\n",
"}\n",
"#PV-TL {\n",
"top: 0;\n",
"left: 0;\n",
"width: 49.5%;\n",
"height: 50%;\n",
"float: left;\n",
"}\n",
"#PV-TR {\n",
"top: 0;\n",
"right: 0;\n",
"width: 49.5%;\n",
"height: 50%;\n",
"float: right;\n",
"}\n",
"#PV-BL {\n",
"bottom: 0;\n",
"left: 0;\n",
"width: 49.5%;\n",
"height: 50%;\n",
"float: left;\n",
"}\n",
"#PV-BR {\n",
"bottom: 0;\n",
"right: 0;\n",
"width: 49.5%;\n",
"height: 50%;\n",
"float: right;\n",
"}\n",
".PV-P {\n",
"width: 100%;\n",
"height: 100%;\n",
"top: 0;\n",
"position: absolute;\n",
"display: none;\n",
"}\n"])
f.close()
build_html_start = perf_counter()
if cover:
cover.save_to_folder(os.path.join(path, 'OEBPS', 'Images', 'cover.jpg'), tomenumber, len_tomes)
dot_clean(path)
options.covers.append((cover, options.uuid))
for dirpath, dirnames, filenames in os.walk(os.path.join(path, 'OEBPS', 'Images')):
chapter = False
dirnames, filenames = walkSort(dirnames, filenames)
for afile in filenames:
if afile == 'cover.jpg':
continue
if 'below' in afile:
continue
if not chapter:
chapterlist.append((dirpath.replace('Images', 'Text'), afile))
chapter = True
if 'above' in afile:
bottom = afile.replace('above', 'below')
filelist.append(buildHTML(dirpath, afile, os.path.join(dirpath, afile), bottom))
else:
filelist.append(buildHTML(dirpath, afile, os.path.join(dirpath, afile)))
build_html_end = perf_counter()
print(f"{job_progress}buildHTML: {build_html_end - build_html_start} seconds")
# Overwrite chapternames if ComicInfo.xml has bookmarks
if ischunked:
options.comicinfo_chapters = []
if options.comicinfo_chapters:
chapterlist = []
global_diff = 0
diff_delta = 0
# if split
if options.splitter == 0:
diff_delta = 1
# if rotate and split
elif options.splitter == 2:
diff_delta = 2
for aChapter in options.comicinfo_chapters:
pageid = aChapter[0]
cur_diff = global_diff
global_diff = 0
for x in range(0, pageid + cur_diff + 1):
if '-kcc-b' in filelist[x][1]:
pageid += diff_delta
global_diff += diff_delta
filename = filelist[pageid][1]
chapterlist.append((filelist[pageid][0].replace('Images', 'Text'), filename))
chapternames[filename] = aChapter[1]
buildNCX(path, options.title, chapterlist, chapternames)
buildNAV(path, options.title, chapterlist, chapternames)
buildOPF(path, options.title, filelist, originalpath, cover)
def buildPDF(path, title, job_progress='', cover=None, output_file=None):
"""
Build a PDF file from processed comic images.
Images are combined into a single PDF optimized for e-readers.
"""
start = perf_counter()
# open empty PDF
with pymupdf.open() as doc:
doc.set_metadata({'title': title, 'author': options.authors[0]})
# Stream images to PDF
for root, dirs, files in os.walk(os.path.join(path, "OEBPS", "Images")):
files.sort(key=OS_SORT_KEY)
dirs.sort(key=OS_SORT_KEY)
for file in files:
w, h = Image.open(os.path.join(root, file)).size
page = doc.new_page(width=w, height=h)
page.insert_image(page.rect, filename=os.path.join(root, file))
# determine output filename if not provided
if output_file is None:
output_file = getOutputFilename(path, None, '.pdf', '')
# Save with optimizations for smaller file size
doc.save(output_file, deflate=True, garbage=4, clean=True)
end = perf_counter()
print(f"{job_progress}MuPDF output: {end-start} sec")
return output_file
def imgDirectoryProcessing(path, job_progress=''):
global workerPool, workerOutput
workerPool = Pool(maxtasksperchild=100)
workerOutput = []
options.imgMetadata = {}
work = []
pagenumber = 0
for dirpath, _, filenames in os.walk(path):
for afile in filenames:
pagenumber += 1
work.append([afile, dirpath, options])
if GUI:
GUI.progressBarTick.emit(str(pagenumber))
if len(work) > 0:
img_processing_start = perf_counter()
for i in work:
workerPool.apply_async(func=imgFileProcessing, args=(i,), callback=imgFileProcessingTick)
workerPool.close()
workerPool.join()
img_processing_end = perf_counter()
print(f"{job_progress}imgFileProcessing: {img_processing_end - img_processing_start} seconds")
# macOS 15 likes to add ._ files after multiprocessing
dot_clean(path)
if GUI and not GUI.conversionAlive:
rmtree(os.path.join(path, '..', '..'), True)
raise UserWarning("Conversion interrupted.")
if len(workerOutput) > 0:
rmtree(os.path.join(path, '..', '..'), True)
raise RuntimeError("One of workers crashed. Maybe restart PC. Cause: " + workerOutput[0][0], workerOutput[0][1])
else:
rmtree(os.path.join(path, '..', '..'), True)
raise UserWarning("C2E: Source directory is empty.")
def imgFileProcessingTick(output):
if isinstance(output, tuple):
workerOutput.append(output)
workerPool.terminate()
else:
for page in output:
if page is not None:
options.imgMetadata[page[0]] = page[1]
if GUI:
GUI.progressBarTick.emit('tick')
if not GUI.conversionAlive:
workerPool.terminate()
def imgFileProcessing(work):
try:
afile = work[0]
dirpath = work[1]
opt = work[2]
output = []
workImg = image.ComicPageParser((dirpath, afile), opt)
for i in workImg.payload:
img = image.ComicPage(opt, *i)
if opt.cropping == 2 and not opt.webtoon:
img.cropPageNumber(opt.croppingp, opt.croppingm)
if opt.cropping == 1 and not opt.webtoon:
img.cropMargin(opt.croppingp, opt.croppingm)
if opt.interpanelcrop > 0:
img.cropInterPanelEmptySections("horizontal" if opt.interpanelcrop == 1 else "both")
img.gammaCorrectImage()
if not img.colorOutput:
img.convertToGrayscale()
img.autocontrastImage()
img.resizeImage()
img.optimizeForDisplay(opt.eraserainbow, img.colorOutput)
if img.colorOutput:
pass
elif opt.forcepng:
if not opt.noquantize:
img.quantizeImage()
if opt.format == 'PDF':
img.convertToGrayscale()
elif opt.profile == 'KDX' and opt.format == 'CBZ':
img.convertToGrayscale()
elif opt.pnglegacy:
img.convertToGrayscale()
output.append(img.saveToDir())
return output
except Exception:
return str(sys.exc_info()[1]), sanitizeTrace(sys.exc_info()[2])
def render_page(vector):
"""Render a page range of a document.
Notes:
The PyMuPDF document cannot be part of the argument, because that
cannot be pickled. So we are being passed in just its filename.
This is no performance issue, because we are a separate process and
need to open the document anyway.
