mirror of
https://git.friendi.ca/friendica/friendica-addons.git
synced 2024-11-25 21:53:19 +00:00
Merge pull request #871 from annando/block-config
Admin config setting added for blockbot, added option to block gabsocial
This commit is contained in:
commit
ee8f0f8bd7
2 changed files with 46 additions and 6 deletions
|
@ -2,8 +2,9 @@
|
||||||
/**
|
/**
|
||||||
* Name: blockbot
|
* Name: blockbot
|
||||||
* Description: Blocking bots based on detecting bots/crawlers/spiders via the user agent and http_from header.
|
* Description: Blocking bots based on detecting bots/crawlers/spiders via the user agent and http_from header.
|
||||||
* Version: 0.1
|
* Version: 0.2
|
||||||
* Author: Philipp Holzer <admin@philipp.info>
|
* Author: Philipp Holzer <admin@philipp.info>
|
||||||
|
* Author: Michael Vogel <https://pirati.ca/profile/heluecht>
|
||||||
*
|
*
|
||||||
*/
|
*/
|
||||||
|
|
||||||
|
@ -13,6 +14,8 @@ use Friendica\Core\Hook;
|
||||||
use Friendica\Core\System;
|
use Friendica\Core\System;
|
||||||
use Jaybizzle\CrawlerDetect\CrawlerDetect;
|
use Jaybizzle\CrawlerDetect\CrawlerDetect;
|
||||||
use Friendica\Core\Logger;
|
use Friendica\Core\Logger;
|
||||||
|
use Friendica\Core\Renderer;
|
||||||
|
use Friendica\Core\L10n;
|
||||||
|
|
||||||
require_once __DIR__ . DIRECTORY_SEPARATOR . 'vendor' . DIRECTORY_SEPARATOR . 'autoload.php';
|
require_once __DIR__ . DIRECTORY_SEPARATOR . 'vendor' . DIRECTORY_SEPARATOR . 'autoload.php';
|
||||||
|
|
||||||
|
@ -25,6 +28,24 @@ function blockbot_uninstall() {
|
||||||
Hook::unregister('init_1', __FILE__, 'blockbot_init_1');
|
Hook::unregister('init_1', __FILE__, 'blockbot_init_1');
|
||||||
}
|
}
|
||||||
|
|
||||||
|
function blockbot_addon_admin(&$a, &$o) {
|
||||||
|
$t = Renderer::getMarkupTemplate("admin.tpl", "addon/blockbot/");
|
||||||
|
|
||||||
|
$o = Renderer::replaceMacros($t, [
|
||||||
|
'$submit' => L10n::t('Save Settings'),
|
||||||
|
'$good_crawlers' => ['good_crawlers', L10n::t('Allow "good" crawlers'), Config::get('blockbot', 'good_crawlers'), "Don't block fediverse crawlers, relay servers and other bots with good purposes."],
|
||||||
|
'$block_gab' => ['block_gab', L10n::t('Block GabSocial'), Config::get('blockbot', 'block_gab'), 'Block the software GabSocial. This will block every access for that software. You can block dedicated gab instances in the blocklist settings in the admin section.'],
|
||||||
|
'$training' => ['training', L10n::t('Training mode'), Config::get('blockbot', 'training'), "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."],
|
||||||
|
]);
|
||||||
|
}
|
||||||
|
|
||||||
|
function blockbot_addon_admin_post(&$a) {
|
||||||
|
Config::set('blockbot', 'good_crawlers', $_POST['good_crawlers'] ?? false);
|
||||||
|
Config::set('blockbot', 'block_gab', $_POST['block_gab'] ?? false);
|
||||||
|
Config::set('blockbot', 'training', $_POST['training'] ?? false);
|
||||||
|
info(L10n::t('Settings updated.'). EOL);
|
||||||
|
}
|
||||||
|
|
||||||
function blockbot_init_1(App $a) {
|
function blockbot_init_1(App $a) {
|
||||||
if (empty($_SERVER['HTTP_USER_AGENT'])) {
|
if (empty($_SERVER['HTTP_USER_AGENT'])) {
|
||||||
return;
|
return;
|
||||||
|
@ -32,6 +53,10 @@ function blockbot_init_1(App $a) {
|
||||||
|
|
||||||
$logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']];
|
$logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']];
|
||||||
|
|
||||||
|
// List of "good" crawlers
|
||||||
|
$good_agents = ['fediverse.space crawler', 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0',
|
||||||
|
'Social-Relay/', 'Test Certificate Info', 'Uptimebot/'];
|
||||||
|
|
||||||
// List of known crawlers.
