revi/sandbox
1
0
Fork 0
Code Issues Wiki Activity

PhabExt: add more domains

Browse source 
More LLM domains
Source: https://darkvisitors.com/docs/set-up-a-robots-txt

Bug: N/A
Signed-off-by: Yongmin Hong <revi@omglol.email>
This commit is contained in:
revi 2024-04-21 04:36:07 +09:00
parent 383155f51d
commit 59fb26f299
Signed by: revi
GPG key ID: 1EB4F6CEEA100E94
1 changed files with 19 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
PhabExt/PhabricatorCustomRobotsTxtController.php
View file

@ -11,7 +11,7 @@ public function processRequest() {
$out[] = '# Forked from phabricator.wikimedia.org, we.phorge.it'; $out[] = '# Forked from phabricator.wikimedia.org, we.phorge.it';
// Version timestamp is when I started editing them. // Version timestamp is when I started editing them.
$out[] = '# version: 20240417T011800+0900'; $out[] = '# version: 20240421T042000+0900';
$out[] = '# also at https://github.com/revi/sandbox.git'; $out[] = '# also at https://github.com/revi/sandbox.git';
$out[] = 'User-Agent: *'; $out[] = 'User-Agent: *';
$out[] = 'Disallow: /diffusion/'; $out[] = 'Disallow: /diffusion/';
@ -56,6 +56,8 @@ public function processRequest() {
$out[] = 'Disallow: /'; $out[] = 'Disallow: /';
$out[] = 'User-agent: AdsBot-Google-Mobile'; $out[] = 'User-agent: AdsBot-Google-Mobile';
$out[] = 'Disallow: /'; $out[] = 'Disallow: /';
// While I sometimes (borderline 'rare') use LLMs (GPT, Gemini, …), I'd rather prefer LLMs not use my stuff to profit
// Well I think my stuff is mostly out of interest for them, tho…
$out[] = '# ChatGPT Crawlers are not welcome'; $out[] = '# ChatGPT Crawlers are not welcome';
$out[] = '# Ref: https://platform.openai.com/docs/plugins/bot'; $out[] = '# Ref: https://platform.openai.com/docs/plugins/bot';
$out[] = 'User-agent: ChatGPT-User'; $out[] = 'User-agent: ChatGPT-User';
@ -66,6 +68,22 @@ public function processRequest() {
$out[] = '# Ref: https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers?hl=en#google-extended'; $out[] = '# Ref: https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers?hl=en#google-extended';
$out[] = 'User-agent: Google-Extended'; $out[] = 'User-agent: Google-Extended';
$out[] = 'Disallow: /'; $out[] = 'Disallow: /';
$out[] = '# CCBot (ab)used to train LLMs';
$out[] = '# Ref: https://darkvisitors.com/agents/ccbot';
$out[] = 'User-agent: CCBot';
$out[] = 'Disallow: /';
$out[] = '# Facebook LLM Bot';
$out[] = '# Ref: https://developers.facebook.com/docs/sharing/bot/';
$out[] = 'User-agent: FacebookBot';
$out[] = 'Disallow: /';
$out[] = '# DiffBot, though this one is known to have option to ignore robotstxt';
$out[] = '# Ref https://docs.diffbot.com/docs/why-is-my-crawl-not-crawling-and-other-uncommon-crawl-problems';
$out[] = 'User-agent: Diffbot';
$out[] = 'Disallow: /';
$out[] = '# Bytespider';
$out[] = '# Ref: https://darkvisitors.com/agents/bytespider';
$out[] = 'User-agent: Bytespider';
$out[] = 'Disallow: /';
// Crawl-delay entries at the bottom // Crawl-delay entries at the bottom
// Ref: https://github.com/otwcode/otwarchive/pull/4411#discussion_r1044351129 // Ref: https://github.com/otwcode/otwarchive/pull/4411#discussion_r1044351129
$out[] = 'User-agent: *'; $out[] = 'User-agent: *';