]>
Commit | Line | Data |
---|---|---|
1 | # paperdoorknob: Print glowfic | |
2 | # | |
3 | # This program is free software: you can redistribute it and/or modify it | |
4 | # under the terms of the GNU General Public License as published by the | |
5 | # Free Software Foundation, version 3. | |
6 | ||
7 | ||
8 | import itertools | |
9 | ||
10 | from typing import Iterable | |
11 | ||
12 | from bs4 import BeautifulSoup | |
13 | from bs4.element import Tag | |
14 | ||
15 | from args import spec_from_commandline_args | |
16 | from spec import Spec | |
17 | ||
18 | ||
19 | def parse(content: bytes) -> BeautifulSoup: | |
20 | return BeautifulSoup(content, 'html.parser') | |
21 | ||
22 | ||
23 | def replies(html: BeautifulSoup) -> Iterable[Tag]: | |
24 | def text() -> Tag: | |
25 | body = html.body | |
26 | assert body | |
27 | text = body.find_next("div", class_="post-post") | |
28 | assert isinstance(text, Tag) | |
29 | return text | |
30 | ||
31 | def the_replies() -> Iterable[Tag]: | |
32 | rs = html.find_all("div", class_="post-reply") | |
33 | assert all(isinstance(r, Tag) for r in rs) | |
34 | return rs | |
35 | ||
36 | return itertools.chain([text()], the_replies()) | |
37 | ||
38 | ||
39 | def process(spec: Spec) -> None: | |
40 | spec.texout.write(b'\\documentclass{article}\n\\begin{document}\n') | |
41 | html = parse(spec.htmlfilter(spec.fetcher.fetch(spec.url))) | |
42 | for r in replies(html): | |
43 | spec.domfilter(r) | |
44 | spec.texout.write(spec.texifier.texify(r)) | |
45 | spec.texout.write(b'\\end{document}\n') | |
46 | ||
47 | ||
48 | def main() -> None: | |
49 | with spec_from_commandline_args() as spec: | |
50 | process(spec) | |
51 | ||
52 | ||
53 | if __name__ == '__main__': | |
54 | main() |