Any page-specific function can be processed here - rendering is just
an example - text extraction might be another.
The work must however be self-contained: no inter-process communication
or synchronization is possible with this design.
Care must also be taken with which parameters are contained in the
argument, because it will be passed in via pickling by the Pool class.
So any large objects will increase the overall duration.
Args:
vector: a list containing required parameters.
"""
# recreate the arguments
idx = vector[0] # this is the segment number we have to process
cpu = vector[1] # number of CPUs
filename = vector[2] # document filename
output_dir = vector[3]
target_width = vector[4]
target_height = vector[5]
pdf_width = vector[6]
with pymupdf.open(filename) as doc: # open the document
num_pages = doc.page_count # get number of pages
# pages per segment: make sure that cpu * seg_size >= num_pages!
seg_size = int(num_pages / cpu + 1)
seg_from = idx * seg_size # our first page number
seg_to = min(seg_from + seg_size, num_pages) # last page number
for i in range(seg_from, seg_to): # work through our page segment
page = doc[i]
if not pdf_width or page.rect.width > page.rect.height:
zoom = target_height / page.rect.height
else:
zoom = target_width / page.rect.width
mat = pymupdf.Matrix(zoom, zoom)
# TODO: decide colorspace earlier so later color check is cheaper.
# This is actually pretty hard when you have to deal with color vector text
pix = page.get_pixmap(matrix=mat, colorspace='RGB', alpha=False)
pix.save(os.path.join(output_dir, "p-%i.png" % i))
print("Processed page numbers %i through %i" % (seg_from, seg_to - 1))
def extract_page(vector):
"""For pages with single image (and no text). Otherwise it's recommended to use render_page()
Notes:
The PyMuPDF document cannot be part of the argument, because that
cannot be pickled. So we are being passed in just its filename.
This is no performance issue, because we are a separate process and
need to open the document anyway.
Any page-specific function can be processed here - rendering is just
an example - text extraction might be another.
The work must however be self-contained: no inter-process communication
or synchronization is possible with this design.
Care must also be taken with which parameters are contained in the
argument, because it will be passed in via pickling by the Pool class.
So any large objects will increase the overall duration.
Args:
vector: a list containing required parameters.
"""
# recreate the arguments
idx = vector[0] # this is the segment number we have to process
cpu = vector[1] # number of CPUs
filename = vector[2] # document filename
output_dir = vector[3]
with pymupdf.open(filename) as doc: # open the document
num_pages = doc.page_count # get number of pages
# pages per segment: make sure that cpu * seg_size >= num_pages!
seg_size = int(num_pages / cpu + 1)
seg_from = idx * seg_size # our first page number
seg_to = min(seg_from + seg_size, num_pages) # last page number
for i in range(seg_from, seg_to): # work through our page segment
output_path = os.path.join(output_dir, "p-%i.png" % i)
page = doc.load_page(i)
image_list = page.get_images()
if len(image_list) > 1:
raise UserWarning("mupdf_pdf_extract_page_image() function can be used only with single image pages.")
if not image_list:
continue
else:
xref = image_list[0][0]
d = doc.extract_image(xref)
if d['cs-name'] == 'DeviceCMYK':
pix = pymupdf.Pixmap(doc, xref)
pix = pymupdf.Pixmap(pymupdf.csRGB, pix)
pix.save(output_path)
else:
with open(Path(output_path).with_suffix('.' + d['ext']), "wb") as imgout:
imgout.write(d["image"])
print("Processed page numbers %i through %i" % (seg_from, seg_to - 1))
def mupdf_pdf_process_pages_parallel(filename, output_dir, target_width, target_height):
render = False
with pymupdf.open(filename) as doc:
for page in doc:
page_text = page.get_text().strip()
if page_text != "":
render = True
break
if len(page.get_images()) > 1:
render = True
break
if len(page.get_images()) == 1:
image = page.get_images()[0]
if not image[5] or image[8] == 'CCITTFaxDecode':
render = True
break
cpu = cpu_count()
# make vectors of arguments for the processes
vectors = [(i, cpu, filename, output_dir, target_width, target_height, options.pdfwidth) for i in range(cpu)]
print("Starting %i processes for '%s'." % (cpu, filename))
start = perf_counter()
with Pool() as pool:
results = pool.map(
render_page if render else extract_page, vectors
)
end = perf_counter()
print(f"MuPDF: {end - start} sec")
def getWorkFolder(afile, workdir=None):
if not workdir:
if options.tempdir:
workdir = mkdtemp('', 'KCC-', os.path.dirname(afile))
else:
workdir = mkdtemp('', 'KCC-')
fullPath = os.path.join(workdir, 'OEBPS', 'Images')
else:
fullPath = workdir
if options.tempdir:
check_path = os.path.dirname(afile)
else:
check_path = gettempdir()
DISK_WARNING = "Not enough disk space to perform conversion. Try Temp Directory option."
if os.path.isdir(afile):
if disk_usage(check_path)[2] < getDirectorySize(afile) * 2.5:
raise UserWarning(DISK_WARNING)
try:
copytree(afile, fullPath)
sanitizePermissions(fullPath)
return workdir
except Exception:
rmtree(workdir, True)
raise UserWarning("Failed to prepare a workspace.")
elif os.path.isfile(afile):
if disk_usage(check_path)[2]< os.path.getsize(afile) * 2.5:
raise UserWarning(DISK_WARNING)
if afile.lower().endswith('.pdf'):
if not os.path.exists(fullPath):
os.makedirs(fullPath)
path = workdir
sanitizePermissions(path)
if options.legacyextract:
pdf = pdfjpgextract.PdfJpgExtract(afile, fullPath)
njpg = pdf.extract()
if njpg == 0:
raise UserWarning("Failed to extract images from PDF file.")
