Merge pull request 'Blockbot: You can now allow social media agents' (#1474) from heluecht/friendica-addons:blockbot into 2024.03-rc

Reviewed-on: https://git.friendi.ca/friendica/friendica-addons/pulls/1474

blockbot/blockbot.php

@@ -29,6 +29,7 @@ function blockbot_addon_admin(string &$o)
 	$o = Renderer::replaceMacros($t, [
 		'$submit'             => DI::l10n()->t('Save Settings'),
 		'$good_crawlers'      => ['good_crawlers', DI::l10n()->t('Allow "good" crawlers'), DI::config()->get('blockbot', 'good_crawlers'), DI::l10n()->t("Don't block fediverse crawlers, relay servers and other bots with good purposes.")],
+		'$socialmedia_agents' => ['socialmedia_agents', DI::l10n()->t('Allow preview agents'), DI::config()->get('blockbot', 'socialmedia_agents'), DI::l10n()->t("Don't block agents from social media systems that want to generate preview data for links that had been set by their users.")],
 		'$block_gab'          => ['block_gab', DI::l10n()->t('Block GabSocial'), DI::config()->get('blockbot', 'block_gab'), DI::l10n()->t('Block the software GabSocial. This will block every access for that software. You can block dedicated gab instances in the blocklist settings in the admin section.')],
 		'$training'           => ['training', DI::l10n()->t('Training mode'), DI::config()->get('blockbot', 'training'), DI::l10n()->t("Activates the training mode. This is only meant for developing purposes. Don't activate this on a production machine. This can cut communication with some systems.")],
 	]);
@@ -37,6 +38,7 @@ function blockbot_addon_admin(string &$o)
 function blockbot_addon_admin_post()
 {
 	DI::config()->set('blockbot', 'good_crawlers', $_POST['good_crawlers'] ?? false);
+	DI::config()->set('blockbot', 'socialmedia_agents', $_POST['socialmedia_agents'] ?? false);
 	DI::config()->set('blockbot', 'block_gab', $_POST['block_gab'] ?? false);
 	DI::config()->set('blockbot', 'training', $_POST['training'] ?? false);
 }
@@ -53,34 +55,41 @@ function blockbot_init_1()
 	$good_agents = [
 		'fediverse.space crawler', 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0',
 		'Social-Relay/', 'Test Certificate Info', 'Uptimebot/', 'GNUSocialBot', 'UptimeRobot/',
-		'PTST/', 'Zabbix', 'Poduptime/'
+		'PTST/', 'Zabbix', 'Poduptime/', 'FediFetcher', 'lemmy-stats-crawler',
+		'FedditLemmyverseCrawler/', 'kbinBot/', 'lemmy-explorer-crawler/',
 	];
 
-	// List of known crawlers.
+	// List of agents from social media systems that fetch preview data via opem graph or twitter cards
+	$socialmedia_agents = ['Twitterbot/', 'facebookexternalhit/', 'SkypeUriPreview Preview/',
+		'TelegramBot', 'WhatsApp/', 'github-camo', 'Bluesky Cardyb/', 'XING-contenttabreceiver/', 
+		'LinkedInBot/', 'Instagram ', 'Synapse (bot; ', 'Discordbot/'];
+
+	// List of known unwanted crawlers.
 	$agents = [
 		'SemrushBot', 's~feedly-nikon3', 'Qwantify/Bleriot/', 'ltx71', 'Sogou web spider/',
-		'Diffbot/', 'Twitterbot/', 'YisouSpider', 'evc-batch/', 'LivelapBot/', 'TrendsmapResolver/',
+		'Diffbot/', 'YisouSpider', 'evc-batch/', 'LivelapBot/', 'TrendsmapResolver/',
 		'PaperLiBot/', 'Nuzzel', 'um-LN/', 'Google Favicon', 'Datanyze', 'BLEXBot/', '360Spider',
 		'adscanner/', 'HeadlessChrome', 'wpif', 'startmebot/', 'Googlebot/', 'Applebot/',
-		'facebookexternalhit/', 'GoogleImageProxy', 'bingbot/', 'heritrix/', 'ldspider',
+		'GoogleImageProxy', 'bingbot/', 'heritrix/', 'ldspider',
 		'AwarioRssBot/', 'TweetmemeBot/', 'dcrawl/', 'PhantomJS/', 'Googlebot-Image/',
 		'CrowdTanglebot/', 'Mediapartners-Google', 'Baiduspider/', 'datagnionbot',
 		'MegaIndex.ru/', 'SMUrlExpander', 'Hatena-Favicon/', 'Wappalyzer', 'FlipboardProxy/',
 		'NetcraftSurveyAgent/', 'Dataprovider.com', 'SMTBot/', 'Nimbostratus-Bot/',
 		'DuckDuckGo-Favicons-Bot/', 'IndieWebCards/', 'proximic', 'netEstate NE Crawler',
-		'AhrefsBot/', 'YandexBot/', 'Exabot/', 'Mediumbot-MetaTagFetcher/', 'WhatsApp/',
+		'AhrefsBot/', 'YandexBot/', 'Exabot/', 'Mediumbot-MetaTagFetcher/',
-		'TelegramBot', 'SurdotlyBot/', 'BingPreview/', 'SabsimBot/', 'CCBot/', 'WbSrch/',
+		'SurdotlyBot/', 'BingPreview/', 'SabsimBot/', 'CCBot/', 'WbSrch/',
 		'DuckDuckBot-Https/', 'HTTP Banner Detection', 'YandexImages/', 'archive.org_bot',
 		'ArchiveTeam ArchiveBot/', 'yacybot', 'https://developers.google.com/+/web/snippet/',
-		'Scrapy/', 'github-camo', 'MJ12bot/', 'DotBot/', 'Pinterestbot/', 'Jooblebot/',
+		'Scrapy/', 'MJ12bot/', 'DotBot/', 'Pinterestbot/', 'Jooblebot/',
 		'Cliqzbot/', 'YaK/', 'Mediatoolkitbot', 'Snacktory', 'FunWebProducts', 'oBot/',
 		'7Siters/', 'KOCMOHABT', 'Google-SearchByImage', 'FemtosearchBot/',
 		'HubSpot Crawler', 'DomainStatsBot/', 'Re-re Studio', 'AwarioSmartBot/',
 		'SummalyBot/', 'DNSResearchBot/', 'PetalBot;', 'Nmap Scripting Engine;',
 		'Google-Apps-Script; beanserver;', 'woorankreview/', 'Seekport Crawler;', 'AHC/',
-		'SkypeUriPreview Preview/', 'Semanticbot/', 'Embed PHP library', 'XoviOnpageCrawler;',
+		'Semanticbot/', 'Embed PHP library', 'XoviOnpageCrawler;', 'Pinterest/',
 		'GetHPinfo.com-Bot/', 'BoardReader Favicon Fetcher', 'Google-Adwords-Instant', 'newspaper/',
-		'YurichevBot/', 'Crawling at Home Project', 'InfoTigerBot/'
+		'YurichevBot/', 'Crawling at Home Project', 'InfoTigerBot/',
+		'AdIdxBot/', 'MicrosoftPreview/', 'masscan/'
 	];
 
