Crawl-delay: 10 # START WPFORMS BLOCK # --------------------------- User-agent: * Disallow: /wp-content/uploads/wpforms/ # --------------------------- # END WPFORMS BLOCK Crawl-delay: 10 # START CRAWL-TRAP FIX # --------------------------- # /find-a-collaborator/ has a taxonomy filter that generates a near-infinite # number of crawlable URL combinations (?tax_areas-of-interest=a,b,c,...). # Confirmed Bingbot traffic was found crawling these combinations, which is # contributing to server overload / 504s on that page. This blocks the # filtered variants while still allowing the base listing page to be indexed. User-agent: * Disallow: /find-a-collaborator/?* # --------------------------- # END CRAWL-TRAP FIX # START YOAST BLOCK # --------------------------- User-agent: * Disallow: Sitemap: https://www.foldnet.uk/sitemap_index.xml # --------------------------- # END YOAST BLOCK # --- Optional: block named AI-training crawlers --- # Separate from the crawl-trap fix above (that blocks ALL bots from the # problem URLs). If you also want this site opted out of AI-training # crawling more broadly, uncomment the block(s) you want. Has no effect on # scrapers that ignore robots.txt entirely (see the traffic report for why # rate-limiting / a WAF is the tool for those). # # User-agent: GPTBot # Disallow: / # # User-agent: ChatGPT-User # Disallow: / # # User-agent: Google-Extended # Disallow: / # # User-agent: CCBot # Disallow: / # # User-agent: Bytespider # Disallow: / # # User-agent: PerplexityBot # Disallow: / # # User-agent: ClaudeBot # Disallow: / # # User-agent: anthropic-ai # Disallow: /