diff --git a/src/wp-includes/html-api/class-wp-html-tag-processor.php b/src/wp-includes/html-api/class-wp-html-tag-processor.php
index 79d96dc8be3f1..e6ac98daae6ab 100644
--- a/src/wp-includes/html-api/class-wp-html-tag-processor.php
+++ b/src/wp-includes/html-api/class-wp-html-tag-processor.php
@@ -378,6 +378,15 @@ class WP_HTML_Tag_Processor {
 	 */
 	private $is_closing_tag;
 
+	/**
+	 * Stores the position of the last-matched tag, or the start of the document if not matched yet.
+	 *
+	 * @var WP_HTML_Span
+	 */
+	private $last_position = null;
+
+	private $last_token_end = 0;
+
 	/**
 	 * Lazily-built index of attributes found within an HTML tag, keyed by the attribute name.
 	 *
@@ -507,6 +516,8 @@ class WP_HTML_Tag_Processor {
 	 */
 	public function __construct( $html ) {
 		$this->html = $html;
+
+		$this->last_position = new WP_HTML_Span( 0, 0 );
 	}
 
 	/**
@@ -530,6 +541,16 @@ public function next_tag( $query = null ) {
 		$this->parse_query( $query );
 		$already_found = 0;
 
+		if ( null !== $this->tag_name_starts_at ) {
+			$rewind_amount = $this->is_closing_tag ? 2 : 1;
+			$before_tag    = $this->tag_name_starts_at - $rewind_amount;
+			$end_of_tag    = $this->tag_ends_at;
+
+			$this->last_position->start = $before_tag;
+			$this->last_position->end   = $end_of_tag;
+			$this->last_token_end       = $this->tag_ends_at + 1;
+		}
+
 		do {
 			if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
 				return false;
@@ -1876,6 +1897,74 @@ public function is_tag_closer() {
 		return $this->is_closing_tag;
 	}
 
+	/**
+	 * Returns the chunk of text from the end of the preceding tag or token to the
+	 * start of the matched tag or token, with decoded character references.
+	 *
+	 * Example:
+	 *
+	 *     $q = array( 'tag_closers' => 'visit' );
+	 *     $processor = new WP_HTML_Tag_Processor( 'Before<div>Inside</div>After' );
+	 *     $processor->next_tag( $q ); 'Before' === $processor->get_prev_text_chunk();
+	 *     $processor->next_tag( $q ); 'Inside' === $processor->get_prev_text_chunk();
+	 *     $processor->next_tag( $q ); 'After'  === $processor->get_prev_text_chunk();
+	 *
+	 * @since 6.4.0
+	 *
+	 * @return string|null Chunk of text from end of last token to current token, or NULL if not yet matched.
+	 */
+	public function get_previous_text_chunk() {
+		if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
+			$chunk = substr( $this->html, $this->last_position->end === 0 ? 0 : $this->last_position->end + 1 );
+			$chunk = preg_replace( '/<[^a-z].*>/i', '', $chunk );
+			return html_entity_decode( $chunk, ENT_HTML5 | ENT_QUOTES | ENT_SUBSTITUTE );
+		}
+
+		if ( ! $this->tag_name_starts_at ) {
+			return null;
+		}
+
+		$chunk_start = $this->last_position->end === 0 ? 0 : $this->last_position->end + 1;
+		$chunk_end   = $this->is_tag_closer() ? $this->tag_name_starts_at - 2 : $this->tag_name_starts_at - 1;
+		$chunk       = substr( $this->html, $chunk_start, $chunk_end - $chunk_start );
+		$chunk = preg_replace( '/<[^a-z].*>/i', '', $chunk );
+		return html_entity_decode( $chunk, ENT_HTML5 | ENT_QUOTES | ENT_SUBSTITUTE );
+	}
+
+	/**
+	 * Returns the chunk of html from the start of the preceding tag or token to the
+	 * start of the matched tag or token, without decoded character references.