return workdir
target_width, target_height = options.profileData[1]
if options.cropping == 1:
target_height *= 1.2 #Account for possible margin at the top and bottom
target_width *= 1.2
elif options.cropping == 2:
target_height *= 1.25 #Account for possible margin at the top and bottom with page number
target_width *= 1.25
try:
mupdf_pdf_process_pages_parallel(afile, fullPath, target_width, target_height)
except Exception as e:
rmtree(path, True)
raise UserWarning(f"Failed to extract images from PDF file. {e}")
return workdir
else:
if not os.path.exists(fullPath):
os.makedirs(fullPath)
try:
cbx = comicarchive.ComicArchive(afile)
path = cbx.extract(fullPath)
if options.lightnovel:
return workdir
sanitizePermissions(path)
tdir = os.listdir(fullPath)
if len(tdir) == 2 and 'ComicInfo.xml' in tdir:
tdir.remove('ComicInfo.xml')
if os.path.isdir(os.path.join(fullPath, tdir[0])):
os.replace(
os.path.join(fullPath, 'ComicInfo.xml'),
os.path.join(fullPath, tdir[0], 'ComicInfo.xml')
)
if len(tdir) == 1 and os.path.isdir(os.path.join(fullPath, tdir[0])):
for file in os.listdir(os.path.join(fullPath, tdir[0])):
move(os.path.join(fullPath, tdir[0], file), fullPath)
os.rmdir(os.path.join(fullPath, tdir[0]))
if options.legacyextract:
return workdir
if afile.lower().endswith('.epub'):
container = ET.parse(os.path.join(path, 'META-INF', 'container.xml'))
opf_path = container.find(r'.//{*}rootfile').attrib['full-path']
opf_path = os.path.join(path, opf_path)
opf = ET.parse(opf_path)
spine = []
for spine_item in opf.findall(r'.//{*}itemref'):
spine.append(spine_item.attrib.get('idref'))
manifest_dict = {}
for manifest_item in opf.findall(".//*[@media-type='application/xhtml+xml']"):
manifest_dict[manifest_item.attrib.get('id')] = manifest_item.attrib.get('href')
ordered_image_paths = []
for i, spine_item in enumerate(spine):
try:
page_path = os.path.join(os.path.dirname(opf_path), manifest_dict[spine_item])
page = ET.parse(page_path)
except Exception:
continue
imgs = page.findall(r'.//{*}img') + page.findall(r'.//{*}image')
largest_size = 0
img_path = None
for img in imgs:
for key in img.attrib:
if 'src' in key or 'href' in key:
temp_img_path = img.attrib[key]
if temp_img_path.startswith('..'):
temp_img_path = os.path.join(os.path.dirname(opf_path), os.path.dirname(manifest_dict[spine_item]), temp_img_path)
else:
temp_img_path = os.path.join(os.path.dirname(opf_path), os.path.dirname(manifest_dict[spine_item]), temp_img_path)
try:
temp_size = os.path.getsize(temp_img_path)
if temp_size > largest_size:
largest_size = temp_size
img_path = temp_img_path
except OSError:
pass
# TODO empty image
if img_path:
ordered_image_paths.append(img_path)
# fallback if naive spine extraction fails
if not ordered_image_paths:
return workdir
if options.tempdir:
workdir2 = mkdtemp('', 'KCC-', os.path.dirname(afile))
else:
workdir2 = mkdtemp('', 'KCC-')
for i, img_path in enumerate(ordered_image_paths):
_, ext = os.path.splitext(img_path)
fullpath2 = os.path.join(workdir2, 'OEBPS', 'Images')
os.makedirs(fullpath2, exist_ok=True)
shutil.copyfile(img_path, os.path.join(fullpath2, f"{i}{ext}"))
rmtree(workdir, True)
return workdir2
return workdir
finally:
pass
else:
raise UserWarning("Failed to open source file/directory.")
def getOutputFilename(srcpath, wantedname, ext, tomenumber):
source_path = Path(srcpath)
if srcpath[-1] == os.path.sep:
srcpath = srcpath[:-1]
if 'Ko' in options.profile and options.format == 'EPUB':
if options.noKepub:
# Just use normal epub extension if no_kepub option is true
ext = '.epub'
else:
ext = '.kepub.epub'
if wantedname is not None:
wanted_root, wanted_ext = os.path.splitext(wantedname)
if wantedname.endswith(ext):
filename = os.path.abspath(wantedname)
elif wanted_ext == '.mobi' and ext == '.epub':
filename = os.path.abspath(wanted_root + ext)
# output directory
else:
abs_path = os.path.abspath(options.output)
if not os.path.exists(abs_path):
os.mkdir(abs_path)
if source_path.is_file():
filename = os.path.join(os.path.abspath(options.output), source_path.stem + tomenumber + ext)
else:
filename = os.path.join(os.path.abspath(options.output), source_path.name + tomenumber + ext)
elif os.path.isdir(srcpath):
filename = srcpath + tomenumber + ext
else:
if 'Ko' in options.profile and options.format == 'EPUB':
if source_path.is_file():
name = re.sub(r'\W+', '_', source_path.stem) + tomenumber + ext
else:
name = re.sub(r'\W+', '_', source_path.name) + tomenumber + ext
filename = source_path.with_name(name)
else:
filename = os.path.splitext(srcpath)[0] + tomenumber + ext
if os.path.isfile(filename):
counter = 0
basename = os.path.splitext(filename)[0]
while os.path.isfile(basename + '_kcc' + str(counter) + ext):
counter += 1
filename = basename + '_kcc' + str(counter) + ext
elif options.format == 'MOBI' and ext == '.epub':
counter = 0
basename = os.path.splitext(filename)[0]
if os.path.isfile(basename + '.mobi'):
while os.path.isfile(basename + '_kcc' + str(counter) + '.mobi'):
counter += 1
filename = basename + '_kcc' + str(counter) + ext
return filename
def getMetadata(path, originalpath):
xmlPath = os.path.join(path, 'ComicInfo.xml')
options.comicinfo_chapters = []
options.summary = ''
titleSuffix = ''
options.volume = ''
options.number = ''
options.series = ''
if options.title == 'defaulttitle':
defaultTitle = True
if os.path.isdir(originalpath):
options.title = os.path.basename(originalpath)
else:
options.title = os.path.splitext(os.path.basename(originalpath))[0]
else:
defaultTitle = False
if options.author == 'defaultauthor':
defaultAuthor = True
options.authors = ['KCC']
else:
defaultAuthor = False
options.authors = [options.author]
if os.path.exists(xmlPath):
try:
xml = metadata.MetadataParser(xmlPath)
except Exception:
os.remove(xmlPath)
return
if options.metadatatitle == 2:
options.title = xml.data['Title']
elif defaultTitle:
if xml.data['Series']:
options.title = xml.data['Series']
if xml.data['Volume']:
titleSuffix += ' Vol. ' + xml.data['Volume'].zfill(2)
options.volume = xml.data['Volume']
if xml.data['Number']:
titleSuffix += ' #' + xml.data['Number'].zfill(3)
options.number = xml.data['Number']
if options.metadatatitle == 1 and xml.data['Title']:
titleSuffix += ': ' + xml.data['Title']
options.title += titleSuffix
if defaultAuthor:
options.authors = []
for field in ['Writers', 'Pencillers', 'Inkers', 'Colorists']:
for person in xml.data[field]:
options.authors.append(person)
if len(options.authors) > 0:
options.authors = list(set(options.authors))
options.authors.sort()
else:
options.authors = ['KCC']
if xml.data['Bookmarks']:
options.comicinfo_chapters = xml.data['Bookmarks']
if xml.data['Summary']:
options.summary = xml.data['Summary']
if xml.data['Series']:
options.series = xml.data['Series']
os.remove(xmlPath)
if originalpath.lower().endswith('.pdf'):
with pymupdf.open(originalpath) as doc:
if options.metadatatitle and doc.metadata['title']:
options.title = doc.metadata['title']
if defaultAuthor and doc.metadata['author']:
options.authors = [doc.metadata['author']]
def getDirectorySize(start_path='.'):
total_size = 0
for dirpath, _, filenames in os.walk(start_path):
for f in filenames:
fp = os.path.join(dirpath, f)
total_size += os.path.getsize(fp)
return total_size
def getPanelViewResolution(imagesize, deviceres):
scale = float(deviceres[0]) / float(imagesize[0])
return int(deviceres[0]), int(scale * imagesize[1])
def getPanelViewSize(deviceres, size):
x = int(deviceres[0] / 2 - size[0] / 2) / deviceres[0] * 100
y = int(deviceres[1] / 2 - size[1] / 2) / deviceres[1] * 100
return str(int(x)), str(int(y))
def removeNonImages(filetree):
# clean dot from original file
dot_clean(filetree)
for root, dirs, files in os.walk(filetree):
for name in files:
_, ext = getImageFileName(name)
if ext not in IMAGE_TYPES:
if os.path.exists(os.path.join(root, name)):
os.remove(os.path.join(root, name))
# remove empty nested folders
for root, dirs, files in os.walk(filetree, False):
if not files and not dirs:
os.rmdir(root)
if not os.listdir(Path(filetree).parent):
raise UserWarning('No images detected, nested archives are not supported.')
