MatchElemAttr func implementation

go.mod

@@ -1,5 +0,0 @@
-module git.nkpl.cc/XoxJlopeZi4BB/scraper.git
-
-go 1.25.5
-
-require golang.org/x/net v0.48.0

go.sum

@@ -1,2 +0,0 @@
-golang.org/x/net v0.48.0 h1:zyQRTTrjc33Lhh0fBgT/H3oZq9WuvRR5gPC70xpDiQU=
-golang.org/x/net v0.48.0/go.mod h1:+ndRgGjkh8FGtu1w1FGbEC31if4VrNVMuKTgcAAnQRY=

match.go

@@ -0,0 +1,38 @@
+package scraper
+
+import (
+	"errors"
+	"slices"
+	"strings"
+
+	"golang.org/x/net/html"
+	"golang.org/x/net/html/atom"
+)
+
+var body = &html.Node{
+	Type:     html.ElementNode,
+	Data:     "body",
+	DataAtom: atom.Body,
+}
+
+var ErrNotAnElementNode = errors.New("not an ElementNode")
+
+func MatchElemAttr(s string, n2 *html.Node) (bool, error) {
+	r := strings.NewReader(s)
+	n, err := html.ParseFragment(r, body)
+	if err != nil {
+		return false, err
+	}
+	n1 := n[0]
+
+	if !(n1.Type == html.ElementNode &&
+		n2.Type == html.ElementNode) {
+		return false, ErrNotAnElementNode
+	}
+
+	if n1.Data == n2.Data &&
+		slices.Equal(n1.Attr, n2.Attr) {
+		return true, nil
+	}
+	return false, nil
+}

match_test.go

@@ -0,0 +1,26 @@
+package scraper
+
+import (
+	"strings"
+	"testing"
+
+	"golang.org/x/net/html"
+)
+
+const fragment = `<div id="main-copy"></div>`
+
+func TestMatchElemAttr(t *testing.T) {
+	n, err := html.ParseFragment(strings.NewReader(fragment), body)
+	if err != nil {
+		t.Error(err)
+	}
+	n1 := n[0]
+
+	result, err := MatchElemAttr(fragment, n1)
+	if err != nil {
+		t.Error(err)
+	}
+	if !result {
+		t.Fail()
+	}
+}

scraper.go

@@ -8,7 +8,7 @@ import (
 
 type crawlFunc func(*html.Node)
 
-func searchElem(n *html.Node, data string) chan *html.Node {
+func SearchElem(n *html.Node, data string) chan *html.Node {
 	ch := make(chan *html.Node)
 	var crawl crawlFunc
 	crawl = func(n *html.Node) {
@@ -29,7 +29,7 @@ func searchElem(n *html.Node, data string) chan *html.Node {
 	return ch
 }
 
-func searchAttr(n *html.Node, key, contains string) chan *html.Node {
+func SearchAttr(n *html.Node, key, contains string) chan *html.Node {
 	ch := make(chan *html.Node)
 	var crawl crawlFunc
 	crawl = func(n *html.Node) {
@@ -52,14 +52,14 @@ func searchAttr(n *html.Node, key, contains string) chan *html.Node {
 	return ch
 }
 
-func searchElemAttr(n *html.Node, elem, key, value string) chan *html.Node {
+func SearchElemAttr(n *html.Node, elem, key, value string) chan *html.Node {
 	ch := make(chan *html.Node)
 	go func() {
 		defer close(ch)
-		for e := range searchElem(n, elem) {
+		for e := range SearchElem(n, elem) {
 			// If document is too large there are
 			// would be a hundreds of goroutines :((
-			for attr := range searchAttr(e, key, value) {
+			for attr := range SearchAttr(e, key, value) {
 				ch <- attr
 			}
 		}
@@ -67,7 +67,7 @@ func searchElemAttr(n *html.Node, elem, key, value string) chan *html.Node {
 	return ch
 }
 
-func crawlText(n *html.Node) string {
+func CrawlText(n *html.Node) string {
 	var s = new(strings.Builder)
 	var crawl crawlFunc
 	crawl = func(n *html.Node) {

scraper_test.go

@@ -15,7 +15,7 @@ func TestSearchElem(t *testing.T) {
 		html.Parse(strings.NewReader(htmlStr)),
 	)
 
-	ch := searchElem(doc, "span")
+	ch := SearchElem(doc, "span")
 	count := 0
 	for range ch {
 		count++
@@ -31,7 +31,7 @@ func TestSearchAttr(t *testing.T) {
 		html.Parse(strings.NewReader(htmlStr)),
 	)
 
-	ch := searchAttr(doc, "id", "test")
+	ch := SearchAttr(doc, "id", "test")
 	count := 0
 	for range ch {
 		count++
@@ -47,7 +47,7 @@ func TestSearchElemAttr(t *testing.T) {
 		html.Parse(strings.NewReader(htmlStr)),
 	)
 
-	ch := searchElemAttr(doc, "span", "id", "test")
+	ch := SearchElemAttr(doc, "span", "id", "test")
 	count := 0
 	for range ch {
 		count++