+	 *
+	 * Example:
+	 *
+	 *     $q = array( 'tag_closers' => 'visit' );
+	 *     $processor = new WP_HTML_Tag_Processor( 'Before<div>Inside</div>After' );
+	 *     $processor->next_tag( $q ); 'Before'       === $processor->get_prev_text_chunk();
+	 *     $processor->next_tag( $q ); '<div>Inside'  === $processor->get_prev_text_chunk();
+	 *     $processor->next_tag( $q ); '</div>After'  === $processor->get_prev_text_chunk();
+	 *
+	 * @since 6.4.0
+	 *
+	 * @return array|null Chunk of text from end of last token to current token, or NULL if not yet matched.
+	 */
+	public function get_previous_html_chunk() {
+		if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
+			$html = substr( $this->html, $this->last_position->start, $this->last_token_end - $this->last_position->start );
+			$text = substr( $this->html, $this->last_token_end );
+
+			return array( $html, $text );
+		}
+
+		if ( ! $this->tag_name_starts_at ) {
+			return null;
+		}
+
+		$html = substr( $this->html, $this->last_position->start, $this->last_token_end - $this->last_position->start );
+		$text = substr( $this->html, $this->last_token_end, ( $this->is_tag_closer() ? $this->tag_name_starts_at - 2 : $this->tag_name_starts_at - 1 ) - $this->last_token_end );
+
+		return array( $html, $text );
+	}
+
 	/**
 	 * Updates or creates a new attribute on the currently matched tag with the passed value.
 	 *
diff --git a/tests/phpunit/tests/html-api/wpHtmlProcessor-stringBuilder.php b/tests/phpunit/tests/html-api/wpHtmlProcessor-stringBuilder.php
new file mode 100644
index 0000000000000..4511e093a60ad
--- /dev/null
+++ b/tests/phpunit/tests/html-api/wpHtmlProcessor-stringBuilder.php
@@ -0,0 +1,114 @@
+<?php
+/**
+ * Unit tests covering WP_HTML_Processor string building functionality.
+ *
+ * @package WordPress
+ * @subpackage HTML-API
+ */
+
+/**
+ * @group html-api
+ *
+ * @coversDefaultClass WP_HTML_Processor
+ */
+class Tests_HtmlApi_WpHtmlProcessor_StringBuilder extends WP_UnitTestCase {
+	/**
+	 * @ticket {TICKET_NUMBER}
+	 *
+	 * @dataProvider data_html_and_associated_text_content
+	 *
+	 * @param string $html         HTML containing text that should be extracted.
+	 * @param string $text_content Plaintext content represented inside the given HTML.
+	 */
+	public function test_extracts_text_chunks_properly( $html, $text_content ) {
+		$processor = new WP_HTML_Tag_Processor( $html );
+
+		$extracted_text_content = '';
+		while ( $processor->next_tag( array( 'tag_closers' => 'visit' ) ) ) {
+			$extracted_text_content .= $processor->get_previous_text_chunk();
+		}
+		$extracted_text_content .= $processor->get_previous_text_chunk();
+
+		$this->assertEquals( $text_content, $extracted_text_content, 'Extracted unexpected text content.' );
+	}
+
+	/**
+	 * Data provider.
+	 *
+	 * @return array[].
