X-Git-Url: http://git.scottworley.com/paperdoorknob/blobdiff_plain/136277e30143cd1219c896bb4980027ac3c6dbe1..b254976424d0f56fab14f8897dade345ce46a2d1:/paperdoorknob.py?ds=sidebyside diff --git a/paperdoorknob.py b/paperdoorknob.py index bb8bdd1..6a55675 100644 --- a/paperdoorknob.py +++ b/paperdoorknob.py @@ -4,40 +4,55 @@ # under the terms of the GNU General Public License as published by the # Free Software Foundation, version 3. +from typing import Any, Iterable -from argparse import ArgumentParser -import os.path from bs4 import BeautifulSoup -import requests -import requests_cache -from xdg_base_dirs import xdg_cache_home - -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') +from args import spec_from_commandline_args +from glowfic import chunkDOMs, flatURL, makeChunk +from spec import Spec + + +def parse(content: bytes) -> BeautifulSoup: + return BeautifulSoup(content, 'html.parser') + + +def ilen(it: Iterable[Any]) -> int: + return sum(1 for _ in it) + + +def process(spec: Spec) -> None: + spec.texout.write(b'''\\documentclass{article} +\\usepackage{booktabs} +\\usepackage{graphicx} +\\usepackage{longtable} +\\usepackage{soul} +\\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} +\\newcommand{\\href}[2]{#2\\footnote{#1}} +''') + url = flatURL(spec.url) + html = parse(spec.htmlfilter(spec.fetcher.fetch(url))) + num_chunks = ilen(chunkDOMs(html)) + for i, r in enumerate(chunkDOMs(html)): + percent = 100.0 * i / num_chunks + spec.log(f'Processing chunk {i} of {num_chunks} ({percent:.1f}%)\r') + spec.domfilter(r) + chunk = makeChunk(r, spec.images) + spec.texout.write(spec.texfilter(spec.layout.renderChunk(chunk))) + spec.log('') + 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: - fetch(args.url, session, args.timeout) + with spec_from_commandline_args() as spec: + process(spec) if __name__ == '__main__':