def sanitizeTree(filetree, prefix='kcc'):
chapterNames = {}
page = 1
cover_path = None
for root, dirs, files in os.walk(filetree):
files.sort(key=OS_SORT_KEY)
for name in files:
_, ext = getImageFileName(name)
# 9999 page limit
unique_name = f'{prefix}-{page:04}'
page += 1
newKey = os.path.join(root, unique_name + ext)
key = os.path.join(root, name)
if key != newKey:
os.replace(key, newKey)
if not cover_path:
cover_path = newKey
is_natural_sorted = False
if os_sorted(dirs) == sorted(dirs):
is_natural_sorted = True
dirs.sort(key=OS_SORT_KEY)
for i, name in enumerate(dirs):
tmpName = name
slugified = slugify(name, is_natural_sorted)
while os.path.exists(os.path.join(root, slugified)) and name.upper() != slugified.upper():
slugified += "A"
chapterNames[slugified] = tmpName
newKey = os.path.join(root, slugified)
key = os.path.join(root, name)
if key != newKey:
os.replace(key, newKey)
dirs[i] = newKey
return chapterNames, cover_path
def flattenTree(filetree):
for root, dirs, files in os.walk(filetree, topdown=False):
for name in files:
os.rename(os.path.join(root, name), os.path.join(filetree, name))
for name in dirs:
os.rmdir(os.path.join(root, name))
def sanitizePermissions(filetree):
for root, dirs, files in os.walk(filetree, False):
for name in files:
os.chmod(os.path.join(root, name), S_IWRITE | S_IREAD)
for name in dirs:
os.chmod(os.path.join(root, name), S_IWRITE | S_IREAD | S_IEXEC)
dot_clean(filetree)
def chunk_directory(path):
level = -1
for root, _, files in os.walk(os.path.join(path, 'OEBPS', 'Images')):
for f in files:
# Windows MAX_LEN = 260 plus some buffer
if os.name == 'nt' and len(os.path.join(root, f)) > 220:
flattenTree(os.path.join(path, 'OEBPS', 'Images'))
level = 1
break
if getImageFileName(f):
newLevel = os.path.join(root, f).replace(os.path.join(path, 'OEBPS', 'Images'), '').count(os.sep)
if level != -1 and level != newLevel:
flattenTree(os.path.join(path, 'OEBPS', 'Images'))
level = 1
break
else:
level = newLevel
if level > 0:
parent = pathlib.Path(path).parent
chunker = chunk_process(os.path.join(path, 'OEBPS', 'Images'), level, parent)
path = [path]
for tome in chunker:
path.append(tome)
return path
else:
raise UserWarning('Unsupported directory structure.')
def chunk_process(path, mode, parent):
output = []
currentSize = 0
currentTarget = path
if options.targetsize:
targetSize = options.targetsize * 1048576
elif options.webtoon:
targetSize = 104857600
else:
targetSize = 419430400
if options.batchsplit == 2 and mode == 2:
mode = 3
if options.batchsplit == 1 and mode == 2:
with os.scandir(path) as it:
for entry in it:
if not entry.name.startswith('.') and entry.is_dir():
if getDirectorySize(os.path.join(path, entry)) > targetSize:
flattenTree(path)
mode = 1
break
if mode < 3:
for root, dirs, files in walkLevel(path, 0):
for name in files if mode == 1 else dirs:
size = 0
if mode == 1:
if 'below' not in name:
size = os.path.getsize(os.path.join(root, name))
if 'above' in name:
size += os.path.getsize(os.path.join(root, name.replace('above', 'below')))
else:
size = getDirectorySize(os.path.join(root, name))
if currentSize + size > targetSize:
currentTarget, pathRoot = createNewTome(parent)
output.append(pathRoot)
currentSize = size
else:
currentSize += size
if path != currentTarget:
move(os.path.join(root, name), os.path.join(currentTarget, name))
else:
firstTome = True
for root, dirs, _ in walkLevel(path, 0):
for name in dirs:
if not firstTome:
currentTarget, pathRoot = createNewTome(parent)
output.append(pathRoot)
move(os.path.join(root, name), os.path.join(currentTarget, name))
else:
firstTome = False
return output
def detectSuboptimalProcessing(tmppath, orgpath):
imageNumber = 0
imageSmaller = 0
alreadyProcessed = False
for root, _, files in os.walk(tmppath, False):
for name in files:
if getImageFileName(name) is not None:
if not alreadyProcessed and '-kcc' in getImageFileName(name)[0]:
alreadyProcessed = True
path = os.path.join(root, name)
pathOrg = orgpath + path.split('OEBPS' + os.path.sep + 'Images')[1]
if os.path.getsize(path) == 0:
rmtree(os.path.join(tmppath, '..', '..'), True)
raise RuntimeError('Image file %s is corrupted.' % pathOrg)
try:
img = Image.open(path)
imageNumber += 1
# count images smaller than device resolution
if options.profileData[1][0] > img.size[0] and options.profileData[1][1] > img.size[1]:
imageSmaller += 1
except Exception as err:
rmtree(os.path.join(tmppath, '..', '..'), True)
if 'decoder' in str(err) and 'not available' in str(err):
raise RuntimeError('Pillow was compiled without JPG and/or PNG decoder.')
else:
raise RuntimeError('Image file %s is corrupted. Error: %s' % (pathOrg, str(err)))
else:
try:
if os.path.exists(os.path.join(root, name)):
os.remove(os.path.join(root, name))
except OSError as e:
raise RuntimeError(f"{name}: {e}")
if alreadyProcessed:
print("WARNING: Source files are probably created by KCC. The second conversion will decrease quality.")
if GUI:
GUI.addMessage.emit('Source files are probably created by KCC. The second conversion will decrease quality.'
