Blockbot: HTTP library section added

This commit is contained in:
Michael 2024-03-05 04:54:36 +00:00 committed by Tobias Diekershoff
parent ed641e6ccb
commit 0751b2ac16
3 changed files with 74 additions and 55 deletions

View file

@ -30,6 +30,7 @@ function blockbot_addon_admin(string &$o)
'$submit' => DI::l10n()->t('Save Settings'), '$submit' => DI::l10n()->t('Save Settings'),
'$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.")], '$good_crawlers' => ['good_crawlers', DI::l10n()->t('Allow "good" crawlers'), DI::config()->get('blockbot', 'good_crawlers'), DI::l10n()->t("Don't block fediverse crawlers, relay servers and other bots with good purposes.")],
'$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.")], '$socialmedia_agents' => ['socialmedia_agents', DI::l10n()->t('Allow preview agents'), DI::config()->get('blockbot', 'socialmedia_agents'), DI::l10n()->t("Don't block agents from social media systems that want to generate preview data for links that had been set by their users.")],
'$http_libraries' => ['http_libraries', DI::l10n()->t('Allow generic HTTP libraries'), DI::config()->get('blockbot', 'http_libraries'), DI::l10n()->t("Don't block agents from generic HTTP libraries that could be used for good or for bad and that currently can't be traced back to any known Fediverse project.")],
'$block_gab' => ['block_gab', DI::l10n()->t('Block GabSocial'), DI::config()->get('blockbot', 'block_gab'), DI::l10n()->t('Block the software GabSocial. This will block every access for that software. You can block dedicated gab instances in the blocklist settings in the admin section.')], '$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.')],
'$training' => ['training', DI::l10n()->t('Training mode'), DI::config()->get('blockbot', 'training'), DI::l10n()->t("Activates the training mode. This is only meant for developing purposes. Don't activate this on a production machine. This can cut communication with some systems.")], '$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.")],
]); ]);
@ -39,6 +40,7 @@ function blockbot_addon_admin_post()
{ {
DI::config()->set('blockbot', 'good_crawlers', $_POST['good_crawlers'] ?? false); DI::config()->set('blockbot', 'good_crawlers', $_POST['good_crawlers'] ?? false);
DI::config()->set('blockbot', 'socialmedia_agents', $_POST['socialmedia_agents'] ?? false); DI::config()->set('blockbot', 'socialmedia_agents', $_POST['socialmedia_agents'] ?? false);
DI::config()->set('blockbot', 'http_libraries', $_POST['http_libraries'] ?? false);
DI::config()->set('blockbot', 'block_gab', $_POST['block_gab'] ?? false); DI::config()->set('blockbot', 'block_gab', $_POST['block_gab'] ?? false);
DI::config()->set('blockbot', 'training', $_POST['training'] ?? false); DI::config()->set('blockbot', 'training', $_POST['training'] ?? false);
} }
@ -51,19 +53,6 @@ function blockbot_init_1()
$logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']]; $logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']];
// List of "good" crawlers, mostly from the fediverse.
$good_agents = [
'fediverse.space crawler', 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0',
'Social-Relay/', 'Test Certificate Info', 'Uptimebot/', 'GNUSocialBot', 'UptimeRobot/',
'PTST/', 'Zabbix', 'Poduptime/', 'FediFetcher', 'lemmy-stats-crawler',
'FedditLemmyverseCrawler/', 'kbinBot/', 'lemmy-explorer-crawler/',
];
// 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/', 'SummalyBot/'];
// List of known unwanted crawlers. // List of known unwanted crawlers.
$agents = [ $agents = [
'SemrushBot', 's~feedly-nikon3', 'Qwantify/Bleriot/', 'ltx71', 'Sogou web spider/', 'SemrushBot', 's~feedly-nikon3', 'Qwantify/Bleriot/', 'ltx71', 'Sogou web spider/',
@ -86,40 +75,53 @@ function blockbot_init_1()
'HubSpot Crawler', 'DomainStatsBot/', 'Re-re Studio', 'AwarioSmartBot/', 'HubSpot Crawler', 'DomainStatsBot/', 'Re-re Studio', 'AwarioSmartBot/',
'DNSResearchBot/', 'PetalBot;', 'Nmap Scripting Engine;', 'DNSResearchBot/', 'PetalBot;', 'Nmap Scripting Engine;',
'Google-Apps-Script; beanserver;', 'woorankreview/', 'Seekport Crawler;', 'AHC/', 'Google-Apps-Script; beanserver;', 'woorankreview/', 'Seekport Crawler;', 'AHC/',
'Semanticbot/', 'Embed PHP library', 'XoviOnpageCrawler;', 'Pinterest/', 'Semanticbot/', 'XoviOnpageCrawler;', 'Pinterest/',
'GetHPinfo.com-Bot/', 'BoardReader Favicon Fetcher', 'Google-Adwords-Instant', 'newspaper/', 'GetHPinfo.com-Bot/', 'BoardReader Favicon Fetcher', 'Google-Adwords-Instant', 'newspaper/',
