thepaperpilot/pages
1
0
Fork 0
Code Issues 1 Pull requests 1 Projects Releases Packages Wiki Activity Actions

Update robots.txt
All checks were successful
Build and Deploy / build-and-deploy (push) Successful in 1m0s
Details

Browse source
This commit is contained in:
thepaperpilot 2024-06-28 08:57:44 -05:00
parent cc50a62afe
commit d993416154
1 changed files with 4 additions and 118 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

122
site/public/robots.txt
View file

@ -3,8 +3,8 @@ User-agent: Google-Extended
Disallow: / Disallow: /
# Google # Google
User-agent: Googlebot #User-agent: Googlebot
Disallow: / #Disallow: /
User-agent: GoogleOther User-agent: GoogleOther
Disallow: / Disallow: /
@ -16,122 +16,8 @@ User-agent: AdsBot-Google
Disallow: / Disallow: /
# Bing # Bing
User-agent: bingbot #User-agent: bingbot
Disallow: / #Disallow: /
# Common Crawl
User-agent: CCBot
Disallow: /
# OpenAI
User-agent: ChatGPT-User
Disallow: /
User-agent: ChatGPT
Disallow: /
User-agent: GPTBot
Disallow: /
# Omgili
User-agent: Omgilibot
Disallow: /
User-agent: Omgili
Disallow: /
# Facebook AI
User-agent: FacebookBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: ClaudeBot
Disallow: /
# Other AI training known or suspected
User-agent: anthropic-ai
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: The Knowledge AI
Disallow: /
User-agent: aiHitBot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: YouBot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
# Siri and Alexa yuck
User-agent: Amazonbot
Disallow: /
User-agent: Applebot
Disallow: /
# Miscellaneous
User-agent: TurnitinBot
Disallow: /
User-agent: NPBot
Disallow: /
User-agent: SlySearch
Disallow: /
User-agent: 360Spider
Disallow: /
User-agent: netEstate NE Crawler
Disallow: /
User-agent: Pinterestbot
Disallow: /
# Block all crawlers from login and admin section
User-agent: *
Disallow: /wp-login.php
Disallow: /wp-admin/
Disallow: /cgi-bin/
Disallow: /trackback/
Allow: /wp-admin/admin-ajax.php
Sitemap: https://tracydurnell.com/wp-sitemap.xml# Google AI
User-agent: Google-Extended
Disallow: /
# Google
User-agent: Googlebot
Disallow: /
User-agent: GoogleOther
Disallow: /
User-agent: Googlebot-Image
Disallow: /
User-agent: AdsBot-Google
Disallow: /
# Bing
User-agent: bingbot
Disallow: /
# Common Crawl # Common Crawl
User-agent: CCBot User-agent: CCBot