|
// List of known crawlers.
|
||||||
$agents = ['SemrushBot', 's~feedly-nikon3', 'Qwantify/Bleriot/', 'ltx71', 'Sogou web spider/',
|
$agents = ['SemrushBot', 's~feedly-nikon3', 'Qwantify/Bleriot/', 'ltx71', 'Sogou web spider/',
|
||||||
'Diffbot/', 'Twitterbot/', 'YisouSpider', 'evc-batch/', 'LivelapBot/', 'TrendsmapResolver/',
|
'Diffbot/', 'Twitterbot/', 'YisouSpider', 'evc-batch/', 'LivelapBot/', 'TrendsmapResolver/',
|
||||||
|
@ -49,7 +74,15 @@ function blockbot_init_1(App $a) {
|
||||||
'ArchiveTeam ArchiveBot/', 'yacybot', 'https://developers.google.com/+/web/snippet/',
|
'ArchiveTeam ArchiveBot/', 'yacybot', 'https://developers.google.com/+/web/snippet/',
|
||||||
'Scrapy/', 'github-camo', 'MJ12bot/', 'DotBot/', 'Pinterestbot/', 'Jooblebot/',
|
'Scrapy/', 'github-camo', 'MJ12bot/', 'DotBot/', 'Pinterestbot/', 'Jooblebot/',
|
||||||
'Cliqzbot/', 'YaK/', 'Mediatoolkitbot', 'Snacktory', 'FunWebProducts', 'oBot/',
|
'Cliqzbot/', 'YaK/', 'Mediatoolkitbot', 'Snacktory', 'FunWebProducts', 'oBot/',
|
||||||
'7Siters/'];
|
'7Siters/', 'KOCMOHABT', 'Google-SearchByImage'];
|
||||||
|
|
||||||
|
if (!Config::get('blockbot', 'good_crawlers')) {
|
||||||
|
$agents = array_merge($agents, $good_agents);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (Config::get('blockbot', 'block_gab')) {
|
||||||
|
$agents[] = 'GabSocial/';
|
||||||
|
}
|
||||||
|
|
||||||
foreach ($agents as $agent) {
|
foreach ($agents as $agent) {
|
||||||
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
|
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
|
||||||
|
@ -70,13 +103,16 @@ function blockbot_init_1(App $a) {
|
||||||
}
|
}
|
||||||
|
|
||||||
// List of false positives' strings of known "good" agents.
|
// List of false positives' strings of known "good" agents.
|
||||||
$agents = ['fediverse.network crawler', 'Active_Pods_CheckBot_3.0', 'Social-Relay/',
|
$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/',
|
||||||
'Faraday v', 'okhttp', 'UniversalFeedParser', 'PixelFedBot', 'python-requests',
|
'Faraday v', 'okhttp', 'UniversalFeedParser', 'PixelFedBot', 'python-requests',
|
||||||
'WordPress/', 'http.rb/', 'Apache-HttpClient/', 'WordPress.com;', 'Pleroma',
|
'WordPress/', 'http.rb/', 'Apache-HttpClient/', 'WordPress.com;', 'Pleroma',
|
||||||
'Dispatch/', 'Ruby', 'Uptimebot/', 'Java/', 'libwww-perl/', 'Mastodon/',
|
'Dispatch/', 'Ruby', 'Java/', 'libwww-perl/', 'Mastodon/',
|
||||||
'lua-resty-http/', 'Test Certificate Info'];
|
'lua-resty-http/'];
|
||||||
|
|
||||||
|
if (Config::get('blockbot', 'good_crawlers')) {
|
||||||
|
$agents = array_merge($agents, $good_agents);
|
||||||
|
}
|
||||||
|
|
||||||
foreach ($agents as $agent) {
|
foreach ($agents as $agent) {
|
||||||
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
|
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
|
||||||
|
|
4
blockbot/templates/admin.tpl
Normal file
4
blockbot/templates/admin.tpl
Normal file
|
@ -0,0 +1,4 @@
|
||||||
|
{{include file="field_checkbox.tpl" field=$good_crawlers}}
|
||||||
|
{{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>
|
Loading…
Reference in a new issue