# Free Software Foundation, version 3.
-import itertools
-
-from typing import Iterable
-
from bs4 import BeautifulSoup
-from bs4.element import Tag
from args import spec_from_commandline_args
+from glowfic import chunkDOMs, makeChunk
from spec import Spec
return BeautifulSoup(content, 'html.parser')
-def replies(html: BeautifulSoup) -> Iterable[Tag]:
- def text() -> Tag:
- body = html.body
- assert body
- text = body.find_next("div", class_="post-post")
- assert isinstance(text, Tag)
- return text
-
- def the_replies() -> Iterable[Tag]:
- rs = html.find_all("div", class_="post-reply")
- assert all(isinstance(r, Tag) for r in rs)
- return rs
-
- return itertools.chain([text()], the_replies())
-
-
def process(spec: Spec) -> None:
- spec.texout.write(b'\\documentclass{article}\n\\begin{document}\n')
+ spec.texout.write(b'''\\documentclass{article}
+\\usepackage{graphicx}
+\\usepackage{wrapfig}
+''')
+ 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 replies(html):
+ first = True
+ for r in chunkDOMs(html):
+ if first:
+ first = False
+ else:
+ # h/t https://tex.stackexchange.com/questions/309856
+ spec.texout.write(b'''
+\\vspace{-.5\\ht\\strutbox}\\noindent\\hrulefill
+
+''')
spec.domfilter(r)
- spec.texout.write(spec.texifier.texify(r))
+ chunk = makeChunk(r, spec.images)
+ spec.texout.write(spec.layout.renderChunk(chunk))
spec.texout.write(b'\\end{document}\n')