Merge pull request #54 from bobmatyas/updates/082824

Updates/082824
bobmatyas · Aug 29, 2024 · 0b798c2 · 0b798c2
2 parents 5e18b92 + 24f7bc9
commit 0b798c2
Show file tree

Hide file tree

Showing 4 changed files with 181 additions and 96 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:         1.3.8
+ * Version:         1.3.9
  * License:         GPL-2.0-or-later
  * License URI:     https://www.gnu.org/licenses/gpl-2.0.html
  *
@@ -28,6 +28,7 @@
  */
 function block_ai_robots_txt( $robots ) {
 		$robots .= "\n# Block AI Crawlers\n\n";
+		$robots .= "User-agent: AI2Bot\n";
 		$robots .= "User-agent: AmazonBot\n";
 		$robots .= "User-agent: Applebot-Extended\n";
 		$robots .= "User-agent: anthropic-ai\n";
@@ -44,11 +45,15 @@ function block_ai_robots_txt( $robots ) {
 		$robots .= "User-agent: ImagesiftBot\n";
 		$robots .= "User-agent: Meta-ExternalAgent\n";
 		$robots .= "User-agent: Meta-ExternalFetcher\n";
+		$robots .= "User-agent: OAI-SearchBot\n";
 		$robots .= "User-agent: Omgili\n";
 		$robots .= "User-agent: Omgilibot\n";
+		$robots .= "User-agent: PetalBot\n";
 		$robots .= "User-agent: PerplexityBot\n";
-		$robots .= "User-agent: Timpibot\n";		
+		$robots .= "User-agent: Timpibot\n";
 		$robots .= "User-agent: YouBot\n";
+		$robots .= "User-agent: webzio\n";
+		$robots .= "User-agent: webzio-extended\n";
 		$robots .= "Disallow: /\n\n";
 		$robots .= "# End Block AI Crawlers\n";
 		return ( $robots );
@@ -74,3 +79,53 @@ function block_ai_activate() {
 }
 
 register_activation_hook( __FILE__, 'block_ai_activate' );
+
+add_filter( 'plugin_action_links', 'block_ai_prepend_plugin_settings_link', 10, 2 );
+
+/**
+ * Adds seettings link to plugins page
+ *
+ * @param array  $links_array            An array of the plugin's metadata.
+ * @param string $plugin_file_name       Path to the plugin file.
+ * @return array $links_array
+ */
+function block_ai_prepend_plugin_settings_link( $links_array, $plugin_file_name ) {
+	if ( strpos( $plugin_file_name, basename( __FILE__ ) ) ) {
+		array_unshift( $links_array, '<a href=" ' . get_admin_url() . ' options-general.php?page=block-ai-crawlers">Settings</a>' );
+	}
+	return $links_array;
+}
+
+
+/**
+ * Adds ratings nudge to plugins page
+ *
+ * @access public
+ * @param array  $links_array            An array of the plugin's metadata.
+ * @param string $plugin_file_name       Path to the plugin file.
+ * @return  array $links_array
+ */
+function block_ai_append_plugin_rating( $links_array, $plugin_file_name ) {
+	if ( strpos( $plugin_file_name, basename( __FILE__ ) ) ) {
+
+		$links_array[] = "<a href='https://wordpress.org/support/plugin/block-ai-crawlers/reviews/#new-post' target='_blank' title='Rate 5 Stars'>
+		<i class='rate-stars'>"
+		. "<svg xmlns='http://www.w3.org/2000/svg' width='15' height='15' viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2' stroke-linecap='round' stroke-linejoin='round' class='feather feather-star'><polygon points='12 2 15.09 8.26 22 9.27 17 14.14 18.18 21.02 12 17.77 5.82 21.02 7 14.14 2 9.27 8.91 8.26 12 2'/></svg>"
+		. "<svg xmlns='http://www.w3.org/2000/svg' width='15' height='15' viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2' stroke-linecap='round' stroke-linejoin='round' class='feather feather-star'><polygon points='12 2 15.09 8.26 22 9.27 17 14.14 18.18 21.02 12 17.77 5.82 21.02 7 14.14 2 9.27 8.91 8.26 12 2'/></svg>"
+		. "<svg xmlns='http://www.w3.org/2000/svg' width='15' height='15' viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2' stroke-linecap='round' stroke-linejoin='round' class='feather feather-star'><polygon points='12 2 15.09 8.26 22 9.27 17 14.14 18.18 21.02 12 17.77 5.82 21.02 7 14.14 2 9.27 8.91 8.26 12 2'/></svg>"
+		. "<svg xmlns='http://www.w3.org/2000/svg' width='15' height='15' viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2' stroke-linecap='round' stroke-linejoin='round' class='feather feather-star'><polygon points='12 2 15.09 8.26 22 9.27 17 14.14 18.18 21.02 12 17.77 5.82 21.02 7 14.14 2 9.27 8.91 8.26 12 2'/></svg>"
+		. "<svg xmlns='http://www.w3.org/2000/svg' width='15' height='15' viewBox='0 0 24 24' fill='none' stroke='currentColor' stroke-width='2' stroke-linecap='round' stroke-linejoin='round' class='feather feather-star'><polygon points='12 2 15.09 8.26 22 9.27 17 14.14 18.18 21.02 12 17.77 5.82 21.02 7 14.14 2 9.27 8.91 8.26 12 2'/></svg>"
+		. '</i></a>';
+
+		$stars_color = '#ffb900';
+
+		echo '<style>'
+		. '.rate-stars{display:inline-block;color:' . $stars_color . ';position:relative;top:3px;}'
+		. '.rate-stars svg {fill:' . $stars_color . ';}'
+		. '</style>';
+	}
+
+	return $links_array;
+}
+
+add_filter( 'plugin_row_meta', 'block_ai_append_plugin_rating', 10, 4 );
diff --git a/inc/css/admin-style.css b/inc/css/admin-style.css
@@ -16,6 +16,10 @@
   color: rgb(75, 75, 75);
 }
 
