public/kcc
1
0
Fork 0
mirror of https://github.com/ciromattia/kcc synced 2025-12-13 17:56:30 +00:00
Code Issues Releases Wiki Activity

Added subfolder support

Browse Source
This commit is contained in:
Ciro Mattia Gonano
2013-01-21 13:15:19 +01:00
parent e4847e6cf4
commit 89b19f2519
3 changed files with 159 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -15,7 +15,8 @@ It also optimizes comic images by:
- flat folders - flat folders
- PDF *(extracting only contained JPG images)* - PDF *(extracting only contained JPG images)*
For now the script does not understand folder depth, so it will work on flat folders/archives only. ~~For now the script does not understand folder depth, so it will work on flat folders/archives only.~~
As of v. 1.50, KCC supports subfolders!
## REQUIREMENTS ## REQUIREMENTS
- `kindlegen` in /usr/local/bin/ - `kindlegen` in /usr/local/bin/
@@ -90,6 +91,7 @@ and installed in `/usr/local/bin/`
- 1.40 - Added some options for controlling image optimization - 1.40 - Added some options for controlling image optimization
Further optimization (ImageOps, page numbering cut, autocontrast) Further optimization (ImageOps, page numbering cut, autocontrast)
- 1.41 - Fixed a serious bug on resizing when img ratio was bigger than device one - 1.41 - Fixed a serious bug on resizing when img ratio was bigger than device one
- 1.50 - Added subfolder support for multiple chapters.
- 2.00 - GUI! AppleScript is gone and Tk is used to provide cross-platform GUI support. - 2.00 - GUI! AppleScript is gone and Tk is used to provide cross-platform GUI support.
## TODO ## TODO

278
kcc/comic2ebook.py
View File

@@ -29,6 +29,7 @@
# 1.40 - Added some options for controlling image optimization # 1.40 - Added some options for controlling image optimization
# Further optimization (ImageOps, page numbering cut, autocontrast) # Further optimization (ImageOps, page numbering cut, autocontrast)
# 1.41 - Fixed a serious bug on resizing when img ratio was bigger than device one # 1.41 - Fixed a serious bug on resizing when img ratio was bigger than device one
# 1.50 - Support for subfolders
# #
# Todo: # Todo:
# - Add gracefully exit for CBR if no rarfile.py and no unrar # - Add gracefully exit for CBR if no rarfile.py and no unrar
@@ -36,85 +37,84 @@
# - Improve error reporting # - Improve error reporting
# - recurse into dirtree for multiple comics # - recurse into dirtree for multiple comics
__version__ = '1.30' __version__ = '1.50'
import os import os
import sys import sys
from optparse import OptionParser from optparse import OptionParser
import image, cbxarchive, pdfjpgextract import image, cbxarchive, pdfjpgextract
class HTMLbuilder: def buildHTML(path,file):
filename = getImageFileName(file)
def getResult(self): if filename is not None:
return getImageFileName(self.file) htmlfile = os.path.join(path,filename[0] + '.html')
f = open(htmlfile, "w")
def __init__(self, dstdir, file): f.writelines(["<!DOCTYPE html SYSTEM \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n",
self.file = file "<html xmlns=\"http://www.w3.org/1999/xhtml\">\n",
filename = getImageFileName(file) "<head>\n",
if filename is not None: "<title>",filename[0],"</title>\n",
htmlfile = dstdir + '/' + filename[0] + '.html' "<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\"/>\n",
f = open(htmlfile, "w") "</head>\n",
f.writelines(["<!DOCTYPE html SYSTEM \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n", "<body>\n",
"<html xmlns=\"http://www.w3.org/1999/xhtml\">\n", "<div><img src=\"",file,"\" /></div>\n",
"<head>\n", "</body>\n",
"<title>",filename[0],"</title>\n", "</html>"
