Sitemap: https://energyhomeservice.ca/sitemap_index.xml # Global base rules User-agent: * Allow: /wp-admin/admin-ajax.php Allow: /*/*.css Allow: /*/*.js Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /readme.html Disallow: /license.txt Disallow: /xmlrpc.php Disallow: /wp-login.php Disallow: /wp-register.php Disallow: */disclaimer/* Disallow: *?attachment_id= Disallow: /*?filtering= # Search Engine Visibility User-agent: Googlebot Allow: / User-agent: bingbot Allow: / User-agent: Slurp Allow: / User-agent: DuckDuckBot Allow: / User-agent: Baiduspider Allow: / User-agent: Yandex Allow: / # AI Bot Restrictions User-agent: GPTBot Disallow: / User-agent: OAI-SearchBot Disallow: / User-agent: Google-Extended Disallow: / User-agent: anthropic-ai Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Claude-Web Disallow: / User-agent: FacebookBot Disallow: / User-agent: Meta-ExternalAgent Disallow: / User-agent: Meta-ExternalFetcher Disallow: / User-agent: Bytespider Disallow: / User-agent: Applebot-Extended Disallow: / User-agent: Bingbot-AI Disallow: / User-agent: cohere-ai Disallow: / User-agent: Diffbot Disallow: / User-agent: Omgilibot Disallow: / User-agent: img2dataset Disallow: / User-agent: CCBot Disallow: / User-agent: Kangaroo Bot Disallow: / User-agent: PanguBot Disallow: / User-agent: Sidetrade indexer Disallow: / User-agent: webz.io Disallow: / User-agent: Scrapy Disallow: / User-agent: Timpibot Disallow: / User-agent: PerplexityBot Disallow: / # SEO Tool Restrictions User-agent: SemrushBot Disallow: / User-agent: DotBot Disallow: / # Bot & Scraper Protection (Full AI-Curated List) User-agent: python-requests Disallow: / User-agent: curl Disallow: / User-agent: wget Disallow: / User-agent: libwww-perl Disallow: / User-agent: Go-http-client Disallow: / User-agent: Apache-HttpClient Disallow: / User-agent: Scrapy Disallow: / User-agent: Java Disallow: / User-agent: GiftGhostBot Disallow: / User-agent: Seznam Disallow: / User-agent: PaperLiBot Disallow: / User-agent: Genieo Disallow: / User-agent: Dataprovider/6.101 Disallow: / User-agent: DataproviderSiteExplorer Disallow: / User-agent: Dataprovider/6.92 Disallow: / User-agent: Dataprovider Site Explorer Disallow: / User-agent: Dazoobot/1.0 Disallow: / User-agent: Diffbot Disallow: / User-agent: Diffbot/0.1 Disallow: / User-agent: DomainStatsBot/1.0 Disallow: / User-agent: dubaiindex Disallow: / User-agent: eCommerceBot Disallow: / User-agent: ExpertSearchSpider Disallow: / User-agent: Feedbin Disallow: / User-agent: Fetch/2.0a Disallow: / User-agent: FFbot/1.0 Disallow: / User-agent: focusbot/1.1 Disallow: / User-agent: HuaweiSymantecSpider Disallow: / User-agent: HuaweiSymantecSpider/1.0 Disallow: / User-agent: JobdiggerSpider Disallow: / User-agent: LemurWebCrawler Disallow: / User-agent: LipperheyLinkExplorer Disallow: / User-agent: LSSRocketCrawler/1.0 Disallow: / User-agent: LYT.SRv1.5 Disallow: / User-agent: MiaDev/0.0.1 Disallow: / User-agent: Najdi.si/3.1 Disallow: / User-agent: BountiiBot Disallow: / User-agent: Experibot_v1 Disallow: / User-agent: bixocrawler Disallow: / User-agent: bixocrawler TestCrawler Disallow: / User-agent: bixo Disallow: / User-agent: bixolabs/1.0 Disallow: / User-agent: Crawler4j Disallow: / User-agent: Crowsnest/0.5 Disallow: / User-agent: CukBot Disallow: / User-agent: DBLBot/1.0 Disallow: / User-agent: Digg Deeper/v1 Disallow: / User-agent: discobot/1.0 Disallow: / User-agent: discobot/1.1 Disallow: / User-agent: discobot/2.0 Disallow: / User-agent: discoverybot/2.0 Disallow: / User-agent: Dlvr.it/1.0 Disallow: / User-agent: drupact/0.7 Disallow: / User-agent: Ezooms/1.0 Disallow: / User-agent: fastbot crawler beta 2.0 Disallow: / User-agent: fastbot crawler beta 4.0 Disallow: / User-agent: feedly social Disallow: / User-agent: Feedly/1.0 Disallow: / User-agent: FeedlyBot/1.0 Disallow: / User-agent: Feedspot Disallow: / User-agent: Feedspotbot/1.0 Disallow: / User-agent: Clickagy Intelligence Bot v2 Disallow: / User-agent: classbot Disallow: / User-agent: CISPA Vulnerability Notification Disallow: / User-agent: CirrusExplorer/1.1 Disallow: / User-agent: Checksem/Nutch-1.10 Disallow: / User-agent: CatchBot/5.0 Disallow: / User-agent: CatchBot/3.0 Disallow: / User-agent: CatchBot/2.0 Disallow: / User-agent: CatchBot/1.0 Disallow: / User-agent: CamontSpider/1.0 Disallow: / User-agent: Buzzbot/1.0 Disallow: / User-agent: Buzzbot Disallow: / User-agent: BusinessSeek.biz_Spider Disallow: / User-agent: BUbiNG Disallow: / User-agent: 008/0.85 Disallow: / User-agent: 008/0.83 Disallow: / User-agent: 008/0.71 Disallow: / User-agent: ^Nail Disallow: / User-agent: FyberSpider/1.3 Disallow: / User-agent: findlinks/1.1.6-beta5 Disallow: / User-agent: g2reader-bot/1.0 Disallow: / User-agent: findlinks/1.1.6-beta6 Disallow: / User-agent: findlinks/2.0 Disallow: / User-agent: findlinks/2.0.1 Disallow: / User-agent: findlinks/2.0.2 Disallow: / User-agent: findlinks/2.0.4 Disallow: / User-agent: findlinks/2.0.5 Disallow: / User-agent: findlinks/2.0.9 Disallow: / User-agent: findlinks/2.1 Disallow: / User-agent: findlinks/2.1.5 Disallow: / User-agent: findlinks/2.1.3 Disallow: / User-agent: findlinks/2.2 Disallow: / User-agent: findlinks/2.5 Disallow: / User-agent: findlinks/2.6 Disallow: / User-agent: findlinks/1.0 Disallow: / User-agent: findlinks/1.1.3-beta8 Disallow: / User-agent: findlinks/1.1.3-beta9 Disallow: / User-agent: findlinks/1.1.4-beta7 Disallow: / User-agent: findlinks/1.1.6-beta1 Disallow: / User-agent: findlinks/1.1.6-beta1 Yacy Disallow: / User-agent: findlinks/1.1.6-beta2 Disallow: / User-agent: findlinks/1.1.6-beta3 Disallow: / User-agent: findlinks/1.1.6-beta4 Disallow: / User-agent: Crawlera/1.10.2 Disallow: / User-agent: SiteExplorer Disallow: / User-agent: spbot Disallow: / User-agent: WBSearchBot Disallow: / User-agent: linkdexbot Disallow: / User-agent: netEstate NE Crawler Disallow: / User-agent: Moreover Disallow: / User-agent: sentibot Disallow: / User-agent: Aboundexbot Disallow: / User-agent: proximic Disallow: / User-agent: oBot Disallow: / User-agent: meanpathbot Disallow: / User-agent: Nutch Disallow: / User-agent: TurnitinBot Disallow: / User-agent: ZoominfoBot Disallow: / User-agent: ZmEu Disallow: / User-agent: grapeshot Disallow: / # Block RSS/Atom Feeds User-agent: * Disallow: /feed/ Disallow: /feed/atom/ Disallow: /feed/rss/ Disallow: /feed/rss2/ Disallow: /feed/rdf/ Disallow: /comments/feed/ Disallow: */feed/ Disallow: */trackback/ Disallow: /trackback/ Disallow: /xmlrpc.php # Block Author Archives User-agent: * Disallow: /author/ Disallow: /?author= Disallow: *?replytocom= Disallow: *?replytocom # Allow CSS/JS User-agent: * Allow: /*.css$ User-agent: * Allow: /*.js$ # Allow Images User-agent: * Allow: /*.jpg$ User-agent: * Allow: /*.jpeg$ User-agent: * Allow: /*.png$ User-agent: * Allow: /*.gif$ User-agent: * Allow: /*.webp$ User-agent: * Allow: /*.bmp$ User-agent: * Allow: /*.ico$ User-agent: * Allow: /*.svg$ # Block Search & Pagination User-agent: * Disallow: /?s= Disallow: /*?s= Disallow: /search/ Disallow: /page/ Disallow: /*?p= Disallow: /*?paged= Disallow: /*?page= # Block common crawl trap parameters User-agent: * Disallow: /*?p=* Disallow: /*&p=* Disallow: /*?preview=* User-agent: * Allow: /ads.txt User-agent: * Allow: /app-ads.txt Crawl-delay: 5 # Generated by Better Robots.txt # https://better-robots.com # Crawl governance based on the Interpretive Governance framework # Reference: https://interpretive-governance.org/