Add PDF output support (#1032)

* Add PDF output support

* optimize

* use with statement

* OS_SORT_KEY

* fix import

* simplify

* fix None

* fix conditional

---------

Co-authored-by: Belgian Coder <>
Co-authored-by: Alex Xu <alexkurosakimh3@gmail.com>

README.md

@@ -12,7 +12,11 @@ like Kindle, Kobo, ReMarkable, and more.
 Pages display in fullscreen without margins, 
 with proper fixed layout support.
 Supported input formats include JPG/PNG/GIF image files in folders, archives, or PDFs.
-Supported output formats include MOBI/AZW3, EPUB, KEPUB, and CBZ.
+Supported output formats include MOBI/AZW3, EPUB, KEPUB, CBZ, and PDF.
+
+**NEW**: PDF output is now supported for direct conversion to reMarkable devices! 
+When using a reMarkable profile (Rmk1, Rmk2, RmkPP), the format automatically defaults to PDF 
+for optimal compatibility with your device's native PDF reader.
 
 The absolute highest quality source files are print quality DRM-free PDFs from Kodansha/[Humble Bundle](https://humblebundleinc.sjv.io/xL6Zv1)/Fanatical,
 which can be directly converted by KCC in v9+. Be sure to check the spread shift option!
@@ -256,7 +260,7 @@ OUTPUT SETTINGS:
   -a AUTHOR, --author AUTHOR
                         Author name [Default=KCC]
   -f FORMAT, --format FORMAT
-                        Output format (Available options: Auto, MOBI, EPUB, CBZ, KFX, MOBI+EPUB) [Default=Auto]
+                        Output format (Available options: Auto, MOBI, EPUB, CBZ, PDF, KFX, MOBI+EPUB) [Default=Auto]
   --nokepub             If format is EPUB, output file with '.epub' extension rather than '.kepub.epub'
   -b BATCHSPLIT, --batchsplit BATCHSPLIT
                         Split output into multiple files. 0: Don't split 1: Automatic mode 2: Consider every subdirectory as separate volume [Default=0]

kindlecomicconverter/KCC_gui.py

@@ -324,6 +324,9 @@ class WorkerThread(QThread):
             if gui_current_format == 'CBZ':
                 MW.addMessage.emit('Creating CBZ files', 'info', False)
                 GUI.progress.content = 'Creating CBZ files'
+            elif gui_current_format == 'PDF':
+                MW.addMessage.emit('Creating PDF files', 'info', False)
+                GUI.progress.content = 'Creating PDF files'
             else:
                 MW.addMessage.emit('Creating EPUB files', 'info', False)
                 GUI.progress.content = 'Creating EPUB files'
@@ -368,6 +371,8 @@ class WorkerThread(QThread):
                 GUI.progress.content = ''
                 if gui_current_format == 'CBZ':
                     MW.addMessage.emit('Creating CBZ files... <b>Done!</b>', 'info', True)
+                elif gui_current_format == 'PDF':
+                    MW.addMessage.emit('Creating PDF files... <b>Done!</b>', 'info', True)
                 else:
                     MW.addMessage.emit('Creating EPUB files... <b>Done!</b>', 'info', True)
                 if 'MOBI' in gui_current_format:
@@ -1011,6 +1016,7 @@ class KCCGUI(KCC_ui.Ui_mainWindow):
             "MOBI/AZW3": {'icon': 'MOBI', 'format': 'MOBI'},
             "EPUB": {'icon': 'EPUB', 'format': 'EPUB'},
             "CBZ": {'icon': 'CBZ', 'format': 'CBZ'},
+            "PDF": {'icon': 'EPUB', 'format': 'PDF'},
             "KFX (does not work)": {'icon': 'KFX', 'format': 'KFX'},
             "MOBI + EPUB": {'icon': 'MOBI', 'format': 'MOBI+EPUB'},
             "EPUB (200MB limit)": {'icon': 'EPUB', 'format': 'EPUB-200MB'},
@@ -1092,11 +1098,11 @@ class KCCGUI(KCC_ui.Ui_mainWindow):
                           'Label': 'KoS'},
             "Kobo Elipsa": {'PVOptions': False, 'ForceExpert': False, 'DefaultFormat': 1, 'DefaultUpscale': True, 'ForceColor': False,
                             'Label': 'KoE'},
-            "reMarkable 1": {'PVOptions': False, 'ForceExpert': False, 'DefaultFormat': 1, 'DefaultUpscale': True, 'ForceColor': False,
+            "reMarkable 1": {'PVOptions': False, 'ForceExpert': False, 'DefaultFormat': 3, 'DefaultUpscale': True, 'ForceColor': False,
                              'Label': 'Rmk1'},
-            "reMarkable 2": {'PVOptions': False, 'ForceExpert': False, 'DefaultFormat': 1, 'DefaultUpscale': True, 'ForceColor': False,
+            "reMarkable 2": {'PVOptions': False, 'ForceExpert': False, 'DefaultFormat': 3, 'DefaultUpscale': True, 'ForceColor': False,
                              'Label': 'Rmk2'},
-            "reMarkable Paper Pro": {'PVOptions': False, 'ForceExpert': False, 'DefaultFormat': 1, 'DefaultUpscale': True, 'ForceColor': True,
+            "reMarkable Paper Pro": {'PVOptions': False, 'ForceExpert': False, 'DefaultFormat': 3, 'DefaultUpscale': True, 'ForceColor': True,
                              'Label': 'RmkPP'},
             "Other": {'PVOptions': False, 'ForceExpert': True, 'DefaultFormat': 1, 'DefaultUpscale': False, 'ForceColor': False,
                       'Label': 'OTHER'},

kindlecomicconverter/comic2ebook.py

@@ -582,6 +582,34 @@ def buildEPUB(path, chapternames, tomenumber, ischunked, cover: image.Cover, len
     buildOPF(path, options.title, filelist, cover)
 
