git.scottworley.com Git - paperdoorknob/blob - paperdoorknob.py

   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 from argparse import ArgumentParser
   9 import itertools
  10 import os.path
  11
  12 from typing import IO, Iterable
  13
  14 from bs4 import BeautifulSoup
  15 from bs4.element import Tag
  16 import requests
  17 import requests_cache
  18 from xdg_base_dirs import xdg_cache_home
  19
  20
  21 def command_line_parser() -> ArgumentParser:
  22     parser = ArgumentParser(prog='paperdoorknob', description='Print glowfic')
  23     parser.add_argument(
  24         '--cache_path',
  25         metavar='PATH',
  26         help='Where to keep the http cache (instead of %(default)s)',
  27         default=os.path.join(xdg_cache_home(), "paperdoorknob"))
  28     parser.add_argument(
  29         '--out',
  30         help='The filename stem at which to write output ' +
  31              '(eg: "%(default)s" produces %(default)s.text, %(default)s.pdf, etc.)',
  32         default='book')
  33     parser.add_argument(
  34         '--timeout',
  35         help='How long to wait for HTTP requests, in seconds',
  36         default=30)
  37     parser.add_argument('url', help='URL to retrieve')
  38     return parser
  39
  40
  41 def fetch(url: str, session: requests.Session, timeout: int) -> BeautifulSoup:
  42     with session.get(url, timeout=timeout) as r:
  43         r.raise_for_status()
  44         return BeautifulSoup(r.text, 'html.parser')
  45
  46
  47 def clean(html: BeautifulSoup) -> BeautifulSoup:
  48     for eb in html.find_all("div", class_="post-edit-box"):
  49         eb.decompose()
  50     for footer in html.find_all("div", class_="post-footer"):
  51         footer.decompose()
  52     return html
  53
  54
  55 def replies(html: BeautifulSoup) -> Iterable[Tag]:
  56     def text() -> Tag:
  57         body = html.body
  58         assert body
  59         text = body.find_next("div", class_="post-post")
  60         assert isinstance(text, Tag)
  61         return text
  62
  63     def the_replies() -> Iterable[Tag]:
  64         rs = html.find_all("div", class_="post-reply")
  65         assert all(isinstance(r, Tag) for r in rs)
  66         return rs
  67
  68     return itertools.chain([text()], the_replies())
  69
  70
  71 def process(
  72         url: str,
  73         session: requests.Session,
  74         timeout: int,
  75         texout: IO[str],
  76 ) -> None:
  77     html = clean(fetch(url, session, timeout))
  78     replies(html)
  79     print("soon", file=texout)
  80
  81
  82 def main() -> None:
  83     args = command_line_parser().parse_args()
  84     with requests_cache.CachedSession(args.cache_path, cache_control=True) as session:
  85         with open(args.out + '.tex', 'w', encoding='UTF-8') as texout:
  86             process(args.url, session, args.timeout, texout)
  87
  88
  89 if __name__ == '__main__':
  90     main()