Optionally have Thread.__init__ fetch the HTML

[paperdoorknob] / paperdoorknob.py

diff --git a/paperdoorknob.py b/paperdoorknob.py
index ade0b885d42addb973f415599798bd2e153ac961..d545f6184514f0386068871a247b6a30fe1aad18 100644 (file)
--- a/paperdoorknob.py
+++ b/paperdoorknob.py
@@ -6,29 +6,15 @@
 
 from typing import Any, Iterable
 
 
 from typing import Any, Iterable
 

-from bs4 import BeautifulSoup
-from bs4.element import Tag
-

 from args import spec_from_commandline_args
 from args import spec_from_commandline_args

-from glowfic import flatURL, makeChunk, renderChunk, Thread
+from glowfic import makeChunk, renderChunk, Thread

 from spec import Spec
 
 
 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 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}
 def process(spec: Spec) -> None:
     spec.texout.write(br'''\documentclass{article}
 \usepackage{booktabs}


@@ -52,15 +38,10 @@ def process(spec: Spec) -> None:
   \detokenize{#1}\relax\else #2\fi}
 %s
 ''' % (spec.icon_size, spec.layout))
   \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())
     spec.log('Counting chunks...\r')
     num_chunks = ilen(thread.chunkDOMs())

-    title = get_title(dom) or "chunk"
+    title = thread.title() 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')
     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')