X-Git-Url: http://git.scottworley.com/paperdoorknob/blobdiff_plain/6409066b6abbe205fa64f844a01516f3f3de2553..ae7b6283ed5ead577d1a8f263d37d01717e2bb33:/paperdoorknob.py?ds=inline diff --git a/paperdoorknob.py b/paperdoorknob.py index b88c02d..5e5747c 100644 --- a/paperdoorknob.py +++ b/paperdoorknob.py @@ -5,53 +5,39 @@ # Free Software Foundation, version 3. -from argparse import ArgumentParser -import os.path from bs4 import BeautifulSoup -from bs4.element import Tag -import requests -import requests_cache -from xdg_base_dirs import xdg_cache_home +from args import spec_from_commandline_args +from glowfic import chunkDOMs, makeChunk +from spec import Spec -class Post: - def __init__(self, html: BeautifulSoup) -> None: - self._html = html - def text(self) -> Tag: - body = self._html.body - assert body - text = body.find_next("div", class_="post-post") - assert isinstance(text, Tag) - return text +def parse(content: bytes) -> BeautifulSoup: + return BeautifulSoup(content, 'html.parser') -def command_line_parser() -> ArgumentParser: - parser = ArgumentParser(prog='paperdoorknob', description='Print glowfic') - parser.add_argument( - '--cache_path', - metavar='PATH', - help='Where to keep the http cache (instead of %(default)s)', - default=os.path.join(xdg_cache_home(), "paperdoorknob")) - 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 - - -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 process(spec: Spec) -> None: + spec.texout.write(b'''\\documentclass{article} +\\usepackage{graphicx} +\\usepackage{varwidth} +\\usepackage{wrapstuff} +''') + if spec.geometry is not None: + spec.texout.write(b'\\usepackage[' + + spec.geometry.encode('UTF-8') + + b']{geometry}\n') + spec.texout.write(b'\\begin{document}\n') + html = parse(spec.htmlfilter(spec.fetcher.fetch(spec.url))) + for r in chunkDOMs(html): + spec.domfilter(r) + chunk = makeChunk(r, spec.images) + spec.texout.write(spec.layout.renderChunk(chunk)) + spec.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: - html = fetch(args.url, session, args.timeout) - Post(html) + with spec_from_commandline_args() as spec: + process(spec) if __name__ == '__main__':