From b8518f39add6637d9c93e5acd21f30e5c7007950 Mon Sep 17 00:00:00 2001
From: wackget <136205263+wackget@users.noreply.github.com>
Date: Tue, 8 Oct 2024 17:10:12 +0100
Subject: [PATCH 1/2] Exclude `rel=dns-prefetch` links

Resolves #1499
---
 lychee-lib/src/extract/html/html5ever.rs | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/lychee-lib/src/extract/html/html5ever.rs b/lychee-lib/src/extract/html/html5ever.rs
index d10ac4e00e..e1b7a6794f 100644
--- a/lychee-lib/src/extract/html/html5ever.rs
+++ b/lychee-lib/src/extract/html/html5ever.rs
@@ -76,10 +76,10 @@ impl TokenSink for LinkExtractor {
                     }
                 }
 
-                // Check and exclude rel=preconnect. Other than prefetch and preload,
-                // preconnect only does DNS lookups and might not be a link to a resource
+                // Check and exclude `rel=preconnect` and `rel=dns-prefetch`. Unlike `prefetch` and `preload`,
+                // `preconnect` and `dns-prefetch` only perform DNS lookups and do not necessarily link to a resource
                 if let Some(rel) = attrs.iter().find(|attr| &attr.name.local == "rel") {
-                    if rel.value.contains("preconnect") {
+                    if rel.value.contains("preconnect") || rel.value.contains("dns-prefetch") {
                         return TokenSinkResult::Continue;
                     }
                 }

From 9be2544b0c3a572c7f05809ce9e59dd60214ccbd Mon Sep 17 00:00:00 2001
From: Matthias <matthias@endler.dev>
Date: Sat, 12 Oct 2024 01:34:26 +0200
Subject: [PATCH 2/2] Add tests for dns-prefetch

---
 lychee-lib/src/extract/html/html5ever.rs | 20 ++++++++++++++++
 lychee-lib/src/extract/html/html5gum.rs  | 29 ++++++++++++++++++++----
 2 files changed, 45 insertions(+), 4 deletions(-)

diff --git a/lychee-lib/src/extract/html/html5ever.rs b/lychee-lib/src/extract/html/html5ever.rs
index e1b7a6794f..3a601287ae 100644
--- a/lychee-lib/src/extract/html/html5ever.rs
+++ b/lychee-lib/src/extract/html/html5ever.rs
@@ -413,4 +413,24 @@ mod tests {
         let uris = extract_html(input, false);
         assert!(uris.is_empty());
     }
+
+    #[test]
+    fn test_skip_dns_prefetch() {
+        let input = r#"
+            <link rel="dns-prefetch" href="https://example.com">
+        "#;
+
+        let uris = extract_html(input, false);
+        assert!(uris.is_empty());
+    }
+
+    #[test]
+    fn test_skip_dns_prefetch_reverse_order() {
+        let input = r#"
+            <link href="https://example.com" rel="dns-prefetch">
+        "#;
+
+        let uris = extract_html(input, false);
+        assert!(uris.is_empty());
+    }
 }
diff --git a/lychee-lib/src/extract/html/html5gum.rs b/lychee-lib/src/extract/html/html5gum.rs
index 276d2e0e86..fa5db3f9b3 100644
--- a/lychee-lib/src/extract/html/html5gum.rs
+++ b/lychee-lib/src/extract/html/html5gum.rs
@@ -151,8 +151,8 @@ impl LinkExtractor {
     /// Here are the rules for extracting links:
     /// - If the current element has a `rel=nofollow` attribute, the current attribute
     ///   value is ignored.
-    /// - If the current element has a `rel=preconnect` attribute, the current attribute
-    ///   value is ignored.
+    /// - If the current element has a `rel=preconnect` or `rel=dns-prefetch`
+    ///   attribute, the current attribute value is ignored.
     /// - If the current attribute value is not a URL, it is treated as plain text and
     ///   added to the links vector.
     /// - If the current attribute name is `id`, the current attribute value is added
@@ -170,8 +170,9 @@ impl LinkExtractor {
         }
 
         if self.current_attributes.get("rel").map_or(false, |rel| {
-            rel.split(',')
-                .any(|r| r.trim() == "nofollow" || r.trim() == "preconnect")
+            rel.split(',').any(|r| {
+                r.trim() == "nofollow" || r.trim() == "preconnect" || r.trim() == "dns-prefetch"
+            })
         }) {
             self.current_attributes.clear();
             return;
@@ -607,4 +608,24 @@ mod tests {
         let uris = extract_html(input, false);
         assert!(uris.is_empty());
     }
+
+    #[test]
+    fn test_skip_dns_prefetch() {
+        let input = r#"
+            <link rel="dns-prefetch" href="https://example.com">
+        "#;
+
+        let uris = extract_html(input, false);
+        assert!(uris.is_empty());
+    }
+
+    #[test]
+    fn test_skip_dns_prefetch_reverse_order() {
+        let input = r#"
+            <link href="https://example.com" rel="dns-prefetch">
+        "#;
+
+        let uris = extract_html(input, false);
+        assert!(uris.is_empty());
+    }
 }