fix: support <meta name=description> in link previews (#6000)

Co-authored-by: goingforstudying-ctrl <goingforstudying-ctrl@users.noreply.github.com>
1 month ago · e8d32e87d1
parent 0d31e3c2fb
commit e8d32e87d1
2 changed files with 75 additions and 6 deletions
--- a/internal/httpgetter/html_meta.go
+++ b/internal/httpgetter/html_meta.go
@ -7,6 +7,7 @@ import (
 	"net"
 	"net/http"
 	"net/url"
+	"strings"
 	"time"

 	"github.com/pkg/errors"
@ -175,11 +176,6 @@ func extractHTMLMeta(resp io.Reader) *HTMLMeta {
 				token := tokenizer.Token()
 				htmlMeta.Title = token.Data
 			} else if token.DataAtom == atom.Meta {
-				description, ok := extractMetaProperty(token, "description")
-				if ok {
-					htmlMeta.Description = description
-				}
-
 				ogTitle, ok := extractMetaProperty(token, "og:title")
 				if ok {
 					htmlMeta.Title = ogTitle
@ -194,6 +190,11 @@ func extractHTMLMeta(resp io.Reader) *HTMLMeta {
 				if ok {
 					htmlMeta.Image = ogImage
 				}
+
+				description, ok := extractMetaProperty(token, "description")
+				if ok && htmlMeta.Description == "" {
+					htmlMeta.Description = description
+				}
 			}
 		}
 	}
@ -204,7 +205,7 @@ func extractHTMLMeta(resp io.Reader) *HTMLMeta {
 func extractMetaProperty(token html.Token, prop string) (content string, ok bool) {
 	content, ok = "", false
 	for _, attr := range token.Attr {
-		if attr.Key == "property" && attr.Val == prop {
+		if (attr.Key == "property" || attr.Key == "name") && strings.EqualFold(attr.Val, prop) {
 			ok = true
 		}
 		if attr.Key == "content" {
--- a/internal/httpgetter/html_meta_test.go
+++ b/internal/httpgetter/html_meta_test.go
@ -55,6 +55,74 @@ func TestGetHTMLMeta(t *testing.T) {
 	}, *metadata)
 }

+func TestGetHTMLMetaWithNameOnly(t *testing.T) {
+	originalHTTPClient := httpClient
+	t.Cleanup(func() {
+		httpClient = originalHTTPClient
+	})
+
+	httpClient = &http.Client{
+		Transport: roundTripFunc(func(req *http.Request) (*http.Response, error) {
+			require.Equal(t, "http://93.184.216.34/blog", req.URL.String())
+			return &http.Response{
+				StatusCode: http.StatusOK,
+				Header:     http.Header{"Content-Type": []string{"text/html; charset=utf-8"}},
+				Body: io.NopCloser(strings.NewReader(`<!doctype html>
+<html>
+<head>
+  <title>Sample Page</title>
+  <meta name="description" content="This description should appear in the link preview.">
+</head>
+<body>Hello</body>
+</html>`)),
+				Request: req,
+			}, nil
+		}),
+	}
+
+	metadata, err := GetHTMLMeta("http://93.184.216.34/blog")
+	require.NoError(t, err)
+	require.Equal(t, HTMLMeta{
+		Title:       "Sample Page",
+		Description: "This description should appear in the link preview.",
+		Image:       "",
+	}, *metadata)
+}
+
+func TestGetHTMLMetaWithNameCaseInsensitive(t *testing.T) {
+	originalHTTPClient := httpClient
+	t.Cleanup(func() {
+		httpClient = originalHTTPClient
+	})
+
+	httpClient = &http.Client{
+		Transport: roundTripFunc(func(req *http.Request) (*http.Response, error) {
+			require.Equal(t, "http://93.184.216.34/blog", req.URL.String())
+			return &http.Response{
+				StatusCode: http.StatusOK,
+				Header:     http.Header{"Content-Type": []string{"text/html; charset=utf-8"}},
+				Body: io.NopCloser(strings.NewReader(`<!doctype html>
+<html>
+<head>
+  <title>Sample Page</title>
+  <meta name="Description" content="Case insensitive description match.">
+</head>
+<body>Hello</body>
+</html>`)),
+				Request: req,
+			}, nil
+		}),
+	}
+
+	metadata, err := GetHTMLMeta("http://93.184.216.34/blog")
+	require.NoError(t, err)
+	require.Equal(t, HTMLMeta{
+		Title:       "Sample Page",
+		Description: "Case insensitive description match.",
+		Image:       "",
+	}, *metadata)
+}
+
 func TestGetHTMLMetaForInternal(t *testing.T) {
 	// test for internal IP
 	if _, err := GetHTMLMeta("http://192.168.0.1"); !errors.Is(err, ErrInternalIP) {