71 lines
1.7 KiB
Text
71 lines
1.7 KiB
Text
# Modified GoToSocial robots.txt
|
|
|
|
# AI scrapers and the like.
|
|
# https://github.com/ai-robots-txt/ai.robots.txt/
|
|
User-agent: AI2Bot
|
|
User-agent: Ai2Bot-Dolma
|
|
User-agent: Amazonbot
|
|
User-agent: anthropic-ai
|
|
User-agent: Applebot
|
|
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: cohere-training-data-crawler
|
|
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: SemrushBot
|
|
User-agent: Sidetrade indexer bot
|
|
User-agent: Timpibot
|
|
User-agent: VelenPublicWebCrawler
|
|
User-agent: Webzio-Extended
|
|
User-agent: YouBot
|
|
Disallow: /
|
|
|
|
# Marketing/SEO "intelligence" data scrapers
|
|
User-agent: AwarioRssBot
|
|
User-agent: AwarioSmartBot
|
|
User-agent: DataForSeoBot
|
|
User-agent: magpie-crawler
|
|
User-agent: Meltwater
|
|
User-agent: peer39_crawler
|
|
User-agent: peer39_crawler/1.0
|
|
User-agent: PiplBot
|
|
User-agent: scoop.it
|
|
User-agent: Seekr
|
|
Disallow: /
|
|
|
|
# Well-known.dev crawler. Indexes stuff under /.well-known.
|
|
# https://well-known.dev/about/
|
|
User-agent: WellKnownBot
|
|
Disallow: /
|
|
|
|
# Rules for everything else.
|
|
User-agent: *
|
|
Crawl-delay: 500
|
|
|