Always have Thread.__init__ fetch the HTML

[paperdoorknob] / glowfic.py

diff --git a/glowfic.py b/glowfic.py
index 372b3aa05f574a20038cf4cd6661d50ebae4bcd3..5ffaac31921e360961967832ad090074e5cd2aaa 100644 (file)
--- 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
 
 
@@ -56,19 +57,28 @@ class Chunk:
 
 class Thread:
 
-    def __init__(self, html: BeautifulSoup) -> None:
-        self._html = html
+    def __init__(self, spec: Spec) -> None:
+        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')
+
+    def title(self) -> str | None:
+        span = self._dom.findChild("span", id="post-title")
+        if not isinstance(span, Tag):
+            return None
+        return span.text.strip()
 
     def chunkDOMs(self) -> Iterable[Tag]:
         def text() -> Tag:
-            body = self._html.body
+            body = self._dom.body
             assert body
             text = body.find_next("div", class_="post-post")
             assert isinstance(text, Tag)
             return text
 
         def the_replies() -> Iterable[Tag]:
-            rs = self._html.find_all("div", class_="post-reply")
+            rs = self._dom.find_all("div", class_="post-reply")
             assert all(isinstance(r, Tag) for r in rs)
             return rs