, 'warning', False)
GUI.addMessage.emit('', '', False)
if imageSmaller > imageNumber * 0.25 and not options.upscale and not options.stretch and not options.profile.startswith('KS'):
print("WARNING: More than 25% of images are smaller than target device resolution. "
"Consider enabling stretching or upscaling to improve readability.")
if GUI:
GUI.addMessage.emit('More than 25% of images are smaller than target device resolution.', 'warning', False)
GUI.addMessage.emit('Consider enabling stretching or upscaling to improve readability.', 'warning', False)
GUI.addMessage.emit('', '', False)
def createNewTome(parent):
tomePathRoot = mkdtemp('', 'KCC-', parent)
tomePath = os.path.join(tomePathRoot, 'OEBPS', 'Images')
os.makedirs(tomePath)
return tomePath, tomePathRoot
def slugify(value, is_natural_sorted):
if options.format == 'CBZ' and is_natural_sorted:
return value
if options.format != 'CBZ':
# convert all unicode to ascii via slugify
value = slugify_ext(value, regex_pattern=r'[^-a-z0-9_\.]+').strip('.')
if not is_natural_sorted:
# pad zeros to numbers
value = sub(r'0*([0-9]{4,})', r'\1', sub(r'([0-9]+)', r'0000\1', value, count=2))
return value
def makeZIP(zipfilename, basedir, job_progress='', isepub=False):
start = perf_counter()
if SEVENZIP in available_archive_tools():
if isepub:
mimetypeFile = open(os.path.join(basedir, '!mimetype'), 'w')
mimetypeFile.write('application/epub+zip')
mimetypeFile.close()
subprocess_run([SEVENZIP, 'a', '-mx0', '-tzip', zipfilename, "*"], capture_output=True, check=True, cwd=basedir)
# crazy hack to ensure mimetype is first when using 7zip
if isepub:
subprocess_run([SEVENZIP, 'rn', zipfilename, '!mimetype', 'mimetype'], capture_output=True, check=True, cwd=basedir)
else:
zipOutput = ZipFile(zipfilename, 'w', ZIP_STORED)
if isepub:
zipOutput.writestr('mimetype', 'application/epub+zip', ZIP_STORED)
for dirpath, _, filenames in os.walk(basedir):
for name in filenames:
path = os.path.normpath(os.path.join(dirpath, name))
aPath = os.path.normpath(os.path.join(dirpath.replace(basedir, ''), name))
if os.path.isfile(path):
zipOutput.write(path, aPath)
zipOutput.close()
end = perf_counter()
print(f"{job_progress}makeZIP time: {end - start} seconds")
return zipfilename
def makeParser():
psr = ArgumentParser(prog="kcc-c2e", usage="kcc-c2e [options] [input]", add_help=False)
mandatory_options = psr.add_argument_group("MANDATORY")
main_options = psr.add_argument_group("MAIN")
processing_options = psr.add_argument_group("PROCESSING")
output_options = psr.add_argument_group("OUTPUT SETTINGS")
custom_profile_options = psr.add_argument_group("CUSTOM PROFILE")
other_options = psr.add_argument_group("OTHER")
mandatory_options.add_argument("input", action="extend", nargs="*", default=None,
help="Full path to comic folder or file(s) to be processed.")
main_options.add_argument("-p", "--profile", action="store", dest="profile", default="KV",
help=f"Device profile (Available options: {', '.join(image.ProfileData.Profiles.keys())})"
" [Default=KV]")
main_options.add_argument("-m", "--manga-style", action="store_true", dest="righttoleft", default=False,
help="Manga style (right-to-left reading and splitting)")
main_options.add_argument("--lightnovel", action="store_true", dest="lightnovel", default=False,
help="Only resize images and preserve original file structure.")
main_options.add_argument("--ebok", action="store_true", dest="ebok", default=False,
help="Force EBOK tag instead of PDOC for MOBI")
main_options.add_argument("--invertdirection", action="store_true", dest="invertdirection", default=False,
help="Invert page turn direction")
main_options.add_argument("-q", "--hq", action="store_true", dest="hq", default=False,
help="Try to increase the quality of magnification")
main_options.add_argument("-2", "--two-panel", action="store_true", dest="autoscale", default=False,
help="Display two not four panels in Panel View mode")
main_options.add_argument("--vertical4panel", action="store_true", dest="vertical4panel", default=False,
help="Display side panels first in virtual panel view")
main_options.add_argument("-w", "--webtoon", action="store_true", dest="webtoon", default=False,
help="Webtoon processing mode"),
main_options.add_argument("--ts", "--targetsize", type=int, dest="targetsize", default=None,
help="the maximal size of output file in MB."
" [Default=100MB for webtoon and 400MB for others]")
output_options.add_argument("-o", "--output", action="store", dest="output", default=None,
help="Output generated file to specified directory or file")
output_options.add_argument("-t", "--title", action="store", dest="title", default="defaulttitle",
help="Comic title [Default=filename or directory name]")
output_options.add_argument("--metadatatitle", type=int, dest="metadatatitle", default=0,
help="Write title using ComicInfo.xml or other embedded metadata. 1: Combine Title with default schema "
"2: Use Title only")
output_options.add_argument("-a", "--author", action="store", dest="author", default="defaultauthor",
help="Author name [Default=KCC]")
output_options.add_argument("--language", action="store", dest="language", default="en-US",
help="EPUB language [Default=en-US]")
output_options.add_argument("-f", "--format", action="store", dest="format", default="Auto",
help="Output format (Available options: Auto, MOBI, EPUB, CBZ, KFX, MOBI+EPUB, PDF) "
"[Default=Auto]")
output_options.add_argument("--nokepub", action="store_true", dest="noKepub", default=False,
help="If format is EPUB, output file with '.epub' extension rather than '.kepub.epub'")
output_options.add_argument("-b", "--batchsplit", type=int, dest="batchsplit", default="0",
help="Split output into multiple files. 0: Don't split 1: Automatic mode "
"2: Consider every subdirectory as separate volume [Default=0]")
output_options.add_argument("--spreadshift", action="store_true", dest="spreadshift", default=False,
help="Shift first page to opposite side in landscape for spread alignment")
output_options.add_argument("--onepagelandscape", action="store_true", dest="onepagelandscape", default=False,
help="Show a single centered page in landscape")
output_options.add_argument("--norotate", action="store_true", dest="norotate", default=False,
help="Do not rotate double page spreads in spread splitter option.")
output_options.add_argument("--rotateright", action="store_true", dest="rotateright", default=False,
help="Rotate double page spreads in opposite direction.")
output_options.add_argument("--rotatefirst", action="store_true", dest="rotatefirst", default=False,
help="Put rotated 2 page spread first in spread splitter option.")
processing_options.add_argument("-n", "--noprocessing", action="store_true", dest="noprocessing", default=False,
help="Do not modify image and ignore any profile or processing option")
processing_options.add_argument("--legacyextract", action="store_true", dest="legacyextract", default=False,
help="Use the legacy PDF/EPUB image extraction method from older KCC versions")
processing_options.add_argument("--pdfwidth", action="store_true", dest="pdfwidth", default=False,
help="Render vector PDFs to device width instead of height.")
processing_options.add_argument("--smartcovercrop", action="store_true", dest="smartcovercrop", default=False,
help="Attempt to crop main cover from wide image")
processing_options.add_argument("--coverfill", action="store_true", dest="coverfill", default=False,
help="Crop cover to fill screen")
processing_options.add_argument("-u", "--upscale", action="store_true", dest="upscale", default=False,
help="Resize images smaller than device's resolution")
processing_options.add_argument("-s", "--stretch", action="store_true", dest="stretch", default=False,
help="Stretch images to device's resolution")
processing_options.add_argument("-r", "--splitter", type=int, dest="splitter", default="0",
help="Double page parsing mode. 0: Split 1: Rotate 2: Both [Default=0]")
processing_options.add_argument("-g", "--gamma", type=float, dest="gamma", default="0.0",
help="Apply gamma correction to linearize the image [Default=Auto]")
output_options.add_argument("--autolevel", action="store_true", dest="autolevel", default=False,
help="Set most common dark pixel value to be black point for leveling.")
