Search

User-agent: *
Disallow: /admin/
Disallow: /log/
Disallow: /includes/
Disallow: /comtocom.php
Disallow: /comments.php
Disallow: /ad/
Disallow: /about
Disallow: /dbchanges.php
Disallow: /clubs.php/*
Disallow: /_Incapsula_Resource
Disallow: /mymessages.php
Disallow: /sns/*/*

# Block crawlers used for AI/LLM training data collection
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: Brightbot 1.0
User-agent: CCBot
User-agent: ChatGLM-Spider
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: DeepSeekBot
User-agent: Diffbot
User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: Google-Extended
User-agent: GPTBot
User-agent: ICC-Crawler
User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: laion-huggingface-processor
User-agent: LAIONDownloader
User-agent: Linguee Bot
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: omgili
User-agent: omgilibot
User-agent: PanguBot
User-agent: SBIntuitionsBot
User-agent: Scrapy
User-agent: Sidetrade indexer bot
User-agent: Spider
User-agent: TerraCotta
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: webzio-extended
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
Disallow: /

# Bytespider requires its own separate block as it ignores grouped directives
# Reference: https://github.com/ai-robots-txt/ai.robots.txt/issues/108
User-agent: Bytespider
Disallow: /

Sitemap: https://myanimelist.net/sitemap/index.xml