# robots.txt for acscricket.com # Goal: Allow search engine indexing; block AI training crawlers; # protect WordPress admin areas. # --------------------------------------------------------------- # Standard search engines — full access # --------------------------------------------------------------- User-agent: Googlebot Allow: / User-agent: Bingbot Allow: / User-agent: Slurp Allow: / User-agent: DuckDuckBot Allow: / # --------------------------------------------------------------- # WordPress admin/sensitive paths — block all crawlers # --------------------------------------------------------------- User-agent: * Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /wp-includes/ Disallow: /wp-content/plugins/ Disallow: /wp-content/themes/ Disallow: /wp-json/ Disallow: /xmlrpc.php Disallow: /?author= Disallow: /trackback/ Disallow: /feed/ Disallow: /comments/feed/ # --------------------------------------------------------------- # AI TRAINING crawlers — blocked # These bots collect content specifically for LLM training. # Blocking them does not affect search engine rankings. # --------------------------------------------------------------- # OpenAI — training crawler User-agent: GPTBot Disallow: / # Anthropic — training crawlers User-agent: ClaudeBot Disallow: / User-agent: anthropic-ai Disallow: / # Google — Gemini/AI training crawler (separate from Googlebot) User-agent: Google-Extended Disallow: / # Common Crawl — open dataset used by many AI labs for training User-agent: CCBot Disallow: / # Meta AI User-agent: FacebookBot Disallow: / # Apple AI User-agent: Applebot-Extended Disallow: / # Cohere User-agent: cohere-ai Disallow: / # AI2 (Allen Institute) User-agent: AI2Bot Disallow: / # Diffbot User-agent: Diffbot Disallow: / # ByteDance / Doubao (known for ignoring robots.txt — block here as first layer; # consider WAF/server-level blocking as well) User-agent: Bytespider Disallow: / # --------------------------------------------------------------- # AI SEARCH / RETRIEVAL crawlers — allowed # These bots power AI-assisted search features (not training). # Allowing them keeps the site visible in AI-assisted search results. # --------------------------------------------------------------- # OpenAI search indexing (not training) User-agent: OAI-SearchBot Allow: / # Perplexity search User-agent: PerplexityBot Allow: / # --------------------------------------------------------------- # Sitemap # --------------------------------------------------------------- Sitemap: https://acscricket.com/sitemap.xml :User-Agent: * Disallow: /Archive/Scorecards/hidden/ Disallow: /Publications_Progress/ Disallow: /Experimental/ Disallow: /famous_cricketers/ Disallow: /journals/1/files Disallow: /journals/2/files Disallow: /journals/3/files Disallow: /journals/4/files Disallow: /journals/5/files Disallow: /journals/6/files Disallow: /journals/7/files Disallow: /journals/8/files Disallow: /journals/9/files Disallow: /journals/10/files Disallow: /journals/11/files Disallow: /journals/12/files Disallow: /journals/13/files Disallow: /journals/14/files Disallow: /journals/15/files Disallow: /journals/16/files Disallow: /journals/17/files Disallow: /journals/18/files Disallow: /journals/19/files Disallow: /journals/20/files Disallow: /journals/21/files Disallow: /journals/22/files Disallow: /journals/23/files Disallow: /journals/24/files Disallow: /journals/25/files Disallow: /journals/26/files Disallow: /journals/27/files Disallow: /journals/28/files Disallow: /journals/29/files Disallow: /journals/30/files Disallow: /journals/31/files Disallow: /journals/32/files Disallow: /journals/33/files Disallow: /journals/34/files Disallow: /journals/35/files Disallow: /journals/36/files Disallow: /journals/37/files Disallow: /journals/38/files Disallow: /journals/39/files Disallow: /journals/40/files Disallow: /journals/41/files Disallow: /journals/42/files Disallow: /journals/43/files Disallow: /journals/44/files Disallow: /journals/45/files Disallow: /journals/46/files Disallow: /journals/47/files Disallow: /journals/48/files Disallow: /journals/49/files Disallow: /journals/50/files Disallow: /journals/51/files Disallow: /journals/52/files Disallow: /journals/53/files Disallow: /journals/54/files Disallow: /journals/55/files Disallow: /journals/56/files Disallow: /journals/57/files Disallow: /journals/58/files Disallow: /journals/59/files Disallow: /journals/60/files Disallow: /journals/61/files Disallow: /journals/62/files Disallow: /journals/63/files Disallow: /journals/64/files Disallow: /journals/65/files Disallow: /journals/66/files Disallow: /journals/67/files Disallow: /journals/68/files Disallow: /journals/69/files Disallow: /journals/70/files Disallow: /journals/71/files Disallow: /journals/72/files Disallow: /journals/73/files Disallow: /journals/74/files Disallow: /journals/75/files Disallow: /journals/76/files Disallow: /journals/77/files Disallow: /journals/78/files Disallow: /journals/79/files Disallow: /journals/80/files Disallow: /journals/81/files Disallow: /journals/82/files Disallow: /journals/83/files Disallow: /journals/84/files Disallow: /journals/85/files Disallow: /journals/86/files Disallow: /journals/87/files Disallow: /journals/88/files Disallow: /journals/89/files Disallow: /journals/90/files Disallow: /journals/91/files Disallow: /journals/92/files Disallow: /journals/93/files Disallow: /journals/94/files Disallow: /journals/95/files Disallow: /journals/96/files Disallow: /journals/97/files Disallow: /journals/98/files Disallow: /journals/99/files Disallow: /journals/100/files Disallow: /journals/101/files Disallow: /journals/102/files Disallow: /journals/103/files Disallow: /journals/104/files Disallow: /journals/105/files Disallow: /journals/106/files Disallow: /journals/107/files Disallow: /journals/108/files Disallow: /journals/109/files Disallow: /journals/110/files Disallow: /journals/111/files Disallow: /journals/112/files Disallow: /journals/113/files Disallow: /journals/114/files Disallow: /journals/115/files Disallow: /journals/116/files Disallow: /journals/117/files Disallow: /journals/118/files Disallow: /journals/119/files Disallow: /journals/120/files Disallow: /journals/121/files Disallow: /journals/122/files Disallow: /journals/123/files Disallow: /journals/124/files Disallow: /journals/125/files Disallow: /journals/126/files Disallow: /journals/127/files Disallow: /journals/128/files Disallow: /journals/129/files Disallow: /journals/130/files Disallow: /journals/131/files Disallow: /journals/132/files Disallow: /journals/133/files Disallow: /journals/134/files Disallow: /journals/135/files Disallow: /journals/136/files Disallow: /journals/137/files Disallow: /journals/138/files Disallow: /journals/139/files Disallow: /journals/140/files Disallow: /journals/141/files Disallow: /journals/142/files Disallow: /journals/143/files Disallow: /journals/144/files Disallow: /journals/145/files Disallow: /journals/146/files Disallow: /journals/147/files Disallow: /journals/148/files Disallow: /journals/149/files Disallow: /journals/150/files Disallow: /journals/151/files Disallow: /journals/152/files Disallow: /journals/153/files Disallow: /journals/154/files Disallow: /journals/155/files Disallow: /journals/index_1-36/files Disallow: /journals/index_1-77/files Disallow: /journals/index_1-100/files User-Agent: * Crawl-Delay: 10 User-Agent: * Crawl-Delay: 10