'YurichevBot/', 'Crawling at Home Project', 'InfoTigerBot/', 'YurichevBot/', 'Crawling at Home Project', 'InfoTigerBot/', 'AdIdxBot/',
'AdIdxBot/', 'MicrosoftPreview/', 'masscan/' 'MicrosoftPreview/', 'masscan/', 'Timpibot/', 'everyfeed-spider/', 'AndroidDownloadManager/',
'WebZIP/', 'WDG_Validator/', 'Screaming Frog SEO Spider/', ' Bytespider;', 'ISSCyberRiskCrawler/',
]; ];
if (!DI::config()->get('blockbot', 'good_crawlers')) {
$agents = array_merge($agents, $good_agents);
} else {
foreach ($good_agents as $good_agent) {
if (stristr($_SERVER['HTTP_USER_AGENT'], $good_agent)) {
return;
}
}
}
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')) { if (DI::config()->get('blockbot', 'block_gab')) {
$agents[] = 'GabSocial/'; $agents[] = 'GabSocial/';
} }
foreach ($agents as $agent) { // List of "good" crawlers, mostly from the fediverse.
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) { $good_agents = [
throw new ForbiddenException('Bots are not allowed. If you consider this a mistake, create an issue at https://github.com/friendica/friendica'); 'fediverse.space crawler', 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0',
'Social-Relay/', 'Test Certificate Info', 'Uptimebot/', 'GNUSocialBot', 'UptimeRobot/',
'PTST/', 'Zabbix', 'Poduptime/', 'FediFetcher', 'lemmy-stats-crawler',
'FedditLemmyverseCrawler/', 'kbinBot/', 'lemmy-explorer-crawler/',
];
if (!DI::config()->get('blockbot', 'good_crawlers')) {
$agents = array_merge($agents, $good_agents);
} elseif (blockbot_match($good_agents)) {
return;
} }
// 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/', 'SummalyBot/'];
if (!DI::config()->get('blockbot', 'socialmedia_agents')) {
$agents = array_merge($agents, $socialmedia_agents);
} elseif (blockbot_match($socialmedia_agents)) {
return;
}
// HTTP Libraries
$http_libraries = ['ReactorNetty/', 'GuzzleHttp/', 'Embed PHP library', 'python-urllib3/'];
if (!DI::config()->get('blockbot', 'http_libraries')) {
$agents = array_merge($agents, $http_libraries);
} elseif (blockbot_match($http_libraries)) {
return;
}
if (blockbot_match($agents)) {
throw new ForbiddenException('Bots are not allowed. If you consider this a mistake, create an issue at https://github.com/friendica/friendica');
} }
// This switch here is only meant for developers who want to add more bots to the list above, it is not safe for production. // This switch here is only meant for developers who want to add more bots to the list above, it is not safe for production.
@ -134,7 +136,7 @@ function blockbot_init_1()
return; return;
} }
// List of false positives' strings of known "good" agents. // List of known "good" agents, mostly used by Fediverse systems, feed readers, ...
$agents = [ $agents = [
'curl', 'zgrab', 'Go-http-client', 'curb', 'github.com', 'reqwest', 'Feedly/', 'curl', 'zgrab', 'Go-http-client', 'curb', 'github.com', 'reqwest', 'Feedly/',
'Python-urllib/', 'Liferea/', 'aiohttp/', 'WordPress.com Reader', 'hackney/', 'Python-urllib/', 'Liferea/', 'aiohttp/', 'WordPress.com Reader', 'hackney/',
@ -144,20 +146,25 @@ function blockbot_init_1()
'lua-resty-http/', 'Tiny Tiny RSS/', 'Wget/', 'PostmanRuntime/', 'lua-resty-http/', 'Tiny Tiny RSS/', 'Wget/', 'PostmanRuntime/',
'W3C_Validator/', 'NetNewsWire', 'FeedValidator/', 'theoldreader.com', 'axios/', 'W3C_Validator/', 'NetNewsWire', 'FeedValidator/', 'theoldreader.com', 'axios/',
'Paw/', 'PeerTube/', 'fedi.inex.dev', 'FediDB/', 'index.community crawler', 'Paw/', 'PeerTube/', 'fedi.inex.dev', 'FediDB/', 'index.community crawler',
'Slackbot-LinkExpanding', 'Firefish/', 'Takahe/', 'Akkoma ', 'Misskey/' 'Slackbot-LinkExpanding', 'Firefish/', 'Takahe/', 'Akkoma ', 'Misskey/', 'Lynx/',
'camo-rs asset proxy',
]; ];
if (DI::config()->get('blockbot', 'good_crawlers')) { if (blockbot_match($agents)) {
$agents = array_merge($agents, $good_agents);
}
foreach ($agents as $agent) {
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
logger::info('False positive', $logdata); logger::info('False positive', $logdata);
return; return;
} }
}
logger::notice('Blocked bot', $logdata); logger::notice('Blocked bot', $logdata);
throw new ForbiddenException('Bots are not allowed. If you consider this a mistake, create an issue at https://github.com/friendica/friendica'); throw new ForbiddenException('Bots are not allowed. If you consider this a mistake, create an issue at https://github.com/friendica/friendica');
} }
function blockbot_match(array $agents)
{
foreach ($agents as $agent) {
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
return true;
}
}
return false;
}

