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 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         '--timeout',
  30         help='How long to wait for HTTP requests, in seconds',
  31         default=30)
  32     parser.add_argument('url', help='URL to retrieve')
  33     return parser
  34
  35
  36 def fetch(url: str, session: requests.Session, timeout: int) -> BeautifulSoup:
  37     with session.get(url, timeout=timeout) as r:
  38         r.raise_for_status()
  39         return BeautifulSoup(r.text, 'html.parser')
  40
  41
  42 def clean(html: BeautifulSoup) -> BeautifulSoup:
  43     for eb in html.find_all("div", class_="post-edit-box"):
  44         eb.decompose()
  45     for footer in html.find_all("div", class_="post-footer"):
  46         footer.decompose()
  47     return html
  48
  49
  50 def replies(html: BeautifulSoup) -> Iterable[Tag]:
  51     def text() -> Tag:
  52         body = html.body
  53         assert body
  54         text = body.find_next("div", class_="post-post")
  55         assert isinstance(text, Tag)
  56         return text
  57
  58     def the_replies() -> Iterable[Tag]:
  59         rs = html.find_all("div", class_="post-reply")
  60         assert all(isinstance(r, Tag) for r in rs)
  61         return rs
  62
  63     return itertools.chain([text()], the_replies())
  64
  65
  66 def process(
  67         url: str,
  68         session: requests.Session,
  69         timeout: int) -> Iterable[Tag]:
  70     html = clean(fetch(url, session, timeout))
  71     return replies(html)
  72
  73
  74 def main() -> None:
  75     args = command_line_parser().parse_args()
  76     with requests_cache.CachedSession(args.cache_path, cache_control=True) as session:
  77         process(args.url, session, args.timeout)
  78
  79
  80 if __name__ == '__main__':
  81     main()