ssokolow/manga_to_html.py

## manga_to_html.py
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""A quick helper for splitting manga pages in a CBZ containing two-page
spreads and then bundling them into base64 URLs in an HTML file so the mobile
Safari preview inside the iOS Files app can act as a quick-and-dirty manga
reader.

Takes .cbz files and produces large .html files.

Currently assumes first image will be a cover and doesn't split it.
"""

# NOTE: This is a quick hack. Most of the polish is from a template that
#       I start all my quick hacks from.

__author__ = "Stephan Sokolow (deitarion/SSokolow)"
__appname__ = "Manga to HTML"
__version__ = "0.1"
__license__ = "MIT"

import base64, logging, os  # noqa: E401
from io import BytesIO
from zipfile import ZipFile

from PIL import Image  # type: ignore

log = logging.getLogger(__name__)

IMAGE_EXTS = Image.registered_extensions()  # Dict[extension, format name]


def write_datauri(image_in: Image, html_fobj):
    tmp = BytesIO()
    image_in.save(tmp, 'jpeg')

    html_fobj.write(b'<img src="data:image/jpeg;base64,')
    html_fobj.write(base64.encodebytes(tmp.getbuffer()))
    html_fobj.write(b'" />')


def process_arg(path):
    log.info("Processing archive %s...", path)
    zbase, zext = os.path.splitext(path)
    outpath = '{}.html'.format(zbase)
    cover_seen = False

    with ZipFile(path) as zobj_in, open(outpath, 'wb') as fobj_out:
        fobj_out.write(b'<!DOCTYPE html>'
            b'<html><head>\n<meta charset="utf-8">'
            b"<style>\n* { margin: 0; padding: 0 }\n"
            b"body { background: black; }\n"
            b"img { width: 100%; margin-bottom: 2px; }\n</style>"
            b"</head><body>\n")

        for zinfo in sorted(zobj_in.infolist(), key=lambda x: x.filename):
            ibase, iext = os.path.splitext(zinfo.filename)
            iext = iext.lower()

            if zinfo.is_dir() or iext not in IMAGE_EXTS:
                log.info("Skipping non-image: %s", zinfo.filename)
            else:
                im = Image.open(zobj_in.open(zinfo.filename, 'r'))
                if not cover_seen:
                    log.info("Copying cover verbatim: %s", zinfo.filename)
                    write_datauri(im, fobj_out)
                    im.close()
                    cover_seen = True
                    continue

                log.info("Processing image: %s", zinfo.filename)

                # im.crop will ideally just take a reference to `im`
                #
                # I'm not sure if this will duplicate the column of pixels at
                # split_point, but it doesn't matter
                split_point = im.size[0] // 2
                page_right = im.crop((split_point, 0, im.size[0], im.size[1]))
                page_left = im.crop((0, 0, split_point, im.size[1]))
                for page in (page_right, page_left):
                    write_datauri(page, fobj_out)
                    page.close()

        fobj_out.write(b"</body>\n</html>")


def main():
    """The main entry point, compatible with setuptools entry points."""
    from argparse import ArgumentParser, RawDescriptionHelpFormatter
    parser = ArgumentParser(formatter_class=RawDescriptionHelpFormatter,
        description=__doc__.replace('\r\n', '\n').split('\n--snip--\n')[0])
    parser.add_argument('-V', '--version', action='version',
        version="%%(prog)s v%s" % __version__)
    parser.add_argument('-v', '--verbose', action="count",
        default=3, help="Increase the verbosity. Use twice for extra effect.")
    parser.add_argument('-q', '--quiet', action="count",
        default=0, help="Decrease the verbosity. Use twice for extra effect.")
    parser.add_argument('path', action="store", nargs="+",
        help="Path to operate on")

    args = parser.parse_args()

    # Set up clean logging to stderr
    log_levels = [logging.CRITICAL, logging.ERROR, logging.WARNING,
                logging.INFO, logging.DEBUG]
    args.verbose = min(args.verbose - args.quiet, len(log_levels) - 1)
    args.verbose = max(args.verbose, 0)
    logging.basicConfig(level=log_levels[args.verbose],
                        format='%(levelname)s: %(message)s')

    for path in args.path:
        process_arg(path)


if __name__ == '__main__':  # pragma: nocover
    main()

# vim: set sw=4 sts=4 expandtab :
	#!/usr/bin/env python3
	# -- coding: utf-8 --
	"""A quick helper for splitting manga pages in a CBZ containing two-page
	spreads and then bundling them into base64 URLs in an HTML file so the mobile
	Safari preview inside the iOS Files app can act as a quick-and-dirty manga
	reader.

