From 5aef591c3d304392e09f9e38739c4005d5836c55 Mon Sep 17 00:00:00 2001
From: Will Boyd <will@codersblock.com>
Date: Mon, 24 Feb 2025 16:53:43 -0500
Subject: [PATCH] Remove style contents, excessive line breaks

---
 src/translator.js | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/src/translator.js b/src/translator.js
index 2642106..6c31b81 100644
--- a/src/translator.js
+++ b/src/translator.js
@@ -14,6 +14,8 @@ function initTurndownService() {
 
 	turndownService.use(turndownPluginGfm.tables);
 
+	turndownService.remove(['style']); // <style> contents get dumped as plain text, would rather remove
+
 	// preserve embedded tweets
 	turndownService.addRule('tweet', {
 		filter: node => node.nodeName === 'BLOCKQUOTE' && node.getAttribute('class') === 'twitter-tweet',
@@ -132,5 +134,8 @@ export function getPostContent(content) {
 	// clean up extra spaces in list items
 	content = content.replace(/(-|\d+\.) +/g, '$1 ');
 
+	// collapse excessive newlines (can happen with a lot of <div>)
+	content = content.replace(/(\r?\n){3,}/g, '\n\n');
+
 	return content;
 }