friendica
/
friendica-addons
mirror of https://git.friendi.ca/friendica/friendica-addons.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Merge pull request 'Blockbot: Misskey-Crawler added' (#1476) from heluecht/friendica-addons:blockbot into 2024.03-rc 

Reviewed-on: https://git.friendi.ca/friendica/friendica-addons/pulls/1476
pull/1478/head
Tobias Diekershoff 2024-03-04 16:32:29 +01:00
parent 6e355979e8 a05e429470
commit ed641e6ccb
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
blockbot/blockbot.php
View File

@ -51,7 +51,7 @@ 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 // List of "good" crawlers, mostly from the fediverse.
$good_agents = [ $good_agents = [
'fediverse.space crawler', 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0', 'fediverse.space crawler', 'fediverse.network crawler', 'Active_Pods_CheckBot_3.0',
'Social-Relay/', 'Test Certificate Info', 'Uptimebot/', 'GNUSocialBot', 'UptimeRobot/', 'Social-Relay/', 'Test Certificate Info', 'Uptimebot/', 'GNUSocialBot', 'UptimeRobot/',
@ -59,10 +59,10 @@ function blockbot_init_1()
'FedditLemmyverseCrawler/', 'kbinBot/', 'lemmy-explorer-crawler/', 'FedditLemmyverseCrawler/', 'kbinBot/', 'lemmy-explorer-crawler/',
]; ];
// List of agents from social media systems that fetch preview data via opem graph or twitter cards // List of agents from social media systems that fetch preview data via opem graph or twitter cards.
$socialmedia_agents = ['Twitterbot/', 'facebookexternalhit/', 'SkypeUriPreview Preview/', $socialmedia_agents = ['Twitterbot/', 'facebookexternalhit/', 'SkypeUriPreview Preview/',
'TelegramBot', 'WhatsApp/', 'github-camo', 'Bluesky Cardyb/', 'XING-contenttabreceiver/', 'TelegramBot', 'WhatsApp/', 'github-camo', 'Bluesky Cardyb/', 'XING-contenttabreceiver/',
'LinkedInBot/', 'Instagram ', 'Synapse (bot; ', 'Discordbot/']; 'LinkedInBot/', 'Instagram ', 'Synapse (bot; ', 'Discordbot/', 'SummalyBot/'];
// List of known unwanted crawlers. // List of known unwanted crawlers.
$agents = [ $agents = [
@ -84,7 +84,7 @@ function blockbot_init_1()
'Cliqzbot/', 'YaK/', 'Mediatoolkitbot', 'Snacktory', 'FunWebProducts', 'oBot/', 'Cliqzbot/', 'YaK/', 'Mediatoolkitbot', 'Snacktory', 'FunWebProducts', 'oBot/',
'7Siters/', 'KOCMOHABT', 'Google-SearchByImage', 'FemtosearchBot/', '7Siters/', 'KOCMOHABT', 'Google-SearchByImage', 'FemtosearchBot/',
'HubSpot Crawler', 'DomainStatsBot/', 'Re-re Studio', 'AwarioSmartBot/', 'HubSpot Crawler', 'DomainStatsBot/', 'Re-re Studio', 'AwarioSmartBot/',
'SummalyBot/', '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/', 'Embed PHP library', 'XoviOnpageCrawler;', 'Pinterest/',
'GetHPinfo.com-Bot/', 'BoardReader Favicon Fetcher', 'Google-Adwords-Instant', 'newspaper/', 'GetHPinfo.com-Bot/', 'BoardReader Favicon Fetcher', 'Google-Adwords-Instant', 'newspaper/',