1- # http://www.robotstxt.org/wc/norobots.html
2-
1+ # Stop anything going into these locations
32User-agent: *
43Disallow: /login/
54Disallow: * /diff/
@@ -14,3 +13,70 @@ Disallow: /*?*size=*
1413
1514Sitemap: https://metacpan.org/sitemap-authors.xml.gz
1615Sitemap: https://metacpan.org/sitemap-releases.xml.gz
16+
17+ # Stop the bots, using list from:
18+ # https://github.com/ai-robots-txt/ai.robots.txt/blob/main/robots.txt
19+ User-agent: AI 2 Bot
20+ User-agent: Ai 2 Bot-Dolma
21+ User-agent: aiHitBot
22+ User-agent: Amazonbot
23+ User-agent: anthropic-ai
24+ User-agent: Applebot
25+ User-agent: Applebot-Extended
26+ User-agent: Brightbot 1 .0
27+ User-agent: Bytespider
28+ User-agent: CCBot
29+ User-agent: ChatGPT-User
30+ User-agent: Claude-SearchBot
31+ User-agent: Claude-User
32+ User-agent: Claude-Web
33+ User-agent: ClaudeBot
34+ User-agent: cohere-ai
35+ User-agent: cohere-training-data-crawler
36+ User-agent: Cotoyogi
37+ User-agent: Crawlspace
38+ User-agent: Diffbot
39+ User-agent: DuckAssistBot
40+ User-agent: FacebookBot
41+ User-agent: Factset _spyderbot
42+ User-agent: FirecrawlAgent
43+ User-agent: FriendlyCrawler
44+ User-agent: Google-CloudVertexBot
45+ User-agent: Google-Extended
46+ User-agent: GoogleOther
47+ User-agent: GoogleOther-Image
48+ User-agent: GoogleOther-Video
49+ User-agent: GPTBot
50+ User-agent: iaskspider /2.0
51+ User-agent: ICC-Crawler
52+ User-agent: ImagesiftBot
53+ User-agent: img 2 dataset
54+ User-agent: imgproxy
55+ User-agent: ISSCyberRiskCrawler
56+ User-agent: Kangaroo Bot
57+ User-agent: meta-externalagent
58+ User-agent: Meta-ExternalAgent
59+ User-agent: meta-externalfetcher
60+ User-agent: Meta-ExternalFetcher
61+ User-agent: MistralAI-User /1.0
62+ User-agent: NovaAct
63+ User-agent: OAI-SearchBot
64+ User-agent: omgili
65+ User-agent: omgilibot
66+ User-agent: Operator
67+ User-agent: PanguBot
68+ User-agent: Perplexity-User
69+ User-agent: PerplexityBot
70+ User-agent: PetalBot
71+ User-agent: QualifiedBot
72+ User-agent: Scrapy
73+ User-agent: SemrushBot-OCOB
74+ User-agent: SemrushBot-SWA
75+ User-agent: Sidetrade indexer bot
76+ User-agent: TikTokSpider
77+ User-agent: Timpibot
78+ User-agent: VelenPublicWebCrawler
79+ User-agent: Webzio-Extended
80+ User-agent: wpbot
81+ User-agent: YouBot
82+ Disallow: /
0 commit comments