Rename html → dom

[paperdoorknob] / paperdoorknob.py

diff --git a/paperdoorknob.py b/paperdoorknob.py
index 86b8766e659601b6d05a1c2dcd28e6c7f2fbb868..ade0b885d42addb973f415599798bd2e153ac961 100644 (file)
--- a/paperdoorknob.py
+++ b/paperdoorknob.py
@@ -7,9 +7,10 @@
 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, flatURL, makeChunk, renderChunk
+from glowfic import flatURL, makeChunk, renderChunk, Thread
 from spec import Spec
 
 
@@ -21,6 +22,13 @@ 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}
@@ -49,11 +57,13 @@ def process(spec: Spec) -> None:
     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(chunkDOMs(dom))
-    for i, r in enumerate(chunkDOMs(dom)):
+    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 chunk {i} of {num_chunks} ({percent:.1f}%)\r')
+        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)))