from argparse import ArgumentParser
import itertools
import os.path
-import subprocess
from typing import IO, Iterable
from bs4 import BeautifulSoup
from bs4.element import Tag
-import requests
-import requests_cache
from xdg_base_dirs import xdg_cache_home
+from fetch import CachingFetcher, Fetcher
+from texify import PandocTexifier, Texifier
+
def command_line_parser() -> ArgumentParser:
parser = ArgumentParser(prog='paperdoorknob', description='Print glowfic')
return parser
-def fetch(url: str, session: requests.Session, timeout: int) -> BeautifulSoup:
- with session.get(url, timeout=timeout) as r:
- r.raise_for_status()
- return BeautifulSoup(r.text, 'html.parser')
+def parse(content: bytes) -> BeautifulSoup:
+ return BeautifulSoup(content, 'html.parser')
def clean(html: BeautifulSoup) -> BeautifulSoup:
return itertools.chain([text()], the_replies())
-def html_to_tex(pandoc: str, tag: Tag) -> bytes:
- return subprocess.run([pandoc, '--from=html', '--to=latex'],
- input=tag.encode(),
- stdout=subprocess.PIPE,
- check=True).stdout
-
-
def process(
url: str,
- session: requests.Session,
- timeout: int,
- texout: IO[bytes],
- pandoc: str,
-) -> None:
+ fetcher: Fetcher,
+ texifier: Texifier,
+ texout: IO[bytes]) -> None:
texout.write(b'\\documentclass{article}\n\\begin{document}\n')
- html = clean(fetch(url, session, timeout))
+ html = clean(parse(fetcher.fetch(url)))
for r in replies(html):
- texout.write(html_to_tex(pandoc, r))
+ texout.write(texifier.texify(r))
texout.write(b'\\end{document}\n')
def main() -> None:
args = command_line_parser().parse_args()
- with requests_cache.CachedSession(args.cache_path, cache_control=True) as session:
+ texifier = PandocTexifier(args.pandoc or 'pandoc')
+ with CachingFetcher(args.cache_path, args.timeout) as fetcher:
with open(args.out + '.tex', 'wb') as texout:
- process(
- args.url,
- session,
- args.timeout,
- texout,
- args.pandoc or 'pandoc')
+ process(args.url, fetcher, texifier, texout)
if __name__ == '__main__':