From 94aa8bcf42d0266febb54516c12a98a562be47b3 Mon Sep 17 00:00:00 2001
From: amhsirak <karishmashuklaa@gmail.com>
Date: Sat, 23 Nov 2024 07:05:55 +0530
Subject: [PATCH] feat: handle relative href urls in scrape list

---
 maxun-core/src/browserSide/scraper.js | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/maxun-core/src/browserSide/scraper.js b/maxun-core/src/browserSide/scraper.js
index 7ee64dc1..e5e1c697 100644
--- a/maxun-core/src/browserSide/scraper.js
+++ b/maxun-core/src/browserSide/scraper.js
@@ -284,7 +284,9 @@ function scrapableHeuristics(maxCountPerPage = 50, minArea = 20000, scrolls = 3,
             } else if (attribute === 'src') {
               record[label] = fieldElement.src;
             } else if (attribute === 'href') {
-              record[label] = fieldElement.href;
+              // Handle relative 'href' URLs
+              const href = fieldElement.getAttribute('href');
+              record[label] = href ? new URL(href, baseUrl).href : null;
             } else {
               record[label] = fieldElement.getAttribute(attribute);
             }