"<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\"/>\n", ])
"</head>\n",
"<body>\n",
"<div><img src=\"",file,"\" /></div>\n",
"</body>\n",
"</html>"
])
f.close()
return
class NCXbuilder:
def __init__(self, dstdir, title):
ncxfile = dstdir + '/content.ncx'
f = open(ncxfile, "w")
f.writelines(["<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
"<!DOCTYPE ncx PUBLIC \"-//NISO//DTD ncx 2005-1//EN\" \"http://www.daisy.org/z3986/2005/ncx-2005-1.dtd\">\n",
"<ncx version=\"2005-1\" xml:lang=\"en-US\" xmlns=\"http://www.daisy.org/z3986/2005/ncx/\">\n",
"<head>\n</head>\n",
"<docTitle><text>",title,"</text></docTitle>\n",
"<navMap></navMap>\n</ncx>"
])
f.close() f.close()
return return path,file
class OPFBuilder: def buildNCX(dstdir, title):
def __init__(self, profile, dstdir, title, filelist): ncxfile = dstdir + '/toc.ncx'
opffile = dstdir + '/content.opf' f = open(ncxfile, "w")
# read the first file resolution f.writelines(["<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
profilelabel, deviceres, palette = image.ProfileData.Profiles[profile] "<!DOCTYPE ncx PUBLIC \"-//NISO//DTD ncx 2005-1//EN\" \"http://www.daisy.org/z3986/2005/ncx-2005-1.dtd\">\n",
imgres = str(deviceres[0]) + "x" + str(deviceres[1]) "<ncx version=\"2005-1\" xml:lang=\"en-US\" xmlns=\"http://www.daisy.org/z3986/2005/ncx/\">\n",
f = open(opffile, "w") "<head>\n</head>\n",
f.writelines(["<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n", "<docTitle><text>",title,"</text></docTitle>\n",
"<package version=\"2.0\" unique-identifier=\"PrimaryID\" xmlns=\"http://www.idpf.org/2007/opf\">\n", "<navMap></navMap>\n</ncx>"
"<metadata xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:opf=\"http://www.idpf.org/2007/opf\">\n", ])
"<dc:title>",title,"</dc:title>\n", f.close()
"<dc:language>en-US</dc:language>\n", return
"<meta name=\"book-type\" content=\"comic\"/>\n",
"<meta name=\"zero-gutter\" content=\"true\"/>\n", def buildOPF(profile, dstdir, title, filelist):
"<meta name=\"zero-margin\" content=\"true\"/>\n", opffile = dstdir + '/content.opf'
"<meta name=\"fixed-layout\" content=\"true\"/>\n", # read the first file resolution
"<meta name=\"orientation-lock\" content=\"portrait\"/>\n", profilelabel, deviceres, palette = image.ProfileData.Profiles[profile]
"<meta name=\"original-resolution\" content=\"" + imgres + "\"/>\n", imgres = str(deviceres[0]) + "x" + str(deviceres[1])
"</metadata><manifest><item id=\"ncx\" href=\"content.ncx\" media-type=\"application/x-dtbncx+xml\"/>\n"]) f = open(opffile, "w")
for filename in filelist: f.writelines(["<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
f.write("<item id=\"page_" + filename[0] + "\" href=\"" + filename[0] + ".html\" media-type=\"application/xhtml+xml\"/>\n") "<package version=\"2.0\" unique-identifier=\"PrimaryID\" xmlns=\"http://www.idpf.org/2007/opf\">\n",
for filename in filelist: "<metadata xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:opf=\"http://www.idpf.org/2007/opf\">\n",
if '.png' == filename[1]: "<dc:title>",title,"</dc:title>\n",
mt = 'image/png' "<dc:language>en-US</dc:language>\n",
else: "<meta name=\"book-type\" content=\"comic\"/>\n",
mt = 'image/jpeg' "<meta name=\"zero-gutter\" content=\"true\"/>\n",
f.write("<item id=\"img_" + filename[0] + "\" href=\"" + filename[0] + filename[1] + "\" media-type=\"" + mt + "\"/>\n") "<meta name=\"zero-margin\" content=\"true\"/>\n",
f.write("</manifest>\n<spine toc=\"ncx\">\n") "<meta name=\"fixed-layout\" content=\"true\"/>\n",
for filename in filelist: "<meta name=\"orientation-lock\" content=\"portrait\"/>\n",
