# paperdoorknob: Print glowfic # # This program is free software: you can redistribute it and/or modify it # under the terms of the GNU General Public License as published by the # Free Software Foundation, version 3. from typing import Any, Iterable from bs4 import BeautifulSoup 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{\\detokenize{#1}}} ''') url = flatURL(spec.url) spec.log('Fetching HTML...\r') html = spec.fetcher.fetch(url) spec.log('Parsing HTML...\r') dom = parse(spec.htmlfilter(html)) spec.log('Counting chunks...\r') num_chunks = ilen(chunkDOMs(dom)) for i, r in enumerate(chunkDOMs(dom)): 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: with spec_from_commandline_args() as spec: process(spec) if __name__ == '__main__': main()