Strip all  

[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.


import itertools

from typing import Iterable

from bs4 import BeautifulSoup
from bs4.element import Tag

from args import spec_from_commandline_args
from spec import Spec


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


def clean(html: BeautifulSoup) -> BeautifulSoup:
    for eb in html.find_all("div", class_="post-edit-box"):
        eb.decompose()
    for footer in html.find_all("div", class_="post-footer"):
        footer.decompose()
    return html


def replies(html: BeautifulSoup) -> Iterable[Tag]:
    def text() -> Tag:
        body = html.body
        assert body
        text = body.find_next("div", class_="post-post")
        assert isinstance(text, Tag)
        return text

    def the_replies() -> Iterable[Tag]:
        rs = html.find_all("div", class_="post-reply")
        assert all(isinstance(r, Tag) for r in rs)
        return rs

    return itertools.chain([text()], the_replies())


def process(spec: Spec) -> None:
    spec.texout.write(b'\\documentclass{article}\n\\begin{document}\n')
    html = clean(parse(spec.htmlfilter(spec.fetcher.fetch(spec.url))))
    for r in replies(html):
        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()