From 2d87c057e67e8b73afe56b467f3eb4a2dfe733c4 Mon Sep 17 00:00:00 2001
From: Danny Spina <danny.spina@hotmail.it>
Date: Tue, 20 Jun 2023 12:36:47 +0200
Subject: [PATCH] Remove images before parsing

---
 index.ts | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/index.ts b/index.ts
index 5fd07e1..07d2428 100644
--- a/index.ts
+++ b/index.ts
@@ -98,11 +98,13 @@ app.get("/blazed", async (req, res) => {
   try {
     const response = await got(pageToBlaze);
     const { document } = parseHTML(response.body);
-
     if (!isProbablyReaderable(document)) {
       return res.sendFile(path.join(__dirname, "/dist/not_blazed.html"));
     }
 
+    //TODO: find if there are more performant ways to remove images or evaluate if is the case to remove images
+    document.querySelectorAll("img").forEach((img) => img.remove());
+
     const reader = new Readability(document);
     const article = reader.parse();