aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSam James <[email protected]>2025-09-22 18:30:42 +0100
committerSam James <[email protected]>2025-09-22 18:30:42 +0100
commitf4610178b5993d5d3e12031d97d0dd6b2ace7ef5 (patch)
treebb996f6b25c9bb429ce95b4356ae9efe2aaea8f8
parent_data/iso3166-sort-of.yaml: add Colombia (CO) (diff)
downloadwww-f461017.tar.gz
www-f461017.tar.bz2
www-f461017.zip
robots.txt: update
https://raw.githubusercontent.com/TecharoHQ/anubis/237a6a98e268df70f2655809010c2b87ce3fca53/web/static/robots.txt Signed-off-by: Sam James <[email protected]>
-rw-r--r--robots.txt21
1 files changed, 17 insertions, 4 deletions
diff --git a/robots.txt b/robots.txt
index 1b93f21..66ebc31 100644
--- a/robots.txt
+++ b/robots.txt
@@ -1,6 +1,7 @@
User-agent: AhrefsBot
Disallow: /
+User-agent: AddSearchBot
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
@@ -9,29 +10,38 @@ User-agent: Andibot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended
+User-agent: Awario
User-agent: bedrockbot
+User-agent: bigsur.ai
User-agent: Brightbot 1.0
User-agent: Bytespider
User-agent: CCBot
+User-agent: ChatGPT Agent
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: ClaudeBot
+User-agent: CloudVertexBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: Crawlspace
+User-agent: Datenbank Crawler
+User-agent: Devin
User-agent: Diffbot
User-agent: DuckAssistBot
+User-agent: Echobot Bot
User-agent: EchoboxBot
User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
+User-agent: Gemini-Deep-Research
User-agent: Google-CloudVertexBot
User-agent: Google-Extended
+User-agent: GoogleAgent-Mariner
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
@@ -42,16 +52,20 @@ User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
+User-agent: LinerBot
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: meta-externalfetcher
User-agent: Meta-ExternalFetcher
+User-agent: MistralAI-User
User-agent: MistralAI-User/1.0
User-agent: MyCentralAIScraperBot
+User-agent: netEstate Imprint Crawler
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
+User-agent: OpenAI
User-agent: Operator
User-agent: PanguBot
User-agent: Panscient
@@ -66,18 +80,17 @@ User-agent: QuillBot
User-agent: quillbot.com
User-agent: SBIntuitionsBot
User-agent: Scrapy
-User-agent: SemrushBot
-User-agent: SemrushBot-BA
-User-agent: SemrushBot-CT
User-agent: SemrushBot-OCOB
-User-agent: SemrushBot-SI
User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot
+User-agent: Thinkbot
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
+User-agent: WARDBot
User-agent: Webzio-Extended
User-agent: wpbot
+User-agent: YaK
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: YouBot