influxdata.com

            Domain Name: INFLUXDATA.COM
Registrar: NameCheap, Inc.
Domain Status: client transfer prohibited
Creation Date: 2014-06-24T09:48:03Z
Registry Expiry Date: 2026-06-24T09:48:03Z
Updated Date: 2025-05-25T07:37:52Z
Name Server: NS-1200.AWSDNS-22.ORG
Name Server: NS-127.AWSDNS-15.COM
Name Server: NS-2037.AWSDNS-62.CO.UK
Name Server: NS-820.AWSDNS-38.NET
REGISTRAR Contact: NameCheap, Inc.
>>> Last update of RDAP database: 2026-01-25T18:36:53Z         

			# robots.txt for www.influxdata.com
# See https://www.robotstxt.org/robotstxt.html for documentation

# =============================================================================
# CONTENT SIGNALS POLICY
# =============================================================================
# As a condition of accessing this website, you agree to abide by the following
# content signals:
#
# (a)  If a content-signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a content-signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a content signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via content signal with respect to the corresponding use.
#
# The content signals and their meanings are:
#
# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
#
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# =============================================================================
# STANDARD CRAWLERS - ALLOWED
# =============================================================================
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: QualifiedBot
Allow: /

# =============================================================================
# AI TRAINING BOTS - ALLOWED
# =============================================================================
# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Common Crawl (used for AI training datasets)
User-agent: CCBot
Allow: /

# Google AI training (separate from search)
User-agent: Google-Extended
Allow: /

# Anthropic
User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Meta/Facebook AI
User-agent: FacebookBot
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Bytedance/TikTok
User-agent: Bytespider
Allow: /

# =============================================================================
# AGGRESSIVE/PROBLEMATIC CRAWLERS - DISALLOWED
# =============================================================================
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: serpstatbot
Disallow: /

User-agent: SeekportBot
Disallow: /

# =============================================================================
# DEFAULT RULES FOR ALL OTHER CRAWLERS
# =============================================================================
User-agent: *
Allow: /

# Paths that should never be crawled (legacy/non-existent)
Disallow: /wp-admin/
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /.env
Disallow: /.git/
Disallow: /admin/
Disallow: /administrator/

# Script/config files that don't exist on this Rails site
Disallow: /*.php$
Disallow: /*.cgi$
Disallow: /*.py$
Disallow: /*.pl$
Disallow: /*.asp$
Disallow: /*.aspx$
Disallow: /*.jsp$
Disallow: /*.cfm$
Disallow: /*.sh$
Disallow: /*.bak$
Disallow: /*.sql$
Disallow: /*.ini$
Disallow: /*.conf$
Disallow: /*.config$
Disallow: /*.yml$
Disallow: /*.yaml$
Disallow: /*.log$

# Preview routes (Contentful preview, not public content)
Disallow: /webinar-preview
Disallow: /blog-preview
Disallow: /customer-preview
Disallow: /page-preview
Disallow: /influxace-preview
Disallow: /integration-preview
Disallow: /event-preview
Disallow: /channel-partner-preview

# Internal/utility routes
Disallow: /webhooks/
Disallow: /cont-webhook
Disallow: /cap
Disallow: /cap/
Disallow: /eml
Disallow: /up

# =============================================================================
# SITEMAP
# =============================================================================
Sitemap: https://www.influxdata.com/sitemap.xml
        

SEO técnico

SEO en la página

Contenido y UX