output_options.add_argument("--noautocontrast", action="store_true", dest="noautocontrast", default=False,
help="Disable autocontrast.")
output_options.add_argument("--colorautocontrast", action="store_true", dest="colorautocontrast", default=False,
help="Autocontrast color pages too. Skipped for pages without near blacks or whites.")
output_options.add_argument("--filefusion", action="store_true", dest="filefusion", default=False,
help="Combines all input files into a single file.")
processing_options.add_argument("-c", "--cropping", type=int, dest="cropping", default="2",
help="Set cropping mode. 0: Disabled 1: Margins 2: Margins + page numbers [Default=2]")
processing_options.add_argument("--cp", "--croppingpower", type=float, dest="croppingp", default="1.0",
help="Set cropping power [Default=1.0]")
processing_options.add_argument("--preservemargin", type=int, dest="preservemargin", default="0",
help="After calculating crop, back up specified percentage amount. [Default=0]")
processing_options.add_argument("--cm", "--croppingminimum", type=float, dest="croppingm", default="0.0",
help="Set cropping minimum area ratio [Default=0.0]")
processing_options.add_argument("--ipc", "--interpanelcrop", type=int, dest="interpanelcrop", default="0",
help="Crop empty sections. 0: Disabled 1: Horizontally 2: Both [Default=0]")
processing_options.add_argument("--blackborders", action="store_true", dest="black_borders", default=False,
help="Disable autodetection and force black borders")
processing_options.add_argument("--whiteborders", action="store_true", dest="white_borders", default=False,
help="Disable autodetection and force white borders")
processing_options.add_argument("--forcecolor", action="store_true", dest="forcecolor", default=False,
help="Don't convert images to grayscale")
output_options.add_argument("--eraserainbow", action="store_true", dest="eraserainbow", default=False,
help="Erase rainbow effect on color eink screen by attenuating interfering frequencies")
processing_options.add_argument("--forcepng", action="store_true", dest="forcepng", default=False,
help="Create PNG files instead JPEG for black and white images")
processing_options.add_argument("--force-png-rgb", action="store_true", dest="force_png_rgb", default=False,
help="Force color images to be saved as PNG")
processing_options.add_argument("--webp", action="store_true", dest="webp", default=False,
help="Replace JPG with lossy WEBP and PNG with lossless WEBP")
processing_options.add_argument("--pnglegacy", action="store_true", dest="pnglegacy", default=False,
help="Use a more compatible 8 bit png instead of 4 bit")
processing_options.add_argument("--noquantize", action="store_true", dest="noquantize", default=False,
help="Don't quantize to 16 color PNG")
processing_options.add_argument("--mozjpeg", action="store_true", dest="mozjpeg", default=False,
help="Create JPEG files using mozJpeg")
processing_options.add_argument("--jpeg-quality", type=int, dest="jpegquality",
help="The JPEG quality, on a scale from 0 (worst) to 95 (best). Default 85 for most devices.")
processing_options.add_argument("--maximizestrips", action="store_true", dest="maximizestrips", default=False,
help="Turn 1x4 strips to 2x2 strips")
processing_options.add_argument("-d", "--delete", action="store_true", dest="delete", default=False,
help="Delete source file(s) or a directory. It's not recoverable.")
processing_options.add_argument("--tempdir", action="store_true", dest="tempdir", default=False,
help="Create temporary files directory on source file drive.")
custom_profile_options.add_argument("--customwidth", type=int, dest="customwidth", default=0,
help="Replace screen width provided by device profile")
custom_profile_options.add_argument("--customheight", type=int, dest="customheight", default=0,
help="Replace screen height provided by device profile")
other_options.add_argument("-h", "--help", action="help",
help="Show this help message and exit")
return psr
def checkOptions(options):
options.panelview = True
options.iskindle = False
options.isKobo = False
options.bordersColor = None
options.keep_epub = False
if options.profile in image.ProfileData.ProfilesKindle.keys():
options.iskindle = True
else:
options.isKobo = True
if options.lightnovel:
options.noKepub = True
if not options.iskindle and ('MOBI' in options.format or 'EPUB-200MB' in options.format or 'KFX' in options.format):
raise UserWarning('MOBI/Send to Kindle not supported for non-Kindle profiles')
if options.format == 'PDF-200MB':
options.targetsize = 195
options.format = 'PDF'
if options.batchsplit != 2:
options.batchsplit = 1
if options.format == 'EPUB-200MB':
options.targetsize = 195
options.format = 'EPUB'
if options.batchsplit != 2:
options.batchsplit = 1
if options.format == 'MOBI+EPUB-200MB':
options.keep_epub = True
options.targetsize = 195
options.format = 'MOBI'
if options.batchsplit != 2:
options.batchsplit = 1
if not options.targetsize and options.profile.startswith('Rmk'):
options.targetsize = 95
if options.format == 'MOBI+EPUB':
options.keep_epub = True
options.format = 'MOBI'
options.kfx = False
if options.format == 'Auto':
if options.profile in ['KDX']:
options.format = 'CBZ'
elif options.profile in image.ProfileData.ProfilesKindle.keys():
options.format = 'MOBI'
elif options.profile in image.ProfileData.ProfilesRemarkable.keys():
options.format = 'PDF'
else:
options.format = 'EPUB'
if options.white_borders:
options.bordersColor = 'white'
if options.black_borders:
options.bordersColor = 'black'
# Splitting MOBI is not optional
if (options.format == 'MOBI' or options.format == 'KFX') and options.batchsplit != 2:
options.batchsplit = 1
# Older Kindle models don't support Panel View.
if options.profile == 'K1' or options.profile == 'K2' or options.profile == 'K34' or options.profile == 'KDX':
options.panelview = False
options.hq = False
if not options.hq and not options.autoscale:
options.panelview = False
# Webtoon mode mandatory options
if options.webtoon:
options.panelview = False
options.righttoleft = False
options.upscale = False
options.hq = False
options.white_borders = True
options.bordersColor = 'white'
# Disable all Kindle features for other e-readers
if options.profile == 'OTHER':
options.panelview = False
options.hq = False
if 'Ko' in options.profile:
options.panelview = False
options.hq = False
# KFX output create EPUB that might be can be by jhowell KFX Output Calibre plugin
if options.format == 'KFX':
options.targetsize = 195
options.format = 'EPUB'
options.kfx = True
options.panelview = False
# Override profile data
if options.customwidth != 0 or options.customheight != 0:
X = image.ProfileData.Profiles[options.profile][1][0]
Y = image.ProfileData.Profiles[options.profile][1][1]
if options.customwidth != 0:
X = options.customwidth
if options.customheight != 0:
Y = options.customheight
newProfile = ("Custom", (int(X), int(Y)), image.ProfileData.Palette16,
image.ProfileData.Profiles[options.profile][3])
image.ProfileData.Profiles["Custom"] = newProfile
options.profile = "Custom"
options.profileData = image.ProfileData.Profiles[options.profile]
if not options.jpegquality:
if options.profile.startswith('KS') or options.profile == 'KCS':
options.jpegquality = 90
else:
options.jpegquality = 85
options.kindle_azw3 = options.iskindle and ('MOBI' in options.format or 'EPUB' in options.format)
options.kindle_scribe_azw3 = options.profile.startswith('KS') and options.kindle_azw3
options.webp_output = options.format != 'PDF' and not options.kindle_azw3 and options.webp
# CBZ files on Kindle DX/DXG support higher resolution
if options.profile == 'KDX' and options.format == 'CBZ':
options.profileData = list(image.ProfileData.Profiles[options.profile])
options.profileData[1] = list(options.profileData[1])
options.profileData[1][1] = 1200
if options.kindle_scribe_azw3:
options.profileData = list(image.ProfileData.Profiles[options.profile])
options.profileData[1] = list(options.profileData[1])
options.profileData[1][0] = min(1920, options.profileData[1][0])
return options
def checkTools(source):
source = source.upper()
if source.endswith('.CB7') or source.endswith('.7Z') or source.endswith('.RAR') or source.endswith('.CBR') or \
source.endswith('.ZIP') or source.endswith('.CBZ'):
if SEVENZIP not in available_archive_tools():
print('ERROR: 7z is missing!')
