More structure and tests around splitting the page into chunks' DOMs.

[paperdoorknob] / paperdoorknob.py

# paperdoorknob: Print glowfic
#
# This program is free software: you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by the
# Free Software Foundation, version 3.


from bs4 import BeautifulSoup

from args import spec_from_commandline_args
from glowfic import chunkDOMs
from spec import Spec


def parse(content: bytes) -> BeautifulSoup:
    return BeautifulSoup(content, 'html.parser')


def process(spec: Spec) -> None:
    spec.texout.write(b'\\documentclass{article}\n')
    if spec.geometry is not None:
        spec.texout.write(b'\\usepackage[' +
                          spec.geometry.encode('UTF-8') +
                          b']{geometry}\n')
    spec.texout.write(b'\\begin{document}\n')
    html = parse(spec.htmlfilter(spec.fetcher.fetch(spec.url)))
    for r in chunkDOMs(html):
        spec.domfilter(r)
        spec.texout.write(spec.texifier.texify(r))
    spec.texout.write(b'\\end{document}\n')


def main() -> None:
    with spec_from_commandline_args() as spec:
        process(spec)


if __name__ == '__main__':
    main()