Move per-thread processing stuff into Thread

[paperdoorknob] / paperdoorknob.py

diff --git a/paperdoorknob.py b/paperdoorknob.py
index ade0b885d42addb973f415599798bd2e153ac961..ed7813b36a8a0977e55744ba1fe9558ef92aeae8 100644 (file)
--- a/paperdoorknob.py
+++ b/paperdoorknob.py
@@ -4,31 +4,11 @@
 # 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 flatURL, makeChunk, renderChunk, Thread
+from glowfic import Thread
 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 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}
@@ -52,22 +32,7 @@ def process(spec: Spec) -> None:
   \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('')
+    Thread(spec).emit()
     spec.texout.write(b'\\end{document}\n')