From 232f83890209f0e84f59b906640065ab8759126d Mon Sep 17 00:00:00 2001 From: amhsirak Date: Sat, 23 Nov 2024 07:06:15 +0530 Subject: [PATCH] feat: handle relative src 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 e5e1c697..467d077b 100644 --- a/maxun-core/src/browserSide/scraper.js +++ b/maxun-core/src/browserSide/scraper.js @@ -282,7 +282,9 @@ function scrapableHeuristics(maxCountPerPage = 50, minArea = 20000, scrolls = 3, } else if (attribute === 'innerHTML') { record[label] = fieldElement.innerHTML.trim(); } else if (attribute === 'src') { - record[label] = fieldElement.src; + // Handle relative 'src' URLs + const src = fieldElement.getAttribute('src'); + record[label] = src ? new URL(src, baseUrl).href : null; } else if (attribute === 'href') { // Handle relative 'href' URLs const href = fieldElement.getAttribute('href');