From 9378dac0fa84db3cb23f1222c691cd89543a60ba Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Joakim=20Hells=C3=A9n?= <tlovinator@gmail.com>
Date: Mon, 8 Dec 2025 17:47:45 +0100
Subject: [PATCH] Unescape HTML entities in summary and content before markdown
 conversion

---
 discord_rss_bot/custom_message.py | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/discord_rss_bot/custom_message.py b/discord_rss_bot/custom_message.py
index 99a7e11..f6ff0f5 100644
--- a/discord_rss_bot/custom_message.py
+++ b/discord_rss_bot/custom_message.py
@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import html
 import json
 import logging
 from dataclasses import dataclass
@@ -68,6 +69,10 @@ def replace_tags_in_text_message(entry: Entry) -> str:
 
     first_image: str = get_first_image(summary, content)
 
+    # Unescape HTML entities (e.g., &lt;h1&gt; becomes <h1>) before converting to markdown
+    summary = html.unescape(summary)
+    content = html.unescape(content)
+
     summary = markdownify(
         html=summary,
         strip=["img", "table", "td", "tr", "tbody", "thead"],
@@ -199,6 +204,10 @@ def replace_tags_in_embed(feed: Feed, entry: Entry) -> CustomEmbed:
 
     first_image: str = get_first_image(summary, content)
 
+    # Unescape HTML entities (e.g., &lt;h1&gt; becomes <h1>) before converting to markdown
+    summary = html.unescape(summary)
+    content = html.unescape(content)
+
     summary = markdownify(
         html=summary,
         strip=["img", "table", "td", "tr", "tbody", "thead"],