f.write("<itemref idref=\"page_" + filename[0] + "\" />\n") "<meta name=\"original-resolution\" content=\"" + imgres + "\"/>\n",
f.write("</spine>\n<guide>\n</guide>\n</package>\n") "</metadata><manifest><item id=\"ncx\" href=\"toc.ncx\" media-type=\"application/x-dtbncx+xml\"/>\n"])
f.close() for path in filelist:
return folder = path[0].replace(dstdir,'').lstrip('/')
filename = getImageFileName(path[1])
uniqueid = os.path.join(folder,filename[0]).replace('/','_')
f.write("<item id=\"page_" + uniqueid + "\" href=\"" + os.path.join(folder,filename[0])
+ ".html\" media-type=\"application/xhtml+xml\"/>\n")
#for filename in filelist:
if '.png' == filename[1]:
mt = 'image/png'
else:
mt = 'image/jpeg'
f.write("<item id=\"img_" + uniqueid + "\" href=\"" + os.path.join(folder,path[1]) + "\" media-type=\"" + mt + "\"/>\n")
f.write("</manifest>\n<spine toc=\"ncx\">\n")
for path in filelist:
folder = path[0].replace(dstdir,'').lstrip('/')
filename = getImageFileName(path[1])
uniqueid = os.path.join(folder,filename[0]).replace('/','_')
f.write("<itemref idref=\"page_" + uniqueid + "\" />\n")
f.write("</spine>\n<guide>\n</guide>\n</package>\n")
f.close()
return
def getImageFileName(file): def getImageFileName(file):
filename = os.path.splitext(file) filename = os.path.splitext(file)
@@ -130,6 +130,78 @@ def isInFilelist(file,list):
seen = True seen = True
return seen return seen
def applyImgOptimization(img):
img.optimizeImage()
img.cropWhiteSpace(10.0)
if options.cutpagenumbers:
img.cutPageNumber()
img.resizeImage(options.upscale,options.stretch)
img.quantizeImage()
def dirImgProcess(path):
global options
for (dirpath, dirnames, filenames) in os.walk(path):
for file in filenames:
if getImageFileName(file) is not None:
if options.verbose:
print "Optimizing " + file + " for " + options.profile
else:
print ".",
img = image.ComicPage(os.path.join(dirpath,file), options.profile)
split = img.splitPage(dirpath, options.righttoleft)
if split is not None:
print "Splitted " + file
img0 = image.ComicPage(split[0],options.profile)
img1 = image.ComicPage(split[1],options.profile)
applyImgOptimization(img0)
img0.saveToDir(dirpath)
applyImgOptimization(img1)
img1.saveToDir(dirpath)
else:
applyImgOptimization(img)
img.saveToDir(dirpath)
def genEpubStruct(path):
global options
filelist = []
for (dirpath, dirnames, filenames) in os.walk(path):
for file in filenames:
if getImageFileName(file) is not None:
# put credits at the end
if "credits" in file.lower():
os.rename(os.path.join(dirpath,file), os.path.join(dirpath,'ZZZ999_'+file))
file = 'ZZZ999_'+file
filelist.append(buildHTML(dirpath,file))
#filelist.extend(filenames)
if options.title == 'defaulttitle':
options.title = os.path.basename(path)
buildNCX(path,options.title)
# ensure we're sorting files alphabetically
filelist = sorted(filelist, key=lambda name: (name[0].lower(), name[1].lower()))
buildOPF(options.profile,path,options.title,filelist)
def getWorkFolder(file):
fname = os.path.splitext(file)
if fname[1].lower() == '.pdf':
pdf = pdfjpgextract.PdfJpgExtract(file)
pdf.extract()
return pdf.getPath()
else:
cbx = cbxarchive.CBxArchive(file)
if cbx.isCbxFile():
cbx.extract()
return cbx.getPath()
else:
try:
import shutil
if not os.path.isdir(file + "_orig"):
shutil.copytree(file, file + "_orig")
return file
except OSError:
raise
def Copyright(): def Copyright():
print ('comic2ebook v%(__version__)s. ' print ('comic2ebook v%(__version__)s. '
'Written 2012 by Ciro Mattia Gonano.' % globals()) 'Written 2012 by Ciro Mattia Gonano.' % globals())
@@ -140,7 +212,7 @@ def Usage():
parser.print_help() parser.print_help()
def main(argv=None): def main(argv=None):
