{ "project": "Verified Bots Directory", "generated_at": "2026-09-05T04:31:23.226Z", "count": 23, "bots": [ { "id": "amazon-seller-initiated-listing", "name": "AmazonSellerInitiatedListing", "operator": { "name": "Amazon", "url": "https://www.amazon.com" }, "description": "Amazon's seller-initiated fetcher, documented alongside AmazonProductDiscoverybot. It fetches a website URL that a seller has supplied so that Amazon can build a product page in its store from that page. Amazon's robots.txt statement on the page covers AmazonProductDiscoverybot only, so no robots behaviour is recorded for this agent.", "docs": [ "https://vendorcentral.amazon.com/support/amazonproductbot" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "AmazonSellerInitiatedListing/\\d" ], "instances": [ "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 (compatible; AmazonSellerInitiatedListing/1.0; https://vendorcentral.amazon.com/support/amazonproductbot)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-08-23T13:20:46.873Z", "resolved_cidrs": [] }, { "id": "apple-podcasts", "name": "Apple Podcasts (iTMS)", "operator": { "name": "Apple", "url": "https://www.apple.com" }, "description": "Apple's podcast feed fetcher, which crawls only URLs associated with content registered on Apple Podcasts. Apple documents that iTMS traffic may come from applebot.apple.com hosts and that it does not follow robots.txt because it is not a general search crawler.", "docs": [ "https://support.apple.com/en-us/119829" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "^i[Tt][Mm][Ss]$" ], "instances": [ "iTMS", "itms" ] }, "behavior": { "respects_robots_txt": false }, "verification": [ { "type": "rdns", "masks": [ "*.applebot.apple.com" ] } ], "tier": 2, "tier_label": "Verifiable", "first_seen": "2026-07-09T03:01:47.690Z", "resolved_cidrs": [] }, { "id": "artemis-web-reader", "name": "Artemis Web Reader", "operator": { "name": "Artemis (jamesg.blog)", "url": "https://artemis.jamesg.blog" }, "description": "The feed poller behind Artemis, a hosted web reader that follows websites and blogs on behalf of its subscribers. It updates once per day and uses HEAD and conditional GET requests with If-Modified-Since and If-None-Match to reduce bandwidth. Artemis publishes the addresses it polls feeds from as a plain-text list.", "docs": [ "https://artemis.jamesg.blog/bot" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "artemis web reader/\\d" ], "instances": [ "artemis web reader/1.0 - https://artemis.jamesg.blog/bot" ] }, "behavior": { "respects_robots_txt": false }, "verification": [ { "type": "cidr_feed", "url": "https://artemis.jamesg.blog/ips.txt", "format": "text_lines" } ], "tier": 1, "tier_label": "Fully verifiable", "first_seen": "2026-08-25T13:21:31.852Z", "resolved_cidrs": [ "2a01:4f8:c0c:969c::/64", "94.130.110.118/32" ] }, { "id": "bazqux", "name": "BazQux Fetcher", "operator": { "name": "BazQux Reader", "url": "https://bazqux.com" }, "description": "The feed fetcher of the BazQux Reader hosted RSS service. It retrieves and periodically refreshes the RSS/Atom and comment feeds that users have subscribed to, typically no more than once an hour per feed. BazQux documents that the fetcher acts as an agent of those users and therefore ignores robots.txt.", "docs": [ "https://bazqux.com/fetcher" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "BazQux" ], "instances": [ "Mozilla/5.0 (compatible; BazQux/2.4; +https://bazqux.com/fetcher; 1 subscribers)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-07-28T19:51:24.263Z", "resolved_cidrs": [] }, { "id": "facebook-catalog", "name": "Facebook Catalog", "operator": { "name": "Meta", "url": "https://www.meta.com" }, "description": "Meta's product-catalog fetcher, identified by the facebookcatalog user-agent. It retrieves merchant product-data feeds used to build and refresh commerce catalogs surfaced across Facebook and Instagram.", "docs": [ "https://developers.facebook.com/docs/sharing/webmasters/web-crawlers" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "facebookcatalog/[\\d.]