From 1e72b1830ab0383e4997b655d5c04308071e40f7 Mon Sep 17 00:00:00 2001 From: edoardottt Date: Sun, 11 Jan 2026 11:43:30 +0100 Subject: [PATCH] fix sitemap URLs discovery --- pkg/crawler/colly.go | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/pkg/crawler/colly.go b/pkg/crawler/colly.go index fd7c722..0c42578 100644 --- a/pkg/crawler/colly.go +++ b/pkg/crawler/colly.go @@ -409,7 +409,7 @@ func registerHTMLEvents(c *colly.Collector, event *Event) { // XML event triggering an action. func registerXMLEvents(c *colly.Collector, event *Event) { // Create a callback on the XPath query searching for the URLs - c.OnXML("//url", func(e *colly.XMLElement) { + c.OnXML("//url/loc", func(e *colly.XMLElement) { visitXMLLink(e.Text, event, e, c) }) @@ -423,11 +423,6 @@ func registerXMLEvents(c *colly.Collector, event *Event) { visitXMLLink(e.Text, event, e, c) }) - // Create a callback on the XPath query searching for the URLs - c.OnXML("//loc", func(e *colly.XMLElement) { - visitXMLLink(e.Text, event, e, c) - }) - // Create a callback on the XPath query searching for the URLs c.OnXML("//fileurl", func(e *colly.XMLElement) { visitXMLLink(e.Text, event, e, c)