]>
git.scottworley.com Git - paperdoorknob/blob - paperdoorknob.py
8ab62f10b655f6b9f7c21cc4dd5a1f5379d066be
1 # paperdoorknob: Print glowfic
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.
8 from argparse
import ArgumentParser
13 from typing
import IO
, Iterable
15 from bs4
import BeautifulSoup
16 from bs4
.element
import Tag
19 from xdg_base_dirs
import xdg_cache_home
22 def command_line_parser() -> ArgumentParser
:
23 parser
= ArgumentParser(prog
='paperdoorknob', description
='Print glowfic')
27 help='Where to keep the http cache (instead of %(default)s)',
28 default
=os
.path
.join(xdg_cache_home(), "paperdoorknob"))
31 help='The filename stem at which to write output ' +
32 '(eg: "%(default)s" produces %(default)s.text, %(default)s.pdf, etc.)',
34 parser
.add_argument('--pandoc', help='Location of the pandoc executable')
37 help='How long to wait for HTTP requests, in seconds',
39 parser
.add_argument('url', help='URL to retrieve')
43 def fetch(url
: str, session
: requests
.Session
, timeout
: int) -> BeautifulSoup
:
44 with session
.get(url
, timeout
=timeout
) as r
:
46 return BeautifulSoup(r
.text
, 'html.parser')
49 def clean(html
: BeautifulSoup
) -> BeautifulSoup
:
50 for eb
in html
.find_all("div", class_
="post-edit-box"):
52 for footer
in html
.find_all("div", class_
="post-footer"):
57 def replies(html
: BeautifulSoup
) -> Iterable
[Tag
]:
61 text
= body
.find_next("div", class_
="post-post")
62 assert isinstance(text
, Tag
)
65 def the_replies() -> Iterable
[Tag
]:
66 rs
= html
.find_all("div", class_
="post-reply")
67 assert all(isinstance(r
, Tag
) for r
in rs
)
70 return itertools
.chain([text()], the_replies())
73 def html_to_tex(pandoc
: str, tag
: Tag
) -> bytes:
74 return subprocess
.run([pandoc
, '--from=html', '--to=latex'],
76 stdout
=subprocess
.PIPE
,
82 session
: requests
.Session
,
87 texout
.write(b
'\\documentclass{article}\n\\begin{document}\n')
88 html
= clean(fetch(url
, session
, timeout
))
89 for r
in replies(html
):
90 texout
.write(html_to_tex(pandoc
, r
))
91 texout
.write(b
'\\end{document}\n')
95 args
= command_line_parser().parse_args()
96 with requests_cache
.CachedSession(args
.cache_path
, cache_control
=True) as session
:
97 with open(args
.out
+ '.tex', 'wb') as texout
:
103 args
.pandoc
or 'pandoc')
106 if __name__
== '__main__':