]> git.scottworley.com Git - paperdoorknob/commitdiff
Optionally have Thread.__init__ fetch the HTML
authorScott Worley <scottworley@scottworley.com>
Fri, 12 Jan 2024 03:30:21 +0000 (19:30 -0800)
committerScott Worley <scottworley@scottworley.com>
Fri, 12 Jan 2024 11:41:35 +0000 (03:41 -0800)
glowfic.py
paperdoorknob.py

index 92ae4ab81a195fceeda74869fad340d9718c4095..8029b5d704f1bffab897426c34a16a8b44fe30fb 100644 (file)
@@ -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")
index cf500571604c9590920d36090e8484f4ba8ad498..d545f6184514f0386068871a247b6a30fe1aad18 100644 (file)
@@ -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"