# https://www.geihanro.co.jp/llms.txt
# (2025.07.28)

user-agent: *

# License
x-content-license: "(c) Geihanro Co., Ltd. All rights reserved."
[cite_start]x-ai-training-policy: "allowed" [cite: 2]

# Rate Limits
crawl-delay: 1
x-rate-limit: 60
x-rate-limit-window: 60
x-rate-limit-policy: "strict"
x-rate-limit-retry: "no-retry"
x-rate-limit-description: "Maximum 60 requests per 60 seconds. If rate limit is exceeded, do not retry and move on to next request."
[cite_start]x-concurrency-limit: 3 [cite: 3]
[cite_start]x-concurrency-limit-description: "Please limit concurrent requests to a maximum of 3. This helps us manage server load." [cite: 3]
[cite_start]x-error-retry-policy: "exponential-backoff" [cite: 4]
[cite_start]x-error-retry-policy-description: "For transient errors (5xx except 429), implement exponential backoff with initial wait of 2 seconds, doubling on each retry, with maximum 5 retries." [cite: 4]
[cite_start]x-rate-limit-exceeded-policy: "wait-and-retry" [cite: 5]
[cite_start]x-rate-limit-exceeded-policy-description: "When receiving HTTP 429 (Too Many Requests), do not retry immediately. Wait at least 60 seconds before attempting the request again." [cite: 5]
[cite_start]x-max-retries: 5 [cite: 6]
[cite_start]x-retry-status-codes: [cite: 6]
  - 500
  - 502
  - 503
  - 504
[cite_start]x-no-immediate-retry-status-codes: [cite: 6]
  - 429
[cite_start]x-no-retry-status-codes: [cite: 6]
  - 403
  - 404
  - 429

# Canonical URL Policy
x-canonical-url-policy: "strict"
x-canonical-url: "https://www.geihanro.co.jp/"
x-canonical-url-description: "Access via other FQDNs or IP addresses is invalid. Use only 'https://www.geihanro.co.jp/' as the base URL. Within the HTML content, links should also start with 'https://www.geihanro.co.jp/'"

# General Pages
x-page-type: "accommodation-info"
x-page-description: "Information pages for Geihanro, a traditional Japanese inn, including details about rooms, dining, facilities, and the surrounding area."
[cite_start]x-page-example: https://www.geihanro.co.jp/rooms/ [cite: 7]
x-page-metadata:
  - title
  - description
  - keywords
x-page-update-frequency: "monthly"
x-new-pages-per-month: "0-5"

# News/Announcements Pages
allow: /news/*
x-news-pattern: /news/{slug}/
x-news-type: "announcement"
x-news-description: "Latest news and announcements from Geihanro."
[cite_start]x-news-example: https://www.geihanro.co.jp/news/example-news/ [cite: 8]
x-news-metadata:
  - title
  - description
  - date
x-news-update-frequency: "weekly"

# Sitemap
allow: /sitemap.xml
x-sitemap: https://www.geihanro.co.jp/sitemap.xml
x-sitemap-format: xml
x-sitemap-structure: "flat"
x-sitemap-description: "The main sitemap for Geihanro's website."
[cite_start]x-sitemap-retention: "long-term" [cite: 9]
[cite_start]x-sitemap-retention-description: "Sitemaps are retained for long term." [cite: 9]

# Disallow Paths
disallow: /admin/*
disallow: /reservations/*
disallow: /temp/*

# Publisher Information
x-publisher-name: "Akari-ya Geihanro"
x-publisher-description: "This is the official website of Geihanro, a traditional Japanese inn in Inuyama City, Aichi Prefecture, offering all rooms with open-air baths and views of Inuyama Castle. We provide a special time in a space surrounded by rich nature and history."
x-publisher-website: "https://www.geihanro.co.jp/"

# Language
x-supported-languages:
  - ja
  - en

# Crawler Hints
x-crawler-hints:
  - "Before accessing each URL, check if the URL ends with '/'."
  - [cite_start]"If the URL does not end with '/', add '/' to the end of the URL before accessing it." [cite: 10]
  - [cite_start]"Extract the HTML content of each page." [cite: 11]

# Encoding
x-content-charset: "utf-8"