 
+def buildPDF(path, title, 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:
+        # 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"MuPDF output: {end-start} sec")
+    return output_file
+
+
 def imgDirectoryProcessing(path):
     global workerPool, workerOutput
     workerPool = Pool(maxtasksperchild=100)
@@ -659,6 +687,7 @@ def imgFileProcessing(work):
                 pass
             elif opt.forcepng:
                 img.convertToGrayscale()
+                if opt.format != 'PDF':
                     img.quantizeImage()
             else:
                 img.convertToGrayscale()
@@ -1137,6 +1166,7 @@ def detectSuboptimalProcessing(tmppath, orgpath):
                 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:
@@ -1184,7 +1214,6 @@ def slugify(value, is_natural_sorted):
         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, isepub=False):
     start = perf_counter()
     zipfilename = os.path.abspath(zipfilename) + '.zip'
@@ -1209,7 +1238,6 @@ def makeZIP(zipfilename, basedir, isepub=False):
     print(f"makeZIP time: {end - start} seconds")
     return zipfilename
 
-
 def makeParser():
     psr = ArgumentParser(prog="kcc-c2e", usage="kcc-c2e [options] [input]", add_help=False)
 
@@ -1247,7 +1275,7 @@ def makeParser():
     output_options.add_argument("-a", "--author", action="store", dest="author", default="defaultauthor",
                                 help="Author name [Default=KCC]")
     output_options.add_argument("-f", "--format", action="store", dest="format", default="Auto",
-                                help="Output format (Available options: Auto, MOBI, EPUB, CBZ, KFX, MOBI+EPUB) "
+                                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'")
@@ -1337,6 +1365,8 @@ def checkOptions(options):
             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.profile in image.ProfileData.ProfilesKindle.keys():
@@ -1500,6 +1530,8 @@ def makeBook(source, qtgui=None):
     if GUI:
         if options.format == 'CBZ':
             GUI.progressBarTick.emit('Compressing CBZ files')
+        elif options.format == 'PDF':
+            GUI.progressBarTick.emit('Creating PDF files')
         else:
             GUI.progressBarTick.emit('Compressing EPUB files')
         GUI.progressBarTick.emit(str(len(tomes) + 1))
@@ -1521,6 +1553,14 @@ def makeBook(source, qtgui=None):
             else:
                 filepath.append(getOutputFilename(source, options.output, '.cbz', ''))
             makeZIP(tome + '_comic', os.path.join(tome, "OEBPS", "Images"))
+        elif options.format == 'PDF':
+            print("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)
+            # use optimized buildPDF logic with streaming and compression
+            output_pdf = buildPDF(tome, options.title, None, output_file)
+            filepath.append(output_pdf)
         else:
             print("Creating EPUB file...")
             if len(tomes) > 1:
@@ -1530,6 +1570,8 @@ def makeBook(source, qtgui=None):
                 buildEPUB(tome, chapterNames, tomeNumber, False, cover)
                 filepath.append(getOutputFilename(source, options.output, '.epub', ''))
             makeZIP(tome + '_comic', tome, True)
+        # Copy files to final destination (PDF files are already saved directly)
+        if options.format != 'PDF':
             copyfile(tome + '_comic.zip', filepath[-1])
             try:
                 os.remove(tome + '_comic.zip')
@@ -1570,6 +1612,12 @@ def makeBook(source, qtgui=None):
 
     end = perf_counter()
     print(f"makeBook: {end - start} seconds")
+    # Clean up temporary workspace
+    try:
+        rmtree(path, True)
+    except Exception:
+        pass
+    print(filepath)
     return filepath
 
 
@@ -1649,3 +1697,4 @@ def makeMOBI(work, qtgui=None):
     makeMOBIWorkerPool.close()
     makeMOBIWorkerPool.join()
     return makeMOBIWorkerOutput
+

requirements.txt

@@ -9,4 +9,4 @@ mozjpeg-lossless-optimization>=1.2.0
 natsort>=8.4.0
 distro>=1.8.0
 numpy>=1.22.4
-PyMuPDF>=1.26.1
+PyMuPDF>=1.18.0

setup.py

@@ -79,6 +79,7 @@ setuptools.setup(
     install_requires=[
         'pyside6>=6.5.1',
         'Pillow>=11.3.0',
+        'PyMuPDF>=1.18.0',
         'psutil>=5.9.5',
         'python-slugify>=1.2.1,<9.0.0',
         'raven>=6.0.0',