+	 */
+	public function data_html_and_associated_text_content() {
+		return array(
+			'Basic text without HTML.'               => array( 'This is plain text.', 'This is plain text.' ),
+			'Basic text with a character reference.' => array( 'A &lt; B', 'A < B' ),
+			'Text before tag.'                       => array( 'Before<img>', 'Before' ),
+			'Text after tag.'                        => array( '<img>After', 'After' ),
+			'Text inside tag.'                       => array( '<div>Inside</div>', 'Inside' ),
+			'Text around tag.'                       => array( 'In <em>the</em> jungle.', 'In the jungle.' ),
+			'Text interrupted by many tags.'         => array( 'A <em>wild <a><img><span>adventure</span></a> awaits.', 'A wild adventure awaits.' ),
+			'Text with comment inside it.'           => array( 'Ignore <!-- everything inside this --> comment.', 'Ignore  comment.' ),
+			'Text with empty comment inside it.'     => array( 'Ignore <!--> comment.', 'Ignore  comment.' ),
+			'Text with invalid comment inside it.'   => array( 'Ignore </^$%> comment.', 'Ignore  comment.' ),
+			'Skipping SCRIPT content.'               => array( '<div>This <script>does not exist</script> in the output.', 'This  in the output.' ),
+		);
+	}
+
+	/**
+	 * @ticket {TICKET_NUMBER}
+	 *
+	 * @dataProvider data_html_and_associated_html_content
+	 *
+	 * @param string $html            HTML containing text that should be extracted.
+	 * @param int    $max_code_points Stop iterating after this many code points have been extracted.
+	 * @param string $html_content    Full HTML containing text of max code point length from input.
+	 */
+	public function test_extracts_html_chunks_properly( $html, $max_code_points, $html_content ) {
+		$processor = new WP_HTML_Tag_Processor( $html );
+
+		$code_points            = 0;
+		$extracted_html_content = '';
+		while ( $processor->next_tag( array( 'tag_closers' => 'visit' ) ) ) {
+			$text_chunk = $processor->get_previous_text_chunk();
+			$chunk_cps           = mb_strlen( $text_chunk );
+			list( $html, $text ) = $processor->get_previous_html_chunk();
+			$extracted_html_content .= $html;
+			if ( 0 === $max_code_points || $code_points + $chunk_cps <= $max_code_points ) {
+				$extracted_html_content .= $text;
+				$code_points            += $chunk_cps;
+			} else {
+				break;
+			}
+		}
+
+		$text_chunk = $processor->get_previous_text_chunk();
+		$chunk_cps  = mb_strlen( $text_chunk );
+		list( $html, $text ) = $processor->get_previous_html_chunk();
+		$extracted_html_content .= $html;
+		if ( 0 === $max_code_points || $code_points + $chunk_cps <= $max_code_points ) {
+			$extracted_html_content .= $text;
+		}
+
+		$this->assertEquals( $html_content, $extracted_html_content, 'Extracted unexpected HTML content.' );
+	}
+
+	/**
+	 * Data provider.
+	 *
+	 * @return array[].
+	 */
+	public function data_html_and_associated_html_content() {
+		return array(
+			'Basic text without HTML.'               => array( 'This is plain text.', 0, 'This is plain text.' ),
+			'Basic text without HTML (too long).'    => array( 'This is plain text.', 8, '' ),
+			'Basic text with a character reference.' => array( 'A &lt; B', 0, 'A &lt; B' ),
+			'Character reference wider than text'    => array( 'A &lt; B', 5, 'A &lt; B' ),
+			'Text before tag.'                       => array( 'Before<img>', 0, 'Before<img>' ),
+			'Text after tag.'                        => array( '<img>After', 0, '<img>After' ),
+			'Text inside tag.'                       => array( '<div>Inside</div>', 0, '<div>Inside</div>' ),
+			'Text around tag.'                       => array( 'In <em>the</em> jungle.', 0, 'In <em>the</em> jungle.' ),
+			'Text interrupted by many tags.'         => array( 'A <em>wild <a><img><span>adventure</span></a> awaits.', 0, 'A <em>wild <a><img><span>adventure</span></a> awaits.' ),
+			'Text interrupted by many tags (long).'  => array( 'A <em>wild <a><img><span>adventure</span></a> awaits.', 16, 'A <em>wild <a><img><span>adventure</span></a>' ),
+			'Text with comment inside it.'           => array( 'Ignore <!-- everything inside this --> comment.', 0, 'Ignore <!-- everything inside this --> comment.' ),
+		);
+	}
+}