]>
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 | from typing import Any, Iterable | |
8 | ||
9 | from bs4 import BeautifulSoup | |
10 | from bs4.element import Tag | |
11 | ||
12 | from args import spec_from_commandline_args | |
13 | from glowfic import chunkDOMs, flatURL, makeChunk, renderChunk | |
14 | from spec import Spec | |
15 | ||
16 | ||
17 | def parse(content: bytes) -> BeautifulSoup: | |
18 | return BeautifulSoup(content, 'html.parser') | |
19 | ||
20 | ||
21 | def ilen(it: Iterable[Any]) -> int: | |
22 | return sum(1 for _ in it) | |
23 | ||
24 | ||
25 | def get_title(dom: BeautifulSoup) -> str | None: | |
26 | span = dom.findChild("span", id="post-title") | |
27 | if not isinstance(span, Tag): | |
28 | return None | |
29 | return span.text | |
30 | ||
31 | ||
32 | def process(spec: Spec) -> None: | |
33 | spec.texout.write(br'''\documentclass{article} | |
34 | \usepackage{booktabs} | |
35 | \usepackage{graphicx} | |
36 | \usepackage{longtable} | |
37 | \usepackage{soul} | |
38 | \usepackage{varwidth} | |
39 | \usepackage{wrapstuff} | |
40 | ''') | |
41 | if spec.geometry is not None: | |
42 | spec.texout.write(br'\usepackage[' + | |
43 | spec.geometry.encode('UTF-8') + | |
44 | b']{geometry}\n') | |
45 | spec.texout.write(br'''\begin{document} | |
46 | \newcommand{\href}[2]{#2\footnote{\detokenize{#1}}} | |
47 | \def\glowiconsize{%fmm} | |
48 | \newcommand{\glowicon}[1]{\includegraphics[ | |
49 | width=\glowiconsize,height=\glowiconsize,keepaspectratio | |
50 | ]{#1}} | |
51 | \newcommand{\ifnotempty}[2]{\expandafter\ifx\expandafter\relax | |
52 | \detokenize{#1}\relax\else #2\fi} | |
53 | %s | |
54 | ''' % (spec.icon_size, spec.layout)) | |
55 | url = flatURL(spec.url) | |
56 | spec.log('Fetching HTML...\r') | |
57 | html = spec.fetcher.fetch(url) | |
58 | spec.log('Parsing HTML...\r') | |
59 | dom = parse(spec.htmlfilter(html)) | |
60 | spec.log('Counting chunks...\r') | |
61 | num_chunks = ilen(chunkDOMs(dom)) | |
62 | title = get_title(dom) or "chunk" | |
63 | for i, r in enumerate(chunkDOMs(dom)): | |
64 | percent = 100.0 * i / num_chunks | |
65 | spec.log(f'Processing {title} {i} of {num_chunks} ({percent:.1f}%)\r') | |
66 | spec.domfilter(r) | |
67 | chunk = makeChunk(r, spec.images) | |
68 | spec.texout.write(spec.texfilter(renderChunk(spec.texifier, chunk))) | |
69 | spec.log('') | |
70 | spec.texout.write(b'\\end{document}\n') | |
71 | ||
72 | ||
73 | def main() -> None: | |
74 | with spec_from_commandline_args() as spec: | |
75 | process(spec) | |
76 | ||
77 | ||
78 | if __name__ == '__main__': | |
79 | main() |