sys.exit(1)
if options.format == 'MOBI':
try:
subprocess_run(['kindlegen', '-locale', 'en'], stdout=PIPE, stderr=STDOUT, check=True)
except (FileNotFoundError, CalledProcessError):
print('ERROR: KindleGen is missing!')
sys.exit(1)
except OSError as e:
print(f"kindlegen: {e.strerror}")
print('Re-install Rosetta/Kindle Previewer/other Intel app?')
print('Please email Amazon to make Kindle Previewer Apple silicon native at amazon.com/kindle-help')
sys.exit(1)
def checkPre(source='KCC-'):
# Make sure that all temporary files are gone
for root, dirs, _ in walkLevel(gettempdir(), 0):
for tempdir in dirs:
if tempdir.startswith(source):
rmtree(os.path.join(root, tempdir), True)
def makeFusion(sources: List[str]):
if len(sources) < 2:
raise UserWarning('Fusion requires at least 2 sources. Did you forget to uncheck fusion?')
start = perf_counter()
first_path = Path(sources[0])
if options.tempdir:
fusion_parent = first_path.parent
else:
# LLL is after KCC
checkPre('LLL-')
fusion_parent = Path(mkdtemp('', 'LLL-'))
if first_path.is_file():
fusion_path = fusion_parent.joinpath(first_path.stem + ' [fused]')
else:
fusion_path = fusion_parent.joinpath(first_path.name + ' [fused]')
print("Running Fusion")
# Check if prefix is needed when user-specified ordering differs from OS natural sorting
path_names = [Path(s).stem if Path(s).is_file() else Path(s).name for s in sources]
needs_prefix = os_sorted(path_names) != path_names
for index, source in enumerate(sources, start=1):
print(f"Processing {source}...")
print("Checking images...")
source_path = Path(source)
# Add the fusion_0001_ prefix to maintain user-specified order if needed
prefix = ''
if needs_prefix:
prefix = f'fusion_{index:04d}_'
if source_path.is_file():
targetpath = fusion_path.joinpath(f'{prefix}{source_path.stem}')
else:
targetpath = fusion_path.joinpath(f'{prefix}{source_path.name}')
path = getWorkFolder(source, str(targetpath))
if path != str(targetpath):
move(os.path.join(path, 'OEBPS', 'Images'), targetpath)
sanitizeTree(targetpath, prefix='fusion')
# TODO: remove flattenTree when subchapters are supported
flattenTree(targetpath)
end = perf_counter()
print(f"makefusion: {end - start} seconds")
print("Combined File: "+ str(fusion_path))
return str(fusion_path)
def makeBook(source, qtgui=None, job_progress=''):
start = perf_counter()
global GUI
GUI = qtgui
if GUI:
GUI.progressBarTick.emit('1')
else:
checkTools(source)
checkPre()
if not options.filefusion:
checkPre('LLL-')
print(f"{job_progress}Preparing source images...")
path = getWorkFolder(source)
print(f"{job_progress}Checking images...")
if options.lightnovel:
for root, _, files in os.walk(os.path.join(path, 'OEBPS', 'Images')):
for file in files:
_, ext = os.path.splitext(file)
if ext.lower() in ('.jpg', '.jpeg', '.png', '.webp', '.gif'):
with Image.open(os.path.join(root, file)) as img:
# TODO: detect BW images saved as RGB
if not options.forcecolor:
if img.mode == 'RGB':
img = img.convert('L')
elif img.mode == 'RGBA':
img = img.convert('LA')
x, y = image.ProfileData.Profiles[options.profile][1]
if options.iskindle:
x = min(x, 1920)
y = min(y, 1920)
if img.size[0] > x or img.size[1] > y:
img = ImageOps.contain(img, (x, y))
img.save(os.path.join(root, file), quality=options.jpegquality)
_, ext = os.path.splitext(source)
if ext != '.epub':
ext = '.cbz'
output_file = getOutputFilename(source, options.output, ext, '')
makeZIP(output_file, os.path.join(path, 'OEBPS', 'Images'), job_progress)
rmtree(path, True)
return [output_file]
getMetadata(os.path.join(path, "OEBPS", "Images"), source)
removeNonImages(os.path.join(path, "OEBPS", "Images"))
detectSuboptimalProcessing(os.path.join(path, "OEBPS", "Images"), source)
chapterNames, cover_path = sanitizeTree(os.path.join(path, 'OEBPS', 'Images'))
if options.filefusion:
# Strip the fusion_0001_ sort prefix from makeFusion if present
chapterNames = {k: sub(r'^fusion_\d{4}_', '', v) for k, v in chapterNames.items()}
cover = None
if not options.webtoon:
cover = image.Cover(cover_path, options)
x, y = image.ProfileData.Profiles[options.profile][1]
if options.webtoon:
comic2panel.main(['-y ' + str(y), '-x' + str(x), '-i', '-m', path], job_progress, qtgui)
options.kfx_resolution = None
if options.kfx:
original_resolutions = []
normalized_resolutions = []
for root, _, files in os.walk(os.path.join(path, "OEBPS", "Images")):
for file in files:
with Image.open(os.path.join(root, file)) as imagef:
original_resolutions.append(imagef.size)
size = get_contain_resolution(imagef, (x, y))
normalized_resolutions.append(size)
counter = Counter(normalized_resolutions)
aspect_ratios = []
filtered_resolutions = []
for w, h in normalized_resolutions:
aspect_ratio = h / w
# page-like aspect ratios, could be improved
if aspect_ratio > 1.3 and aspect_ratio < 1.7:
aspect_ratios.append(aspect_ratio)
filtered_resolutions.append((w, h))
most_common_res, most_common_count = counter.most_common(1)[0]
options.kfx_resolution = most_common_res
if most_common_count / sum(counter.values()) > .6:
pass
#elif max(aspect_ratios) - min(aspect_ratios) < .2:
else:
# get the widest resolution
options.kfx_resolution = max(filtered_resolutions)
# else:
# raise UserWarning('Aspect ratio of pages too different for KFX conversion')
if options.noprocessing:
print(f"{job_progress}Do not process image, ignore any profile or processing option")
else:
print(f"{job_progress}Processing images...")
