# Free Software Foundation, version 3.
-from argparse import ArgumentParser
-import requests
+import itertools
+from typing import Iterable
-def command_line_parser() -> ArgumentParser:
- parser = ArgumentParser(prog='paperdoorknob', description='Print glowfic')
- parser.add_argument(
- '--timeout',
- help='How long to wait for HTTP requests, in seconds',
- default=30)
- parser.add_argument('url', help='URL to retrieve')
- return parser
+from bs4 import BeautifulSoup
+from bs4.element import Tag
+from args import spec_from_commandline_args
+from spec import Spec
-def fetch(url: str, session: requests.Session, timeout: int) -> None:
- with session.get(url, timeout=timeout) as r:
- r.raise_for_status()
+
+def parse(content: bytes) -> BeautifulSoup:
+ return BeautifulSoup(content, 'html.parser')
+
+
+def replies(html: BeautifulSoup) -> Iterable[Tag]:
+ def text() -> Tag:
+ body = html.body
+ assert body
+ text = body.find_next("div", class_="post-post")
+ assert isinstance(text, Tag)
+ return text
+
+ def the_replies() -> Iterable[Tag]:
+ rs = html.find_all("div", class_="post-reply")
+ assert all(isinstance(r, Tag) for r in rs)
+ return rs
+
+ return itertools.chain([text()], the_replies())
+
+
+def process(spec: Spec) -> None:
+ spec.texout.write(b'\\documentclass{article}\n\\begin{document}\n')
+ html = parse(spec.htmlfilter(spec.fetcher.fetch(spec.url)))
+ for r in replies(html):
+ spec.domfilter(r)
+ spec.texout.write(spec.texifier.texify(r))
+ spec.texout.write(b'\\end{document}\n')
def main() -> None:
- args = command_line_parser().parse_args()
- with requests.session() as session:
- fetch(args.url, session, args.timeout)
+ with spec_from_commandline_args() as spec:
+ process(spec)
if __name__ == '__main__':