# 10gag.lol crawler policy
# Search engines and AI answer/search retrieval: allowed.
# AI model training / bulk dataset crawling: not allowed.
# Content-Signal: search=yes, ai-input=yes, ai-train=no

User-agent: *
Allow: /
Allow: /new
Allow: /trending
Allow: /top
Allow: /post/
Allow: /about
Allow: /alternatives-to-9gag
Allow: /sites-like-9gag
Allow: /ifunny-alternative
Allow: /embed
Allow: /new/page/
Allow: /top/page/
Allow: /templates
Allow: /template/
Allow: /memes
Allow: /meme-generator
Allow: /rage-comic-maker
Allow: /rage-faces
Allow: /rage-face/
Disallow: /api/
Disallow: /account
Disallow: /chat
Disallow: /blackjack
Disallow: /suggestions

# ---- AI training / dataset crawlers: blocked site-wide ----
User-agent: GPTBot
User-agent: CCBot
User-agent: Google-Extended
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: omgili
User-agent: omgilibot
User-agent: Webzio-Extended
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Timpibot
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: PanguBot
User-agent: Kangaroo Bot
User-agent: Sidetrade indexer bot
User-agent: VelenPublicWebCrawler
User-agent: iaskspider/2.0
User-agent: ISSCyberRiskCrawler
User-agent: Scrapy
Disallow: /

# ---- AI search / answer retrieval (user-triggered or search index): allowed like a search engine ----
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: YouBot
User-agent: Applebot
User-agent: Meta-ExternalFetcher
Allow: /
Disallow: /api/
Disallow: /account
Disallow: /chat
Disallow: /blackjack
Disallow: /suggestions

Sitemap: https://www.10gag.lol/sitemap_index.xml
Sitemap: https://www.10gag.lol/sitemap.xml