	Takes .cbz files and produces large .html files.

	Currently assumes first image will be a cover and doesn't split it.
	"""

	# NOTE: This is a quick hack. Most of the polish is from a template that
	# I start all my quick hacks from.

	__author__ = "Stephan Sokolow (deitarion/SSokolow)"
	__appname__ = "Manga to HTML"
	__version__ = "0.1"
	__license__ = "MIT"

	import base64, logging, os # noqa: E401
	from io import BytesIO
	from zipfile import ZipFile

	from PIL import Image # type: ignore

	log = logging.getLogger(__name__)

	IMAGE_EXTS = Image.registered_extensions() # Dict[extension, format name]


	def write_datauri(image_in: Image, html_fobj):
	tmp = BytesIO()
	image_in.save(tmp, 'jpeg')

	html_fobj.write(b'<img src="data:image/jpeg;base64,')
	html_fobj.write(base64.encodebytes(tmp.getbuffer()))
	html_fobj.write(b'" />')


	def process_arg(path):
	log.info("Processing archive %s...", path)
	zbase, zext = os.path.splitext(path)
	outpath = '{}.html'.format(zbase)
	cover_seen = False

	with ZipFile(path) as zobj_in, open(outpath, 'wb') as fobj_out:
	fobj_out.write(b'<!DOCTYPE html>'
	b'<html><head>\n<meta charset="utf-8">'
	b"<style>\n* { margin: 0; padding: 0 }\n"
	b"body { background: black; }\n"
	b"img { width: 100%; margin-bottom: 2px; }\n</style>"
	b"</head><body>\n")

	for zinfo in sorted(zobj_in.infolist(), key=lambda x: x.filename):
	ibase, iext = os.path.splitext(zinfo.filename)
	iext = iext.lower()

	if zinfo.is_dir() or iext not in IMAGE_EXTS:
	log.info("Skipping non-image: %s", zinfo.filename)
	else:
	im = Image.open(zobj_in.open(zinfo.filename, 'r'))
	if not cover_seen:
	log.info("Copying cover verbatim: %s", zinfo.filename)
	write_datauri(im, fobj_out)
	im.close()
	cover_seen = True
	continue

	log.info("Processing image: %s", zinfo.filename)

	# im.crop will ideally just take a reference to `im`
	#
	# I'm not sure if this will duplicate the column of pixels at
	# split_point, but it doesn't matter
	split_point = im.size[0] // 2
	page_right = im.crop((split_point, 0, im.size[0], im.size[1]))
	page_left = im.crop((0, 0, split_point, im.size[1]))
	for page in (page_right, page_left):
	write_datauri(page, fobj_out)
	page.close()

	fobj_out.write(b"</body>\n</html>")


	def main():
	"""The main entry point, compatible with setuptools entry points."""
	from argparse import ArgumentParser, RawDescriptionHelpFormatter
	parser = ArgumentParser(formatter_class=RawDescriptionHelpFormatter,
	description=__doc__.replace('\r\n', '\n').split('\n--snip--\n')[0])
	parser.add_argument('-V', '--version', action='version',
	version="%%(prog)s v%s" % __version__)
	parser.add_argument('-v', '--verbose', action="count",
	default=3, help="Increase the verbosity. Use twice for extra effect.")
	parser.add_argument('-q', '--quiet', action="count",
	default=0, help="Decrease the verbosity. Use twice for extra effect.")
	parser.add_argument('path', action="store", nargs="+",
	help="Path to operate on")

	args = parser.parse_args()

	# Set up clean logging to stderr
	log_levels = [logging.CRITICAL, logging.ERROR, logging.WARNING,
	logging.INFO, logging.DEBUG]
	args.verbose = min(args.verbose - args.quiet, len(log_levels) - 1)
	args.verbose = max(args.verbose, 0)
	logging.basicConfig(level=log_levels[args.verbose],
	format='%(levelname)s: %(message)s')

	for path in args.path:
	process_arg(path)


	if __name__ == '__main__': # pragma: nocover
	main()

	# vim: set sw=4 sts=4 expandtab :