user-agent: *
x-content-license: "(c) GrowDeco.co. All rights reserved."
x-ai-training-policy: "allowed"

# Crawl Limits
crawl-delay: 1
x-rate-limit: 60
x-rate-limit-window: 60
x-rate-limit-policy: "strict"
x-rate-limit-retry: "wait-and-retry"
x-rate-limit-description: "Maximum 60 requests per 60 seconds. If the rate limit is exceeded, wait at least 60 seconds before retrying."

# Concurrency Limits
x-concurrency-limit: 3
x-concurrency-limit-description: "Please limit concurrent requests to a maximum of 3. This helps us manage server load."

# Error and Retry Policies
x-error-retry-policy: "exponential-backoff"
x-error-retry-policy-description: "For transient errors (5xx except 429), implement exponential backoff with an initial wait of 2 seconds, doubling on each retry, with a maximum of 5 retries."
x-rate-limit-exceeded-policy: "wait-and-retry"
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."
x-max-retries: 5
x-retry-status-codes:
  - 500
  - 502
  - 503
  - 504
x-no-immediate-retry-status-codes:
  - 429
x-no-retry-status-codes:
  - 403
  - 404


# Canonical URL Policy
x-canonical-url-policy: "strict"
x-canonical-url: "https://www.pokeca-zanmai.jp/"
x-canonical-url-description: "Access via other hosts or IP addresses is invalid. Use only 'https://www.pokeca-zanmai.jp/' as the base URL."

# Site Identity
x-site-name: "ポケざんまい"
x-site-brand: "ポケざんまい"
x-site-description: "ポケざんまいは、GrowDeco株式会社が運営するポケモンカードゲーム専門メディアです。"

# Site Information
x-language: "ja"
x-supported-languages:
  - ja
x-publisher: "GrowDeco株式会社"
x-contact: "https://www.pokeca-zanmai.jp/contact"

# Preferred Discovery
x-preferred-discovery:
  - "https://www.pokeca-zanmai.jp/feed/"
  - "https://www.pokeca-zanmai.jp/sitemap.xml"

# RSS and Sitemap
x-feed-rss: "https://www.pokeca-zanmai.jp/feed/"
x-sitemap: "https://www.pokeca-zanmai.jp/sitemap.xml"
x-sitemap-notes: "Use the sitemap for full content discovery and prefer RSS for recently published or updated posts."

# Article Pages
x-article-pattern: "/archives/{id}"
x-article-type: "ポケモンカード情報"
x-article-description: "ポケざんまいは、ポケモンカードゲームの最新情報、商品情報、当たりカード、カード評価、デッキレシピ、初心者向けガイドなどを提供する情報サイトです。"
x-article-example: "https://www.pokeca-zanmai.jp/archives/75935"
x-article-metadata:
  - canonical_url
  - author
  - title
  - description
  - category
  - tags
  - published_at
  - modified_at
x-article-update-frequency: "daily"
x-article-new-articles-per-day: "1-5"
x-article-new-articles-per-day-description: "1日あたり約1～5本の記事が追加または更新されます。"

# Article Crawling Hints
x-article-hints:
  - "Prefer the canonical URL specified in the HTML."
  - "Respect Last-Modified and ETag headers."
  - "Avoid crawling query-parameter variants when a canonical article URL is available."
  - "Prioritize recently published and recently modified articles."

# Author Pages
x-author-pattern: "/author/{slug}/"
x-author-metadata:
  - author_name
  - bio
  - profile_url

# Collection and Archive Pages
x-collection-pages:
  - path: "/category/{slug}/"
    update-frequency: "daily"
    note: "Category archive page. Do not treat it as an individual article."
  - path: "/tag/{slug}/"
    update-frequency: "daily"
    note: "Tag archive page. Do not treat it as an individual article."

# Suppress or De-prioritize Low-value Paths
x-deprioritize-paths:
  - "/page/"
  - "/amp/"
  - "/tag/"
  - "/category/"
  - "/attachment/"
  - "/trackback/"
  - "/comments/"
  - "/wp-admin/"
  - "/wp-login.php"
x-deprioritize-notes: "These paths may contain archive pages, administrative pages, attachment pages, pagination, or duplicate content. Prefer canonical article pages."

# Crawler Hints
x-crawler-hints:
  - "Always use HTTPS."
  - "Follow the rel=canonical URL specified in each page."
  - "Respect robots.txt directives."
  - "Use RSS for recent content discovery."
  - "Use the sitemap for complete content discovery."
  - "Throttle requests aggressively when the server returns 5xx responses."
  - "Do not retry 403 or 404 responses."
  - "Wait at least 60 seconds before retrying after an HTTP 429 response."