next_thread should be an absolute URL

[paperdoorknob] / glowfic.py

diff --git a/glowfic.py b/glowfic.py
index 92ae4ab81a195fceeda74869fad340d9718c4095..9d863c887e2992cd8bbdbc4d1a8a1ddffce65155 100644 (file)
--- a/glowfic.py
+++ b/glowfic.py
@@ -7,7 +7,7 @@
 
 from dataclasses import dataclass
 import itertools
-from urllib.parse import parse_qsl, urlencode, urlparse, urlunparse
+from urllib.parse import parse_qsl, urlencode, urljoin, urlparse, urlunparse
 
 from typing import Iterable
 
@@ -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 +57,22 @@ class Chunk:
 
 class Thread:
 
-    def __init__(self, dom: BeautifulSoup) -> None:
-        self._dom = dom
+    def __init__(self, spec: Spec) -> None:
+        def find_next_thread(dom: BeautifulSoup) -> str | None:
+            for c in dom.findChildren('div', class_='post-navheader'):
+                for a in c.findChildren('a'):
+                    if 'Next Post' in a.text and 'href' in a.attrs and isinstance(
+                            a.attrs['href'], str):
+                        return urljoin(spec.url, a.attrs['href'])
+            return None
+
+        spec.log('Fetching HTML...\r')
+        html = spec.fetcher.fetch(spec.url)
+        flat_html = spec.fetcher.fetch(flatURL(spec.url))
+        spec.log('Parsing HTML...\r')
+        self._next_thread = find_next_thread(
+            BeautifulSoup(spec.htmlfilter(html), 'html.parser'))
+        self._dom = BeautifulSoup(spec.htmlfilter(flat_html), 'html.parser')
 
     def title(self) -> str | None:
         span = self._dom.findChild("span", id="post-title")
@@ -65,6 +80,9 @@ class Thread:
             return None
         return span.text.strip()
 
+    def next_thread(self) -> str | None:
+        return self._next_thread
+
     def chunkDOMs(self) -> Iterable[Tag]:
         def text() -> Tag:
             body = self._dom.body