mirror of
https://github.com/manualdousuario/marreta.git
synced 2025-09-02 02:30:20 +00:00
novas regras de bloqueio no robots
https://github.com/ai-robots-txt/ai.robots.txt
This commit is contained in:
parent
a4cfef2d40
commit
f7ac0bffa6
1 changed files with 40 additions and 25 deletions
|
@ -1,34 +1,49 @@
|
||||||
|
User-agent: *
|
||||||
|
Allow: /
|
||||||
|
|
||||||
User-agent: *
|
User-agent: *
|
||||||
Disallow: /p/
|
Disallow: /p/
|
||||||
Disallow: /api/
|
Disallow: /api/
|
||||||
|
|
||||||
# Block common AI crawlers
|
User-agent: AI2Bot
|
||||||
User-agent: GPTBot
|
User-agent: Ai2Bot-Dolma
|
||||||
Disallow: /
|
User-agent: Amazonbot
|
||||||
|
|
||||||
User-agent: ChatGPT-User
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: anthropic-ai
|
User-agent: anthropic-ai
|
||||||
Disallow: /
|
User-agent: Applebot
|
||||||
|
User-agent: Applebot-Extended
|
||||||
|
User-agent: Bytespider
|
||||||
User-agent: CCBot
|
User-agent: CCBot
|
||||||
Disallow: /
|
User-agent: ChatGPT-User
|
||||||
|
|
||||||
User-agent: Google-Extended
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: FacebookBot
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: Claude-Web
|
User-agent: Claude-Web
|
||||||
Disallow: /
|
User-agent: ClaudeBot
|
||||||
|
User-agent: cohere-ai
|
||||||
User-agent: Omgilibot
|
User-agent: Diffbot
|
||||||
Disallow: /
|
User-agent: DuckAssistBot
|
||||||
|
|
||||||
User-agent: Omgili
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: FacebookBot
|
User-agent: FacebookBot
|
||||||
|
User-agent: facebookexternalhit
|
||||||
|
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: 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: /
|
Disallow: /
|
Loading…
Add table
Reference in a new issue