X-Git-Url: http://git.scottworley.com/paperdoorknob/blobdiff_plain/d2a41ff4f433a29173259359dcf477fd59ee3c78..940270992010ea5b4c912eb02f502923c0487a31:/paperdoorknob.py diff --git a/paperdoorknob.py b/paperdoorknob.py index f8b3361..ade0b88 100644 --- a/paperdoorknob.py +++ b/paperdoorknob.py @@ -4,11 +4,13 @@ # 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 bs4.element import Tag from args import spec_from_commandline_args -from glowfic import chunkDOMs, makeChunk +from glowfic import flatURL, makeChunk, renderChunk, Thread from spec import Spec @@ -16,21 +18,56 @@ def parse(content: bytes) -> BeautifulSoup: return BeautifulSoup(content, 'html.parser') +def ilen(it: Iterable[Any]) -> int: + return sum(1 for _ in it) + + +def get_title(dom: BeautifulSoup) -> str | None: + span = dom.findChild("span", id="post-title") + if not isinstance(span, Tag): + return None + return span.text + + def process(spec: Spec) -> None: - spec.texout.write(b'''\\documentclass{article} -\\usepackage{graphicx} -\\usepackage{wrapfig} + spec.texout.write(br'''\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.texout.write(br'\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.texout.write(br'''\begin{document} +\newcommand{\href}[2]{#2\footnote{\detokenize{#1}}} +\def\glowiconsize{%fmm} +\newcommand{\glowicon}[1]{\includegraphics[ + width=\glowiconsize,height=\glowiconsize,keepaspectratio +]{#1}} +\newcommand{\ifnotempty}[2]{\expandafter\ifx\expandafter\relax + \detokenize{#1}\relax\else #2\fi} +%s +''' % (spec.icon_size, spec.layout)) + url = flatURL(spec.url) + spec.log('Fetching HTML...\r') + html = spec.fetcher.fetch(url) + spec.log('Parsing HTML...\r') + dom = parse(spec.htmlfilter(html)) + thread = Thread(dom) + spec.log('Counting chunks...\r') + num_chunks = ilen(thread.chunkDOMs()) + title = get_title(dom) or "chunk" + for i, r in enumerate(thread.chunkDOMs()): + percent = 100.0 * i / num_chunks + spec.log(f'Processing {title} {i} of {num_chunks} ({percent:.1f}%)\r') spec.domfilter(r) chunk = makeChunk(r, spec.images) - spec.texout.write(spec.layout.renderChunk(chunk)) + spec.texout.write(spec.texfilter(renderChunk(spec.texifier, chunk))) + spec.log('') spec.texout.write(b'\\end{document}\n')