+.block-ai-container div.block-ai-info table p {
+	font-size: 100%;
+}
+
 .block-ai-container .link {
 	font-size: 100%;
 	padding-top: 2px;
@@ -30,10 +34,8 @@
 .block-ai-container div.block-ai-info table th,
 .block-ai-container div.block-ai-info table p {
   color: rgb(75, 75, 75);
-  font-size: 120%;
 }
 .block-ai-container div.block-ai-info table p {
-  font-size: 115%;
   margin-top: 0;
 }
 
@@ -73,3 +75,7 @@
   border-bottom: 2px solid #eee;
   color: #fff;
 }
+
+.block-ai-container .form-table td {
+	vertical-align: top;
+}
diff --git a/inc/settings-html.php b/inc/settings-html.php
@@ -20,95 +20,110 @@
 			<section>
 				<details> 	
 					<summary><h3>Blocked Crawlers</h3></summary>
-						<table class="form-table">
-							<tbody>
-								<tr>
-									<th>ChatGPT</th>
-									<td><p>Used by OpenAI</p></td>
-									<td><a href="https://platform.openai.com/docs/plugins/bot" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>GPTBot</th>
-									<td><p>Used by OpenAI to allow ChatGPT to access the web</p></td>
-									<td><a href="https://platform.openai.com/docs/gptbot" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>Google Extended</th>
-									<td><p>Used by Google to power Gemini (formerly known as Bard)</p></td>
-									<td><a href="https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers?hl=en#common-crawlers" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>FacebookBot </th>
-									<td><p>Used by Meta (Facebook) for their AI</p></td>
-									<td><a href="https://developers.facebook.com/docs/sharing/bot" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>CommonCrawl</th>
-									<td><p>Compiles datasets used to train AI models</p></td>
-									<td><a href="https://commoncrawl.org/big-picture/frequently-asked-questions/" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>ClaudeBot and Claude-Web</th>
-									<td><p>Used by Anthropic's Claude</p></td>
-									<td><a href="https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>Bytespider</th>
-									<td><p>Used by TikTok for AI training</p></td>
-									<td><a href="https://darkvisitors.com/agents/bytespider" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>Omgilibot</th>
-									<td><p>Used by Omigili to scrape data for AI training</p></td>
-									<td><a href="https://webz.io/blog/machine-learning/common-crawl-vs-webz-io-data-which-one-works-best-for-large-language-models/" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>Cohere</th>
-									<td><p>Used by Cohere to scrape data for AI training</p></td>
-									<td><a href="https://darkvisitors.com/agents/cohere-ai" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>Diffbot</th>
-									<td><p>Used by Diffbot to scrape data for AI training</p></td>
-									<td><a href="https://docs.diffbot.com/reference/crawl-introduction" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>ImagesiftBot</th>
-									<td><p>Used by Hive's Imagesift tool that scrapes images. THis may be used for the company's generative AI product </p></td>
-									<td><a href="https://imagesift.com/about" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>PerplexityBot</th>
-									<td><p>Used by Perplexity for their AI products</p></td>
-									<td><a href="https://docs.perplexity.ai/docs/perplexitybot" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>AppleBot</th>
-									<td><p>Used by Apple for generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools.</p></td>
-									<td><a href="https://support.apple.com/en-us/119829" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>Meta-ExternalAgent / Meta-ExternalFetcher</th>
-									<td><p>Used by Meta to train AI products</p></td>
-									<td><a href="https://developers.facebook.com/docs/sharing/webmasters/web-crawlers" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>YouBot</th>
-									<td><p>Used by You.com to train AI products.</p></td>
-									<td><a href="https://about.you.com/es/youbot/" 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>
-									<td><a href="https://developer.amazon.com/amazonbot" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
-								</tr>
-								<tr>
-									<th>Timpibot</th>
-									<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>
-							</tbody>
-						</table>
+					<table class="form-table">
+						<tbody>
+							<tr>
+								<th>AI2Bot</th>
+								<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>AmazonBot</th>
+								<td><p>Used by Amazon's Alexa AI to provide AI answers.</p></td>
+								<td><a href="https://developer.amazon.com/amazonbot" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>AppleBot</th>
+								<td><p>Used by Apple for generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools.</p></td>
