#43590: Use robots meta tag to better discourage search engines.

This changes the "discourage search engines" option to output a `noindex, nofollow` robots meta tag. `Disallow: /` is removed from the `robots.txt` to allow search engines to discover they are requested not to index the site.

Disallowing search engines from accessing a site in the `robots.txt` file can result in search engines listing a site with a fragment (a listing without content).

Props donmhico, jonoaldersonwp.
Fixes #43590.



git-svn-id: https://develop.svn.wordpress.org/trunk@45928 602fd350-edb4-49c9-b593-d223f7449a82

src/wp-includes/functions.php

@@ -1582,6 +1582,8 @@ function do_feed_atom( $for_comments ) {
  * Displays the default robots.txt file content.
  *
  * @since 2.1.0
+ * @since 5.3.0 Remove the "Disallow: /" output if search engine visiblity is
+ *              discouraged in favor of robots meta HTML tag in wp_no_robots().
  */
 function do_robots() {
 	header( 'Content-Type: text/plain; charset=utf-8' );
@@ -1595,14 +1597,11 @@ function do_robots() {
 
 	$output = "User-agent: *\n";
 	$public = get_option( 'blog_public' );
-	if ( '0' == $public ) {
-		$output .= "Disallow: /\n";
-	} else {
-		$site_url = parse_url( site_url() );
-		$path     = ( ! empty( $site_url['path'] ) ) ? $site_url['path'] : '';
-		$output  .= "Disallow: $path/wp-admin/\n";
-		$output  .= "Allow: $path/wp-admin/admin-ajax.php\n";
-	}
+
+	$site_url = parse_url( site_url() );
+	$path     = ( ! empty( $site_url['path'] ) ) ? $site_url['path'] : '';
+	$output  .= "Disallow: $path/wp-admin/\n";
+	$output  .= "Allow: $path/wp-admin/admin-ajax.php\n";
 
 	/**
 	 * Filters the robots.txt output.

src/wp-includes/general-template.php

@@ -2986,12 +2986,18 @@ function noindex() {
  * Display a noindex meta tag.
  *
  * Outputs a noindex meta tag that tells web robots not to index the page content.
- * Typical usage is as a wp_head callback. add_action( 'wp_head', 'wp_no_robots' );
+ * Typical usage is as a {@see 'wp_head'} callback. add_action( 'wp_head', 'wp_no_robots' );
  *
  * @since 3.3.0
+ * @since 5.3.0 Echo "noindex,nofollow" if search engine visibility is discouraged.
  */
 function wp_no_robots() {
-	echo "<meta name='robots' content='noindex,follow' />\n";
+	if ( get_option( 'blog_public' ) ) {
+		echo "<meta name='robots' content='noindex,follow' />\n";
+		return;
+	}
+
+	echo "<meta name='robots' content='noindex,nofollow' />\n";
 }
 
 /**

tests/phpunit/tests/general/template.php

@@ -612,4 +612,19 @@ function test_get_custom_logo_preserves_switched_state() {
 
 		$this->assertSame( $expected, $result );
 	}
+
+	/**
+	 * @ticket 43590
+	 */
+	function test_wp_no_robots() {
+		// Simulate private site (search engines discouraged).
+		update_option( 'blog_public', '0' );
+		$actual_private = get_echo( 'wp_no_robots' );
+		$this->assertSame( "<meta name='robots' content='noindex,nofollow' />\n", $actual_private );
+
+		// Simulate public site.
+		update_option( 'blog_public', '1' );
+		$actual_public = get_echo( 'wp_no_robots' );
+		$this->assertSame( "<meta name='robots' content='noindex,follow' />\n", $actual_public );
+	}
 }