Merge pull request #65 from bobmatyas/updates/111024

Updates/111024
bobmatyas · Nov 10, 2024 · 28337ab · 28337ab
2 parents 2942b3c + 62d493c
commit 28337ab
Show file tree

Hide file tree

Showing 3 changed files with 20 additions and 3 deletions.
diff --git a/block-ai-crawlers.php b/block-ai-crawlers.php
@@ -5,7 +5,7 @@
  * Author:          Bob Matyas
  * Author URI:      https://www.bobmatyas.com
  * Text Domain:     block-ai-crawlers
- * Version:         1.4.0
+ * Version:         1.4.1
  * License:         GPL-2.0-or-later
  * License URI:     https://www.gnu.org/licenses/gpl-2.0.html
  *
@@ -29,6 +29,7 @@
 function block_ai_robots_txt( $robots ) {
 		$robots .= "\n# Block AI Crawlers\n\n";
 		$robots .= "User-agent: AI2Bot\n";
+		$robots .= "User-agent: Ai2Bot-Dolma\n";
 		$robots .= "User-agent: AmazonBot\n";
 		$robots .= "User-agent: Applebot-Extended\n";
 		$robots .= "User-agent: anthropic-ai\n";
@@ -56,6 +57,7 @@ function block_ai_robots_txt( $robots ) {
 		$robots .= "User-agent: SentiBot\n";
 		$robots .= "User-agent: sentibot\n";
 		$robots .= "User-agent: Timpibot\n";
+		$robots .= "User-agent: TurnitinBot\n";
 		$robots .= "User-agent: YouBot\n";
 		$robots .= "User-agent: webzio\n";
 		$robots .= "User-agent: webzio-extended\n";

diff --git a/inc/settings-html.php b/inc/settings-html.php
@@ -27,6 +27,11 @@
 								<td><p>Explores sites for web content that is used to train open language models</p></td>
 								<td><a href="https://allenai.org/crawler" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
 							</tr>
+							<tr>
+								<th>Ai2Bot-Dolma</th>
+								<td><p>Generates data sets used to train open language models</p></td>
+								<td><a href="https://allenai.org/dolma" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
 							<tr>
 								<th>AmazonBot</th>
 								<td><p>Used by Amazon's Alexa AI to provide AI answers.</p></td>
@@ -127,6 +132,11 @@
 								<td><p>Used by Timpi; likely for their Wilson AI Product.</p></td>
 								<td><a href="https://timpi.io/wilson-ai/" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
 							</tr>
+							<tr>
+								<th>TurnitinBot</th>
+								<td><p>Used by Turnitin to scrape data for plagiarism detection</p></td>
+								<td><a href="https://www.turnitin.com/robot/crawlerinfo.html" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
 							<tr>
 								<th>Webzio</th>
 								<td><p>Used by Webz.io for their social listening and intelligence platforms.</p></td>

diff --git a/readme.txt b/readme.txt
@@ -2,9 +2,9 @@
 Contributors: lastsplash
 Tags: ai, robots.txt, chatgpt, crawlers
 Requires at least: 5.6
-Tested up to: 6.6.2
+Tested up to: 6.7
 Requires PHP: 7.4
-Stable tag: 1.4.0
+Stable tag: 1.4.1
 License: GPLv2 or later
 License URI: https://www.gnu.org/licenses/gpl-2.0.html
 
@@ -95,6 +95,11 @@ No. Search engines follow different `robots.txt` rules.
 
 == Changelog ==
 
+= 1.4.1 =
+= New: Block Turnitinbot
+- New: Block Ai2Bot-Dolma
+- Enhancement: WordPress 6.7 compatibility
+
 = 1.4.0 =
 - New: Block Kangaroo Bot
 - New: Block sentibot