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 class Post:
  22     def __init__(self, html: BeautifulSoup) -> None:
  23         self._html = html
  24         for eb in self._html.find_all("div", class_="post-edit-box"):
  25             eb.decompose()
  26         for footer in self._html.find_all("div", class_="post-footer"):
  27             footer.decompose()
  28
  29     def text(self) -> Tag:
  30         body = self._html.body
  31         assert body
  32         text = body.find_next("div", class_="post-post")
  33         assert isinstance(text, Tag)
  34         return text
  35
  36     def replies(self) -> Iterable[Tag]:
  37         replies = self._html.find_all("div", class_="post-reply")
  38         assert all(isinstance(r, Tag) for r in replies)
  39         return replies
  40
  41     def entries(self) -> Iterable[Tag]:
  42         return itertools.chain([self.text()], self.replies())
  43
  44
  45 def command_line_parser() -> ArgumentParser:
  46     parser = ArgumentParser(prog='paperdoorknob', description='Print glowfic')
  47     parser.add_argument(
  48         '--cache_path',
  49         metavar='PATH',
  50         help='Where to keep the http cache (instead of %(default)s)',
  51         default=os.path.join(xdg_cache_home(), "paperdoorknob"))
  52     parser.add_argument(
  53         '--timeout',
  54         help='How long to wait for HTTP requests, in seconds',
  55         default=30)
  56     parser.add_argument('url', help='URL to retrieve')
  57     return parser
  58
  59
  60 def fetch(url: str, session: requests.Session, timeout: int) -> BeautifulSoup:
  61     with session.get(url, timeout=timeout) as r:
  62         r.raise_for_status()
  63         return BeautifulSoup(r.text, 'html.parser')
  64
  65
  66 def main() -> None:
  67     args = command_line_parser().parse_args()
  68     with requests_cache.CachedSession(args.cache_path, cache_control=True) as session:
  69         html = fetch(args.url, session, args.timeout)
  70         Post(html)
  71
  72
  73 if __name__ == '__main__':
  74     main()