 	if (!DI::config()->get('blockbot', 'good_crawlers')) {
@@ -93,13 +102,23 @@ function blockbot_init_1()
 		}
 	}
 
+	if (!DI::config()->get('blockbot', 'socialmedia_agents')) {
+		$agents = array_merge($agents, $socialmedia_agents);
+	} else {
+		foreach ($socialmedia_agents as $socialmedia_agent) {
+			if (stristr($_SERVER['HTTP_USER_AGENT'], $socialmedia_agent)) {
+				return;
+			}
+		}
+	}
+
 	if (DI::config()->get('blockbot', 'block_gab')) {
 		$agents[] = 'GabSocial/';
 	}
 
 	foreach ($agents as $agent) {
 		if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
-			throw new ForbiddenException('Bots are not allowed');
+			throw new ForbiddenException('Bots are not allowed. If you consider this a mistake, create an issue at https://github.com/friendica/friendica');
 		}
 	}
 
@@ -125,7 +144,7 @@ function blockbot_init_1()
 		'lua-resty-http/', 'Tiny Tiny RSS/', 'Wget/', 'PostmanRuntime/',
 		'W3C_Validator/', 'NetNewsWire', 'FeedValidator/', 'theoldreader.com', 'axios/',
 		'Paw/', 'PeerTube/', 'fedi.inex.dev', 'FediDB/', 'index.community crawler',
-		'Slackbot-LinkExpanding'
+		'Slackbot-LinkExpanding', 'Firefish/', 'Takahe/', 'Akkoma ', 'Misskey/'
 	];
 
 	if (DI::config()->get('blockbot', 'good_crawlers')) {
@@ -140,5 +159,5 @@ function blockbot_init_1()
 	}
 
 	logger::notice('Blocked bot', $logdata);
-	throw new ForbiddenException('Bots are not allowed');
+	throw new ForbiddenException('Bots are not allowed. If you consider this a mistake, create an issue at https://github.com/friendica/friendica');
 }

blockbot/lang/C/messages.po

@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2021-12-13 06:17+0000\n"
+"POT-Creation-Date: 2024-03-04 05:35+0000\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language-Team: LANGUAGE <LL@li.org>\n"
@@ -32,21 +32,31 @@ msgid ""
 msgstr ""
 
 #: blockbot.php:32
-msgid "Block GabSocial"
+msgid "Allow preview agents"
 msgstr ""
 
 #: blockbot.php:32
 msgid ""
+"Don't block agents from social media systems that want to generate preview "
+"data for links that had been set by their users."
+msgstr ""
+
+#: blockbot.php:33
+msgid "Block GabSocial"
+msgstr ""
+
+#: blockbot.php:33
+msgid ""
 "Block the software GabSocial. This will block every access for that "
 "software. You can block dedicated gab instances in the blocklist settings in "
 "the admin section."
 msgstr ""
 
-#: blockbot.php:33
+#: blockbot.php:34
 msgid "Training mode"
 msgstr ""
 
-#: blockbot.php:33
+#: blockbot.php:34
 msgid ""
 "Activates the training mode. This is only meant for developing purposes. "
 "Don't activate this on a production machine. This can cut communication with "

blockbot/templates/admin.tpl

@@ -1,4 +1,5 @@
 {{include file="field_checkbox.tpl" field=$good_crawlers}}
+{{include file="field_checkbox.tpl" field=$socialmedia_agents}}
 {{include file="field_checkbox.tpl" field=$block_gab}}
 {{include file="field_checkbox.tpl" field=$training}}
 <div class="submit"><button type="submit" class="btn btn-primary" name="page_site" value="{{$submit}}">{{$submit}}</button></div>