global parser global parser, options
usage = "Usage: %prog [options] comic_file|comic_folder" usage = "Usage: %prog [options] comic_file|comic_folder"
parser = OptionParser(usage=usage, version=__version__) parser = OptionParser(usage=usage, version=__version__)
parser.add_option("-p", "--profile", action="store", dest="profile", default="KHD", parser.add_option("-p", "--profile", action="store", dest="profile", default="KHD",
@@ -163,68 +235,14 @@ def main(argv=None):
if len(args) != 1: if len(args) != 1:
parser.print_help() parser.print_help()
return return
dir = args[0] path = args[0]
fname = os.path.splitext(dir) path = getWorkFolder(path)
if fname[1].lower() == '.pdf':
pdf = pdfjpgextract.PdfJpgExtract(dir)
pdf.extract()
dir = pdf.getPath()
else:
cbx = cbxarchive.CBxArchive(dir)
if cbx.isCbxFile():
cbx.extract()
dir = cbx.getPath()
else:
try:
import shutil
shutil.copytree(dir, dir + "_orig")
#dir = dir + "_orig"
except OSError as exc:
raise
filelist = []
if options.imgproc: if options.imgproc:
print "Processing images..." print "Processing images..."
try: dirImgProcess(path)
if options.verbose:
print "Splitting double pages..."
for file in os.listdir(dir):
if getImageFileName(file) is not None:
print ".",
img = image.ComicPage(dir+'/'+file, options.profile)
img.splitPage(dir, options.righttoleft)
for file in os.listdir(dir):
if getImageFileName(file) is not None:
if options.verbose:
print "Optimizing " + file + " for " + options.profile
else:
print ".",
img = image.ComicPage(dir+'/'+file, options.profile)
img.optimizeImage()
img.cropWhiteSpace(10.0)
if options.cutpagenumbers:
img.cutPageNumber()
img.resizeImage(options.upscale,options.stretch)
img.quantizeImage()
img.saveToDir(dir)
except ImportError:
print "Could not load PIL, not optimizing image"
print "Creating ePub structure..." print "Creating ePub structure..."
for file in os.listdir(dir): genEpubStruct(path)
if getImageFileName(file) is not None and isInFilelist(file,filelist) == False:
# put credits at the end
if "credits" in file.lower():
os.rename(dir+'/'+file, dir+'/ZZZ999_'+file)
file = 'ZZZ999_'+file
filename = HTMLbuilder(dir,file).getResult()
if filename is not None:
filelist.append(filename)
if options.title == 'defaulttitle':
options.title = os.path.basename(dir)
NCXbuilder(dir,options.title)
# ensure we're sorting files alphabetically
filelist = sorted(filelist, key=lambda name: name[0].lower())
OPFBuilder(options.profile,dir,options.title,filelist)
if __name__ == "__main__": if __name__ == "__main__":

9
kcc/image.py
View File

@@ -118,6 +118,12 @@ class ComicPage:
method = Image.ANTIALIAS method = Image.ANTIALIAS
if self.image.size[0] <= self.size[0] and self.image.size[1] <= self.size[1]: if self.image.size[0] <= self.size[0] and self.image.size[1] <= self.size[1]:
if not upscale: if not upscale:
# do not upscale but center image in a device-sized image
newImage = Image.new('RGB', (self.size[0], self.size[1]), (255,255,255))
newImage.paste(self.image, (
(self.size[0] - self.image.size[0]) / 2,
(self.size[1] - self.image.size[1]) / 2))
self.image = newImage
return self.image return self.image
else: else:
method = Image.NEAREST method = Image.NEAREST
@@ -170,7 +176,8 @@ class ComicPage:
except IOError as e: except IOError as e:
raise RuntimeError('Cannot write image in directory %s: %s' %(targetdir,e)) raise RuntimeError('Cannot write image in directory %s: %s' %(targetdir,e))
return fileone,filetwo return fileone,filetwo
return None else:
return None
def frameImage(self): def frameImage(self):
foreground = tuple(self.palette[:3]) foreground = tuple(self.palette[:3])