friendica/friendica-addons
7
2
Fork 14
Code Issues 3 Pull requests 3 Releases 16 Wiki Activity

Blockbot: Avoid false positives #849

Merged
annando merged 35 commits from false-positive into 2019.06-rc 2019-06-24 05:28:29 +02:00
Conversation 20 Commits 35 Files changed 2 +41 -13
1 changed files with 41 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files
Showing only changes of commit 89b9baf392 - Show all commits

52
blockbot/blockbot.php
View file

@ -27,23 +27,51 @@ function blockbot_uninstall() {
function blockbot_init_1(App $a) { function blockbot_init_1(App $a) {
$crawlerDetect = new CrawlerDetect(); $crawlerDetect = new CrawlerDetect();
// List of strings of known "good" agents $logdata = ['agent' => $_SERVER['HTTP_USER_AGENT'], 'uri' => $_SERVER['REQUEST_URI']];
$agents = ['diaspora-connection-tester', 'DiasporaFederation', 'Friendica', '(compatible; zot)',
'Micro.blog', 'Mastodon', 'hackney', 'GangGo', 'python/federation', 'GNU social', 'winHttp',
'Go-http-client', 'Mr.4x3 Powered', 'Test Certificate Info', 'WordPress.com', 'zgrab',
'curl/', 'StatusNet', 'OpenGraphReader/', 'Uptimebot/', 'python-opengraph-jaywink'];
if ($crawlerDetect->isCrawler()) { if (!$crawlerDetect->isCrawler()) {
logger::debug('Good user agent detected', $logdata);
return;
}
// List of strings of reported false positives
$agents = ['Mastodon', 'hackney', 'Faraday', 'okhttp', 'UniversalFeedParser', 'PixelFedBot', 'python-requests',
'WordPress'];
foreach ($agents as $agent) { foreach ($agents as $agent) {
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) { if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
// @ToDo: Report every false positive here: https://github.com/JayBizzle/Crawler-Detect/issues/326 // The agents had been reported to https://github.com/JayBizzle/Crawler-Detect/issues/
logger::notice('False positive', ['agent' => $_SERVER['HTTP_USER_AGENT']]); logger::notice('Already reported wrong detection', $logdata);
return; return;
} }
} }
logger::info('Blocked bot', ['agent' => $_SERVER['HTTP_USER_AGENT']]);
System::httpExit(403, 'Bots are not allowed'); // List of strings of known "good" agents
} else { $agents = ['diaspora-connection-tester', 'DiasporaFederation', 'Friendica', '(compatible; zot)',
logger::debug('Good user agent detected', ['agent' => $_SERVER['HTTP_USER_AGENT']]); 'Micro.blog', 'GangGo', 'python/federation', 'GNU social', 'winHttp',
'Go-http-client', 'Mr.4x3 Powered', 'Test Certificate Info', 'WordPress.com', 'zgrab',
'curl/', 'StatusNet', 'OpenGraphReader/', 'Uptimebot/', 'python-opengraph-jaywink',
'fediverse.network crawler', 'Active_Pods_CheckBot_3.0', 'Social-Relay'];
foreach ($agents as $agent) {
if (stristr($_SERVER['HTTP_USER_AGENT'], $agent)) {
// Report every false positive here: https://github.com/JayBizzle/Crawler-Detect/issues/
// After report move it into the array above
logger::notice('False positive', $logdata);
return;
} }
}
// List of known crawlers. They are added here to avoid having them logged at the end of the function.
// This helps to detect false positives
$agents = ['Mozilla/5.0 (compatible; SemrushBot/3~bl; +http://www.semrush.com/bot.html)', 'SEMrushBot',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36 AppEngine-Google; (+http://code.google.com/appengine; appid: s~feedly-nikon3)'];
foreach ($agents as $agent) {
if ($_SERVER['HTTP_USER_AGENT'] == $agent) {
System::httpExit(403, 'Bots are not allowed');
}
}
logger::info('Blocked bot', $logdata);
System::httpExit(403, 'Bots are not allowed');
} }