From: Scott Worley <scottworley@scottworley.com>
Date: Fri, 12 Jan 2024 03:30:21 +0000 (-0800)
Subject: Optionally have Thread.__init__ fetch the HTML
X-Git-Url: http://git.scottworley.com/paperdoorknob/commitdiff_plain/70adfbff16123a62d6b25f8ead23789d831d1d70?ds=inline;hp=21e82200b2887fc4f4f9eff4023f4a73547cacb5

Optionally have Thread.__init__ fetch the HTML
---

diff --git a/glowfic.py b/glowfic.py
index 92ae4ab..8029b5d 100644
--- a/glowfic.py
+++ b/glowfic.py
@@ -15,6 +15,7 @@ from bs4 import BeautifulSoup
 from bs4.element import Tag
 
 from images import ImageStore
+from spec import Spec
 from texify import Texifier
 
 
@@ -56,8 +57,15 @@ class Chunk:
 
 class Thread:
 
-    def __init__(self, dom: BeautifulSoup) -> None:
-        self._dom = dom
+    def __init__(self, thing: BeautifulSoup | Spec) -> None:
+        if isinstance(thing, Spec):
+            spec = thing
+            spec.log('Fetching HTML...\r')
+            html = spec.fetcher.fetch(flatURL(spec.url))
+            spec.log('Parsing HTML...\r')
+            self._dom = BeautifulSoup(spec.htmlfilter(html), 'html.parser')
+        else:
+            self._dom = thing
 
     def title(self) -> str | None:
         span = self._dom.findChild("span", id="post-title")
diff --git a/paperdoorknob.py b/paperdoorknob.py
index cf50057..d545f61 100644
--- a/paperdoorknob.py
+++ b/paperdoorknob.py
@@ -6,17 +6,11 @@
 
 from typing import Any, Iterable
 
-from bs4 import BeautifulSoup
-
 from args import spec_from_commandline_args
-from glowfic import flatURL, makeChunk, renderChunk, Thread
+from glowfic import makeChunk, renderChunk, 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)
 
@@ -44,12 +38,7 @@ 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)
+    thread = Thread(spec)
     spec.log('Counting chunks...\r')
     num_chunks = ilen(thread.chunkDOMs())
     title = thread.title() or "chunk"