+								<td><a href="https://support.apple.com/en-us/119829" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>Bytespider</th>
+								<td><p>Used by TikTok for AI training</p></td>
+								<td><a href="https://darkvisitors.com/agents/bytespider" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>Cohere</th>
+								<td><p>Used by Cohere to scrape data for AI training</p></td>
+								<td><a href="https://darkvisitors.com/agents/cohere-ai" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>ChatGPT</th>
+								<td><p>Used by OpenAI</p></td>
+								<td><a href="https://platform.openai.com/docs/plugins/bot" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>ClaudeBot and Claude-Web</th>
+								<td><p>Used by Anthropic's Claude</p></td>
+								<td><a href="https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>CommonCrawl</th>
+								<td><p>Compiles datasets used to train AI models</p></td>
+								<td><a href="https://commoncrawl.org/big-picture/frequently-asked-questions/" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>Diffbot</th>
+								<td><p>Used by Diffbot to scrape data for AI training</p></td>
+								<td><a href="https://docs.diffbot.com/reference/crawl-introduction" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>FacebookBot</th>
+								<td><p>Used by Meta (Facebook) for their AI</p></td>
+								<td><a href="https://developers.facebook.com/docs/sharing/bot" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>Google Extended</th>
+								<td><p>Used by Google to power Gemini (formerly known as Bard)</p></td>
+								<td><a href="https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers?hl=en#common-crawlers" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>ImagesiftBot</th>
+								<td><p>Used by Hive's Imagesift tool that scrapes images. This may be used for the company's generative AI product </p></td>
+								<td><a href="https://imagesift.com/about" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>Meta-ExternalAgent / Meta-ExternalFetcher</th>
+								<td><p>Used by Meta to train AI products</p></td>
+								<td><a href="https://developers.facebook.com/docs/sharing/webmasters/web-crawlers" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>OAI-SearchBot</th>
+								<td><p>Used by OpenAI for their SearchGPT product.</p></td>
+								<td><a href="https://platform.openai.com/docs/bots" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>Omgilibot</th>
+								<td><p>Used by Omigili to scrape data for AI training</p></td>
+								<td><a href="https://webz.io/blog/machine-learning/common-crawl-vs-webz-io-data-which-one-works-best-for-large-language-models/" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>PerplexityBot</th>
+								<td><p>Used by Perplexity for their AI products</p></td>
+								<td><a href="https://docs.perplexity.ai/docs/perplexitybot" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>Timpibot</th>
+								<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>Webzio</th>
+								<td><p>Used by Webz.io for their social listening and intelligence platforms.</p></td>
+								<td><a href="https://webz.io/bot.html" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>Webzio-Extended</th>
+								<td><p>Used by Webz.io for AI training.</p></td>
+								<td><a href="https://webz.io/bot.html" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+							<tr>
+								<th>YouBot</th>
+								<td><p>Used by You.com to train AI products.</p></td>
+								<td><a href="https://about.you.com/es/youbot/" target=_blank>More Info <span class="dashicons dashicons-external link"></span></a></td>
+							</tr>
+						</tbody>
+					</table>
 				</details>
 			</section>
 

diff --git a/readme.txt b/readme.txt
@@ -2,13 +2,13 @@
 Contributors: lastsplash
 Tags: ai, robots.txt, chatgpt, crawlers
 Requires at least: 5.6
-Tested up to: 6.5.3
+Tested up to: 6.6
 Requires PHP: 7.4
-Stable tag: 1.3.8
+Stable tag: 1.3.9
 License: GPLv2 or later
 License URI: https://www.gnu.org/licenses/gpl-2.0.html
 
-Tell AI crawlers not to access your site to train their models.
+Tells AI companies not to access and scrape your site for AI.
 
 == Description ==
 
@@ -72,6 +72,15 @@ No. Search engines follow different `robots.txt` rules.
 
 == Changelog ==
 
+= 1.3.9 =
+- New: Block PetalBot
+- New: Block AI2Bot
+- New: Block Webz.io
+- New: Block OpenAI Search Bot (SearchGPT)
+- Enhancement: Alphabetize list of blocked crawlers
+- Enhancement: Indicate compatibility with WordPress v6.6
+- Enhancement: Add quick link to settings and nudge for rating on plugins page
+
 = 1.3.8 =
 - Maintenance: Auto-deply from Github fixed / bumped version number