mirror of
https://github.com/neocities/neocities.git
synced 2025-08-07 10:05:02 +02:00
48 lines
1.3 KiB
Text
48 lines
1.3 KiB
Text
# This file tells search engines and bots what they are allowed to see on your site.
|
|
|
|
# This is the default rule, which allows search engines to crawl your site (recommended).
|
|
User-agent: *
|
|
Allow: /
|
|
|
|
# If you do not want AI bots to crawl your site, remove the # from the following lines:
|
|
#User-agent: AI2Bot
|
|
#User-agent: Ai2Bot-Dolma
|
|
#User-agent: Amazonbot
|
|
#User-agent: anthropic-ai
|
|
#User-agent: Applebot-Extended
|
|
#User-agent: Bytespider
|
|
#User-agent: CCBot
|
|
#User-agent: ChatGPT-User
|
|
#User-agent: Claude-Web
|
|
#User-agent: ClaudeBot
|
|
#User-agent: cohere-ai
|
|
#User-agent: Diffbot
|
|
#User-agent: DuckAssistBot
|
|
#User-agent: FacebookBot
|
|
#User-agent: FriendlyCrawler
|
|
#User-agent: Google-Extended
|
|
#User-agent: GoogleOther
|
|
#User-agent: GoogleOther-Image
|
|
#User-agent: GoogleOther-Video
|
|
#User-agent: GPTBot
|
|
#User-agent: iaskspider/2.0
|
|
#User-agent: ICC-Crawler
|
|
#User-agent: ImagesiftBot
|
|
#User-agent: img2dataset
|
|
#User-agent: ISSCyberRiskCrawler
|
|
#User-agent: Kangaroo Bot
|
|
#User-agent: Meta-ExternalAgent
|
|
#User-agent: Meta-ExternalFetcher
|
|
#User-agent: OAI-SearchBot
|
|
#User-agent: omgili
|
|
#User-agent: omgilibot
|
|
#User-agent: PanguBot
|
|
#User-agent: PerplexityBot
|
|
#User-agent: PetalBot
|
|
#User-agent: Scrapy
|
|
#User-agent: Sidetrade indexer bot
|
|
#User-agent: Timpibot
|
|
#User-agent: VelenPublicWebCrawler
|
|
#User-agent: Webzio-Extended
|
|
#User-agent: YouBot
|
|
#Disallow: /
|