revi/sandbox
1
0
Fork 0
Code Issues Wiki Activity

robots.txt: shorten some links

Browse source 
Summary:
Less size /shrug

Signed-off-by: Yongmin Hong <revi@omglol.email>

Test Plan: try visiting URLs to test redirection

Reviewers: O1 revi & automations, revi

Reviewed By: O1 revi & automations, revi

Differential Revision: https://issuetracker.revi.xyz/D66
This commit is contained in:
revi 2024-05-10 18:18:36 +09:00
parent 1fc290faa5
commit a257d3ccb4
Signed by: revi
GPG key ID: 1EB4F6CEEA100E94
1 changed files with 8 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
PhabExt/PhabricatorCustomRobotsTxtController.php
View file

@ -1,4 +1,6 @@
<?php
// Copyright (C) 2024 Hong Yongmin <https://revi.xyz/>
// SPDX-License-Identifier: Apache-2.0
abstract class PhabricatorRobotsController extends PhabricatorController {
@ -16,8 +18,8 @@ public function processRequest() {
$out[] = '# Adapted from phabricator.wikimedia.org, we.phorge.it';
// Version timestamp is when I started editing them.
// Edit setLastModified at the bottom as well.
// Calculate EpochTime via go/ZoneStamp
$out[] = '# version: 20240502T184200+0900';
// Calculate EpochTime via go/epoch
$out[] = '# version: 20240509T235513+0900';
$out[] = '# also at https://github.com/revi/sandbox.git';
$out[] = 'User-Agent: *';
$out[] = 'Disallow: /diffusion/';
@ -59,7 +61,7 @@ public function processRequest() {
$out[] = 'Disallow: /p/';
// Phorge specific entries end here.
$out[] = '# This is cloudflare endpoint';
$out[] = '# Ref: https://developers.cloudflare.com/fundamentals/reference/cdn-cgi-endpoint/';
$out[] = '# Ref: https://issuetracker.revi.xyz/u/cloudflarecdncgi';
$out[] = 'Disallow: /cdn-cgi/';
$out[] = '# Google Ads are not welcome';
$out[] = 'User-agent: Mediapartners-Google';
@ -77,7 +79,7 @@ public function processRequest() {
$out[] = 'User-agent: GPTBot';
$out[] = 'Disallow: /';
$out[] = '# Google Gemini AI Crawlers are also not welcome';
$out[] = '# Ref: https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers?hl=en#google-extended';
$out[] = '# Ref: https://issuetracker.revi.xyz/u/googleextended';
$out[] = 'User-agent: Google-Extended';
$out[] = 'Disallow: /';
$out[] = '# CCBot (ab)used to train LLMs';
@ -89,7 +91,7 @@ public function processRequest() {
$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[] = '# Ref https://issuetracker.revi.xyz/u/robotstxtdiffbot';
$out[] = 'User-agent: Diffbot';
$out[] = 'Disallow: /';
$out[] = '# Bytespider';
@ -107,6 +109,6 @@ public function processRequest() {
->setContent($content)
->setCacheDurationInSeconds(phutil_units('2 hours in seconds'))
->setCanCDN(true)
->setLastModified(1714642920);
->setLastModified(1715266513);
}
}