View file

@ -8,7 +8,7 @@ msgid ""
msgstr "" msgstr ""
"Project-Id-Version: \n" "Project-Id-Version: \n"
"Report-Msgid-Bugs-To: \n" "Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2024-03-04 05:35+0000\n" "POT-Creation-Date: 2024-03-05 04:51+0000\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <LL@li.org>\n" "Language-Team: LANGUAGE <LL@li.org>\n"
@ -42,21 +42,32 @@ msgid ""
msgstr "" msgstr ""
#: blockbot.php:33 #: blockbot.php:33
msgid "Block GabSocial" msgid "Allow generic HTTP libraries"
msgstr "" msgstr ""
#: blockbot.php:33 #: blockbot.php:33
msgid "" msgid ""
"Don't block agents from generic HTTP libraries that could be used for good "
"or for bad and that currently can't be traced back to any known Fediverse "
"project."
msgstr ""
#: blockbot.php:34
msgid "Block GabSocial"
msgstr ""
#: blockbot.php:34
msgid ""
"Block the software GabSocial. This will block every access for that " "Block the software GabSocial. This will block every access for that "
"software. You can block dedicated gab instances in the blocklist settings in " "software. You can block dedicated gab instances in the blocklist settings in "
"the admin section." "the admin section."
msgstr "" msgstr ""
#: blockbot.php:34 #: blockbot.php:35
msgid "Training mode" msgid "Training mode"
msgstr "" msgstr ""
#: blockbot.php:34 #: blockbot.php:35
msgid "" msgid ""
"Activates the training mode. This is only meant for developing purposes. " "Activates the training mode. This is only meant for developing purposes. "
"Don't activate this on a production machine. This can cut communication with " "Don't activate this on a production machine. This can cut communication with "

View file

@ -1,5 +1,6 @@
{{include file="field_checkbox.tpl" field=$good_crawlers}} {{include file="field_checkbox.tpl" field=$good_crawlers}}
{{include file="field_checkbox.tpl" field=$socialmedia_agents}} {{include file="field_checkbox.tpl" field=$socialmedia_agents}}
{{include file="field_checkbox.tpl" field=$http_libraries}}
{{include file="field_checkbox.tpl" field=$block_gab}} {{include file="field_checkbox.tpl" field=$block_gab}}
{{include file="field_checkbox.tpl" field=$training}} {{include file="field_checkbox.tpl" field=$training}}
<div class="submit"><button type="submit" class="btn btn-primary" name="page_site" value="{{$submit}}">{{$submit}}</button></div> <div class="submit"><button type="submit" class="btn btn-primary" name="page_site" value="{{$submit}}">{{$submit}}</button></div>