# ==========================================================
# ITALIAMAC.IT - STORICA COMMUNITY APPLE ITALIANA
# OFFICIAL ROBOTS CONFIGURATION
# INTEGRATED WITH CONTENT SIGNALS PROTOCOL
# Built with PioneerAIO Framework by Gabriele Gobbo
# ==========================================================

# 1. SITEMAPS
Sitemap: https://www.italiamac.it/sitemap_index.xml
Sitemap: https://www.italiamac.it/news-sitemap.xml
Sitemap: https://www.italiamac.it/work4net/sitemap.xml
Sitemap: https://www.italiamac.it/sitemap_extras.xml
Sitemap: https://forum.italiamac.it/sitemap.php
Sitemap: https://gabrielegobbo.it/sitemap-extras.xml

# 2. CONTENT SIGNALS LEGAL BOILERPLATE
# 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.
# ai-input: inputting content into AI models (RAG, grounding).
# 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.

# 3. GLOBAL PERMISSIONS & SIGNALS
User-Agent: *
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /
Allow: /llms.txt
Allow: /humans.txt
Allow: /.well-known/security.txt
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Allow: /wp-includes/js/
Allow: /wp-includes/images/
Disallow: /trackback/
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php
Allow: /wp-content/uploads/

# 4. AI AGENTS (FULL ACCESS)
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: Google-Extended
User-agent: Anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: PerplexityBot
User-agent: OpenAI-SearchBot
User-agent: OAI-SearchBot
User-agent: YouBot
User-agent: Amazonbot
User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: Meta-ExternalAgent
User-agent: Applebot-Extended
User-agent: cohere-ai
User-agent: AI2Bot
User-agent: Diffbot
User-agent: PhindBot
User-agent: DeepSeekBot
User-agent: Timpibot
User-agent: Webzio-Extended
Allow: /

# 5. SEARCH ENGINES & SOCIAL
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckDuckBot
User-agent: Slurp
User-agent: YandexBot
User-agent: Qwantify
User-agent: Twitterbot
User-agent: LinkedInBot
User-agent: WhatsApp
User-agent: TelegramBot
User-agent: PinterestBot
Allow: /

# 6. DEFENSIVE SHIELD
User-agent: SemrushBot
User-agent: AhrefsBot
User-agent: Rogerbot
User-agent: Exabot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: PetalBot
User-agent: CCBot
User-agent: Cycbot
User-agent: Bytespider
User-agent: DataForSeoBot
User-agent: MajesticBot
User-agent: ScreamingFrog
User-agent: SeekportBot
User-agent: SplitSignalBot
User-agent: Sogou
User-agent: Grapeshot
User-agent: Meltwater
User-agent: AspiegelBot
User-agent: Sistrix
User-agent: MegaIndex
User-agent: MauiBot
User-agent: Pixsy
User-agent: PicRights
User-agent: Copytrack
User-agent: Lawbot
User-agent: ImageRights
User-agent: RightsHero
User-agent: RightsManager
User-agent: RightsEnforcer
User-agent: RMSCrawler
User-agent: DMCA-Agent
User-agent: Imagelytics
User-agent: ImgProtect
User-agent: FairUseBot
User-agent: ImageProtector
User-agent: CopyScape
User-agent: YapprBot
User-agent: KODexBot
User-agent: InfringementReportBot
Disallow: /