From 8e3c2b28550aafcdf4627724940a3b951672c496 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gerg=C5=91=20M=C3=B3ricz?= <mo.geryy@gmail.com>
Date: Thu, 22 Aug 2024 23:30:19 +0200
Subject: [PATCH] fix(crawler): verify URL

---
 apps/api/src/scraper/WebScraper/crawler.ts | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/apps/api/src/scraper/WebScraper/crawler.ts b/apps/api/src/scraper/WebScraper/crawler.ts
index 67f1c22..92b9ae4 100644
--- a/apps/api/src/scraper/WebScraper/crawler.ts
+++ b/apps/api/src/scraper/WebScraper/crawler.ts
@@ -108,7 +108,12 @@ export class WebCrawler {
 
         // Normalize the initial URL and the link to account for www and non-www versions
         const normalizedInitialUrl = new URL(this.initialUrl);
-        const normalizedLink = new URL(link);
+        let normalizedLink;
+        try {
+          normalizedLink = new URL(link);
+        } catch (_) {
+          return false;
+        }
         const initialHostname = normalizedInitialUrl.hostname.replace(/^www\./, '');
         const linkHostname = normalizedLink.hostname.replace(/^www\./, '');