# 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
-import requests
-import requests_cache
-from xdg_base_dirs import xdg_cache_home
+from bs4 import BeautifulSoup
+from bs4.element import Tag
+from args import spec_from_commandline_args
+from glowfic import flatURL, makeChunk, renderChunk, Thread
+from spec import Spec
-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 parse(content: bytes) -> BeautifulSoup:
+ return BeautifulSoup(content, 'html.parser')
-def fetch(url: str, session: requests.Session, timeout: int) -> None:
- with session.get(url, timeout=timeout) as r:
- r.raise_for_status()
+
+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(br'''\documentclass{article}
+\usepackage{booktabs}
+\usepackage{graphicx}
+\usepackage{longtable}
+\usepackage{soul}
+\usepackage{varwidth}
+\usepackage{wrapstuff}
+''')
+ if spec.geometry is not None:
+ spec.texout.write(br'\usepackage[' +
+ spec.geometry.encode('UTF-8') +
+ b']{geometry}\n')
+ 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.texfilter(renderChunk(spec.texifier, 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__':