User-agent: *
Disallow: /wp-login.php
Disallow: /wp-includes/*.php
Disallow: /wp-content/plugins/*.php
Disallow: /wp-content/themes/JointsWP-CSS-master/*.php
Disallow: /tag/top-news
Disallow: /serviceworker.js*
Disallow: /?wordfence_syncAttackData*

# Consentire l'accesso ai file CSS, JS e immagini per evitare problemi di rendering
Allow: /*.css$
Allow: /*.js$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.gif$
Allow: /*.svg$
Allow: /*.webp$

# Consentire risorse utili per WordPress
Allow: /wp-admin/load-scripts.php
Allow: /wp-admin/load-styles.php
Allow: /favicon.ico

# --- AI and Scraper Blocklist ---
# User-agent: GPTBot
User-agent: Google-Extended
User-agent: CCBot
# User-agent: anthropic-ai
User-agent: Omgilibot
# User-agent: FacebookBot
User-agent: cohere-ai
User-agent: PetalBot
User-agent: Yandex
User-agent: PerplexityBot
User-agent: AhrefsBot
User-agent: archive.org_bot
User-agent: ArchiveBot
User-agent: Arquivo-web-crawler
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: BacklinkCrawler
User-agent: BIXOCRAWLER
User-agent: BLEXBot
User-agent: Bytespider
User-agent: Cliqzbot
User-agent: ConveraCrawler
User-agent: crawler4j
User-agent: CrystalSemanticsBot
User-agent: DataForSeoBot
User-agent: Diffbot
User-agent: discobot
User-agent: discoverybot
User-agent: dloader(NaverRobot)
User-agent: dotbot
User-agent: Download Ninja
User-agent: DuckAssistBot
User-agent: europarchive.org
User-agent: Exabot
User-agent: ExtractorPro
User-agent: Fetch
User-agent: Flamingo_SearchEngine
User-agent: FriendlyCrawler
User-agent: Gigabot
User-agent: GumGum Bot
User-agent: ia_archiver
User-agent: ia_archiver-web.archive.org
User-agent: ImagesiftBot
User-agent: IstellaBot
User-agent: Jetbot
User-agent: JikeSpider
User-agent: Jyxobot
User-agent: k2spider
User-agent: Kangaroo Bot
User-agent: kbcrawl
User-agent: LexxeBot/1.0
User-agent: LinkArchiver
User-agent: LinkextractorPro
User-agent: Livelapbot
User-agent: magpie-crawler
User-agent: meta-externalfetcher
User-agent: MJ12bot
User-agent: Moreoverbot
User-agent: MSIECrawler
User-agent: nabot
User-agent: NaverBot
User-agent: NerdByNature.Bot
User-agent: netEstate NE Crawler
User-agent: nNetSeer crawler
User-agent: NextGenSearchBot
User-agent: Nicecrawler
User-agent: NPBot
User-agent: nutch
User-agent: Openbot
User-agent: PanguBot
User-agent: peer39_crawler
User-agent: peer39_crawler/1.0
User-agent: PiplBot
User-agent: Pixray-Seeker
User-agent: Primalbot
User-agent: psbot
User-agent: QuerySeekerSpider
User-agent: Quora-Bot
User-agent: rogerbot
User-agent: Scrapy
User-agent: searchpreview
User-agent: SemrushBot
User-agent: SEOENGBot
User-agent: SEOkicks-Robot
User-agent: SiteBot
User-agent: SiteBot/0.1
User-agent: Slurp
User-agent: Sosospider
User-agent: Sogou web spider
User-agent: Sogou spider
User-agent: Sogou inst spider
User-agent: spbot
User-agent: Timpibot
User-agent: trendictionbot
User-agent: trovitBot
User-agent: True_Robot
User-agent: TurnitinBot
User-agent: UbiCrawler
User-agent: uMBot-LN
User-agent: URL_Spider_Pro
User-agent: verticalsearch
User-agent: WBSearchBot
User-agent: web-archive-net.com.bot
User-agent: WeSEE:Search
User-agent: Wotbot
User-agent: YouBot
User-agent: Zealbot
User-agent: Applebot-Extended
Disallow: /

# Sitemap
Sitemap: https://www.sportal.it/sitemap_index.xml