# ===================================================== # ROBOTS.TXT FOR RAFTAAR.IN # Optimized for News, Google Discover & SEO # ===================================================== # ----------------------------------------------------- # Default rules for all crawlers # ----------------------------------------------------- User-agent: * Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /wp-register.php Disallow: /search/ Disallow: /?s= Disallow: /trackback/ Disallow: */trackback/ Disallow: /xmlrpc.php Disallow: /wp-json/ Disallow: /tag/*/page/ Disallow: /category/*/page/ Disallow: /author/*/page/ Disallow: /*/page/ Disallow: /*?paged= Disallow: /comments/feed/ Disallow: */feed/comments/ Allow: /wp-admin/admin-ajax.php # ----------------------------------------------------- # Google crawlers (primary) # ----------------------------------------------------- User-agent: Googlebot Crawl-delay: 1 Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /wp-register.php Disallow: /search/ Disallow: /?s= Disallow: /xmlrpc.php Disallow: /wp-json/ Disallow: /tag/*/page/ Disallow: /category/*/page/ Disallow: /author/*/page/ Disallow: /*/page/ Disallow: /*?paged= User-agent: Googlebot-News Crawl-delay: 1 Allow: / # ----------------------------------------------------- # Sitemaps # ----------------------------------------------------- Sitemap: https://raftaar.in/sitemap.xml Sitemap: https://raftaar.in/sitemaps/news.xml # ----------------------------------------------------- # Bing # ----------------------------------------------------- User-agent: Bingbot Crawl-delay: 5 # ----------------------------------------------------- # Apple crawler (Apple News / Siri) # ----------------------------------------------------- User-agent: Applebot Crawl-delay: 5 # ----------------------------------------------------- # Social media crawlers # ----------------------------------------------------- #User-agent: facebookexternalhit #Crawl-delay: 10 #User-agent: meta-externalagent #Crawl-delay: 10 #User-agent: meta-webindexer #Crawl-delay: 10 #User-agent: Twitterbot #Crawl-delay: 5 User-agent: facebookexternalhit Allow: / User-agent: Facebot Allow: / User-agent: meta-externalagent Allow: / User-agent: meta-externalfetcher Allow: / User-agent: meta-webindexer Allow: / User-agent: Twitterbot Allow: / # ----------------------------------------------------- # AI crawlers (allowed but slowed) # ----------------------------------------------------- User-agent: GPTBot Crawl-delay: 10 User-agent: ClaudeBot Crawl-delay: 10 User-agent: PerplexityBot Crawl-delay: 10 User-agent: OAI-SearchBot Crawl-delay: 10 # ----------------------------------------------------- # SEO crawlers (blocked) # ----------------------------------------------------- User-agent: SemrushBot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / # ----------------------------------------------------- # High bandwidth crawlers # ----------------------------------------------------- User-agent: Baiduspider Disallow: / User-agent: PetalBot Disallow: / User-agent: Sogou Disallow: / User-agent: Yandex Disallow: / User-agent: YandexBot Disallow: /