if GUI:
GUI.progressBarTick.emit(f'{job_progress}Processing images')
imgDirectoryProcessing(os.path.join(path, "OEBPS", "Images"), job_progress)
if GUI:
GUI.progressBarTick.emit('1')
if options.batchsplit > 0 or options.targetsize:
tomes = chunk_directory(path)
else:
tomes = [path]
filepath = []
tomeNumber = 0
if GUI:
if options.format == 'CBZ':
GUI.progressBarTick.emit(f'{job_progress}Compressing CBZ files')
elif options.format == 'PDF':
GUI.progressBarTick.emit(f'{job_progress}Creating PDF files')
else:
GUI.progressBarTick.emit(f'{job_progress}Compressing EPUB files')
GUI.progressBarTick.emit(str(len(tomes) + 1))
GUI.progressBarTick.emit('tick')
options.baseTitle = options.title
options.covers = []
for tome in tomes:
options.uuid = str(uuid4())
if len(tomes) > 9:
tomeNumber += 1
options.title = options.baseTitle + ' [' + str(tomeNumber).zfill(2) + '/' + str(len(tomes)).zfill(2) + ']'
elif len(tomes) > 1:
tomeNumber += 1
options.title = options.baseTitle + ' [' + str(tomeNumber) + '/' + str(len(tomes)) + ']'
if options.format == 'CBZ':
print(f"{job_progress}Creating CBZ file...")
if len(tomes) > 1:
filepath.append(getOutputFilename(source, options.output, '.cbz', ' ' + str(tomeNumber)))
else:
filepath.append(getOutputFilename(source, options.output, '.cbz', ''))
if cover and cover.smartcover:
cover.save_to_folder(os.path.join(tome, 'OEBPS', 'Images', '!cover.jpg'), tomeNumber, len(tomes))
makeZIP(filepath[-1], os.path.join(tome, "OEBPS", "Images"), job_progress)
elif options.format == 'PDF':
print(f"{job_progress}Creating PDF file with PyMuPDF...")
# determine output filename based on source and tome count
suffix = (' ' + str(tomeNumber)) if len(tomes) > 1 else ''
output_file = getOutputFilename(source, options.output, '.pdf', suffix)
if cover and cover.smartcover:
cover.save_to_folder(os.path.join(tome, 'OEBPS', 'Images', 'cover.jpg'), tomeNumber, len(tomes))
# use optimized buildPDF logic with streaming and compression
output_pdf = buildPDF(tome, options.title, job_progress, None, output_file)
filepath.append(output_pdf)
else:
print(f"{job_progress}Creating EPUB file...")
if len(tomes) > 1:
buildEPUB(tome, chapterNames, tomeNumber, True, cover, source, job_progress, len(tomes))
filepath.append(getOutputFilename(source, options.output, '.epub', ' ' + str(tomeNumber)))
else:
buildEPUB(tome, chapterNames, tomeNumber, False, cover, source, job_progress)
filepath.append(getOutputFilename(source, options.output, '.epub', ''))
makeZIP(filepath[-1], tome, job_progress, True)
rmtree(tome, True)
if GUI:
GUI.progressBarTick.emit('tick')
if not GUI and options.format == 'MOBI' and not options.lightnovel:
print(f"{job_progress}Creating MOBI files...")
work = []
for i in filepath:
work.append([i])
output = makeMOBI(work, GUI)
for errors in output:
if errors[0] != 0:
print(f"{job_progress}Error: KindleGen failed to create MOBI!")
print(errors)
return filepath
k = kindle.Kindle(options.profile)
if k.path and k.coverSupport:
print(f"{job_progress}Kindle detected. Uploading covers...")
for i in filepath:
output = makeMOBIFix(i, options.covers[filepath.index(i)][1])
if not output[0]:
print(f'{job_progress}Error: Failed to tweak KindleGen output!')
return filepath
if cover and k.path and k.coverSupport:
options.covers[filepath.index(i)][0].saveToKindle(k, options.covers[filepath.index(i)][1])
if options.delete:
if os.path.isfile(source):
os.remove(source)
elif os.path.isdir(source):
rmtree(source, True)
end = perf_counter()
print(f"{job_progress}makeBook: {end - start} seconds")
if options.filefusion:
rmtree(source, True)
checkPre('LLL-')
return filepath
def makeMOBIFix(item, uuid):
is_pdoc = options.profile in image.ProfileData.ProfilesKindlePDOC.keys()
if options.ebok:
is_pdoc = False
if not options.keep_epub:
os.remove(item)
mobiPath = item.replace('.epub', '.mobi')
try:
dualmetafix.DualMobiMetaFix(mobiPath, bytes(uuid, 'UTF-8'), is_pdoc)
return [True]
except Exception as err:
return [False, format(err)]
def makeMOBIWorkerTick(output):
makeMOBIWorkerOutput.append(output)
if output[0] != 0:
makeMOBIWorkerPool.terminate()
if GUI:
GUI.progressBarTick.emit('tick')
if not GUI.conversionAlive:
makeMOBIWorkerPool.terminate()
def makeMOBIWorker(item):
item = item[0]
kindlegenErrorCode = 0
kindlegenError = ''
try:
if os.path.getsize(item) < 629145600:
start = perf_counter()
output = subprocess_run(['kindlegen', '-dont_append_source', '-locale', 'en', item],
stdout=PIPE, stderr=STDOUT, encoding='UTF-8', errors='ignore', check=True)
end = perf_counter()
print(f"kindlegen: {end - start} sec")
else:
# ERROR: EPUB too big
kindlegenErrorCode = 23026
return [kindlegenErrorCode, kindlegenError, item]
except CalledProcessError as err:
for line in err.stdout.splitlines():
# ERROR: Generic error
if "Error(" in line:
kindlegenErrorCode = 1
kindlegenError = line
# ERROR: EPUB too big
if ":E23026:" in line:
kindlegenErrorCode = 23026
if kindlegenErrorCode > 0:
break
if ":I1036: Mobi file built successfully" in line:
return [0, '', item]
if ":I1037: Mobi file built with WARNINGS!" in line:
return [0, '', item]
# ERROR: KCC unknown generic error
if kindlegenErrorCode == 0:
kindlegenErrorCode = err.returncode
kindlegenError = err.stdout
return [kindlegenErrorCode, kindlegenError, item]
def makeMOBI(work, qtgui=None):
global GUI, makeMOBIWorkerPool, makeMOBIWorkerOutput
GUI = qtgui
makeMOBIWorkerOutput = []
availableMemory = virtual_memory().total / 1000000000
if availableMemory <= 2:
threadNumber = 1
elif 2 < availableMemory <= 4:
threadNumber = 2
elif 4 < availableMemory:
threadNumber = 4
else:
threadNumber = None
makeMOBIWorkerPool = Pool(threadNumber, maxtasksperchild=10)
for i in work:
makeMOBIWorkerPool.apply_async(func=makeMOBIWorker, args=(i, ), callback=makeMOBIWorkerTick)
makeMOBIWorkerPool.close()
makeMOBIWorkerPool.join()
return makeMOBIWorkerOutput
Reference in New Issue View Git Blame Copy Permalink