Embed images in HTML file as dataurl

dataurlify.py

#!/usr/bin/python3

import os
import argparse
import base64
import mimetypes
import re

RE = b'src="([^"]*)"'


def img_to_data(path):
    mime, _ = mimetypes.guess_type(path.decode('ascii', errors='replace'))
    mime = mime.encode('ascii')
    with open(path, 'rb') as fp:
        data = fp.read()
        data64 = b''.join(base64.encodebytes(data).splitlines())
        return b'data:%s;base64,%s' % (mime, data64)


def subfn(m):
    fname = m.group(1)
    dataurl = img_to_data(fname)
    return b'src="%s"' % (dataurl,)


def main():
    parser = argparse.ArgumentParser(description='Embed images in HTML file as dataurl')
    parser.add_argument('input', help='input file name')
    parser.add_argument('output', help='output file name')
    args = parser.parse_args()

    # Chdir to the input HTML directory to correctly resolve relative links.
    inputfname = os.path.abspath(args.input)
    outputfname = os.path.abspath(args.output)
    os.chdir(os.path.dirname(inputfname))

    data = open(inputfname, 'rb').read()
    output = re.sub(RE, subfn, data)
    with open(outputfname, 'wb') as f:
        f.write(output)

if __name__ == '__main__':
    main()