Optionally have Thread.__init__ fetch the HTML

[paperdoorknob] / paperdoorknob.py

diff --git a/paperdoorknob.py b/paperdoorknob.py
index cf500571604c9590920d36090e8484f4ba8ad498..d545f6184514f0386068871a247b6a30fe1aad18 100644 (file)
--- 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"