From 81f35db25ab6f634b24d4f66b9ff80d3fa9dc5b9 Mon Sep 17 00:00:00 2001
From: dualfroz <me@dualfroz.com>
Date: Fri, 4 Sep 2026 07:54:24 +0200
Subject: [PATCH] feat: add NewDocumentFromReaderWithOptions

goquery calls html.Parse, so callers cannot reach the parse options that
golang.org/x/net/html has since grown. The one that matters is
ParseOptionEnableScripting(false): with scripting assumed enabled the
contents of a noscript element are parsed as raw text and no selector
can reach inside it.

Add a constructor taking html.ParseOption values. Existing constructors
are untouched.

Refs #139
---
 type.go      | 18 ++++++++++++++++++
 type_test.go | 37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+)

diff --git a/type.go b/type.go
index dd3778d..7f34170 100644
--- a/type.go
+++ b/type.go
@@ -56,6 +56,24 @@ func NewDocumentFromReader(r io.Reader) (*Document, error) {
 	return newDocument(root, nil), nil
 }
 
+// NewDocumentFromReaderWithOptions is like NewDocumentFromReader, with the
+// parse options of the html package.
+//
+// The option that usually matters is html.ParseOptionEnableScripting(false),
+// which makes <noscript> content reachable by selectors:
+//
+//	doc, err := goquery.NewDocumentFromReaderWithOptions(r,
+//		html.ParseOptionEnableScripting(false))
+//
+// The options apply to this parse only.
+func NewDocumentFromReaderWithOptions(r io.Reader, opts ...html.ParseOption) (*Document, error) {
+	root, e := html.ParseWithOptions(r, opts...)
+	if e != nil {
+		return nil, e
+	}
+	return newDocument(root, nil), nil
+}
+
 // NewDocumentFromResponse is another Document constructor that takes an http response as argument.
 // It loads the specified response's document, parses it, and stores the root Document
 // node, ready to be manipulated. The response's body is closed on return.
diff --git a/type_test.go b/type_test.go
index 84080a9..1a85fb3 100644
--- a/type_test.go
+++ b/type_test.go
@@ -253,3 +253,40 @@ func TestSingle(t *testing.T) {
 		t.Fatalf("want %q, got %q", "142", text)
 	}
 }
+
+func TestNewDocumentFromReaderWithOptions(t *testing.T) {
+	const doc = `<html><body><p>before</p><noscript><a href="http://example.org">click this link</a></noscript></body></html>`
+
+	// With scripting on, <noscript> content is raw text no selector can reach.
+	d, e := NewDocumentFromReader(strings.NewReader(doc))
+	if e != nil {
+		t.Fatal(e)
+	}
+	if _, ok := d.Find("noscript a").Attr("href"); ok {
+		t.Error("expected no match inside noscript with scripting enabled")
+	}
+
+	d, e = NewDocumentFromReaderWithOptions(strings.NewReader(doc), html.ParseOptionEnableScripting(false))
+	if e != nil {
+		t.Fatal(e)
+	}
+	href, ok := d.Find("noscript a").Attr("href")
+	if !ok {
+		t.Fatal("expected a match inside noscript with scripting disabled")
+	}
+	if href != "http://example.org" {
+		t.Errorf("got href %q, want %q", href, "http://example.org")
+	}
+}
+
+func TestNewDocumentFromReaderWithOptionsNoOptions(t *testing.T) {
+	const doc = `<html><body><p class="x">hi</p></body></html>`
+
+	d, e := NewDocumentFromReaderWithOptions(strings.NewReader(doc))
+	if e != nil {
+		t.Fatal(e)
+	}
+	if got := d.Find("p.x").Text(); got != "hi" {
+		t.Errorf("got %q, want %q", got, "hi")
+	}
+}