+" ], "instances": [ "facebookcatalog/1.0" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-07-16T01:14:20.999Z", "resolved_cidrs": [] }, { "id": "fedicabot", "name": "Fedicabot", "operator": { "name": "Fedica", "url": "https://fedica.com" }, "description": "The fetcher used by Fedica's social-media publishing platform. The operator documents that it does not crawl whole sites: it reads only the page or RSS feed a Fedica user has specified, downloading feed content so the user can schedule posts from it, and reading Open Graph metadata so a shared link renders as a card. Fedica publishes the robots.txt token but states no robots.txt policy and no address ranges.", "docs": [ "https://fedica.com/info/fedicabot" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Fedicabot", "FedicaApp" ], "instances": [ "Fedicabot / FedicaApp" ] }, "behavior": { "respects_robots_txt": false, "robots_token": "Fedicabot" }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-09-03T13:20:13.415Z", "resolved_cidrs": [] }, { "id": "feedbin", "name": "Feedbin", "operator": { "name": "Feedbin", "url": "https://feedbin.com" }, "description": "Feedbin's feed fetcher, which retrieves RSS/Atom feeds that users have subscribed to. Its user agent includes the internal feed id and current subscriber count, and Feedbin documents forward-confirmed reverse DNS in *.bot.feedbin.com as the way to verify its requests.", "docs": [ "https://feedbin.com/help/verifying-feed-requests/" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Feedbin feed-id:\\d+" ], "instances": [ "Feedbin feed-id:2005098 - 2 subscribers", "Feedbin feed-id:1234 - 21 subscribers" ] }, "behavior": { "respects_robots_txt": false }, "verification": [ { "type": "rdns", "masks": [ "*.bot.feedbin.com" ] } ], "tier": 2, "tier_label": "Verifiable", "first_seen": "2026-07-09T03:01:47.690Z", "resolved_cidrs": [] }, { "id": "feeder-co", "name": "Feeder Crawler", "operator": { "name": "Feeder", "url": "https://feeder.co" }, "description": "Crawler for Feeder, a hosted RSS reading service. The operator documents that it only fetches feeds users have actively subscribed to, that it acts as an agent on the user's behalf and therefore does not check robots.txt, and that rate limits can be arranged by contacting support. Its user agent is a browser-shaped string in which Feeder deliberately inserts the feeder.co identifier as the honest self-identification.", "docs": [ "https://feeder.co/crawler" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "feeder\\.co(?:/crawler)?[;)]" ], "instances": [ "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6; +feeder.co/crawler) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2; +feeder.co/crawler) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/37.0.2062.120 Safari/537.36", "Mozilla/5.0 (feeder.co; Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-08-27T13:23:13.415Z", "resolved_cidrs": [] }, { "id": "feedly", "name": "Feedly Fetcher", "operator": { "name": "Feedly", "url": "https://feedly.com" }, "description": "Feedly's fetcher, which retrieves RSS/Atom feed URLs after a user has explicitly added them to their Feedly. Feedly documents that it behaves as a direct agent of the user rather than a robot, and does not publish a fixed IP list because its source IPs change over time.", "docs": [ "https://feedly.com/fetcher.html" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Feedly/[\\d.]+" ], "instances": [ "Feedly/1.0 (+http://www.feedly.com/fetcher.html; like FeedFetcher-Google)", "FeedlyBot/1.0 (http://feedly.com)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-07-08T19:13:49.571Z", "resolved_cidrs": [] }, { "id": "feedspot-feedfetcher", "name": "Feedspot", "operator": { "name": "Feedspot", "url": "https://www.feedspot.com/" }, "description": "Feedspot is a hosted content reader and feed aggregation service. Its bot fetches RSS and Atom feeds and web content on behalf of Feedspot users.", "docs": [ "https://www.feedspot.com/fs/bot" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Feedspot" ], "instances": [ "Mozilla/5.0 (compatible; Feedspotbot/1.0; +http://www.feedspot.com/fs/bot)", "Mozilla/5.0 (compatible; Feedspot/1.0 (+https://www.feedspot.com/fs/fetcher; like FeedFetcher-Google)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-07-16T01:14:20.999Z", "resolved_cidrs": [] }, { "id": "feedwind-crawler", "name": "FeedWind Crawler", "operator": { "name": "Mikle KK (FeedWind)", "url": "https://feed.mikle.com" }, "description": "The crawler behind FeedWind, an embeddable RSS/Atom widget. It fetches the feed sources that a widget owner has configured, every five minutes to five hours depending on their plan, so the rendered widget stays current. The operator's support page prints the crawler's full user agent and asks feed publishers to unblock it if a firewall is turning it away.", "docs": [ "https://feed.mikle.com/support/description/" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Feedwind/\\d" ], "instances": [ "Mozilla/5.0 (compatible; Feedwind/3.0; +https://feed.mikle.com/support/description/)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-08-31T13:20:25.762Z", "resolved_cidrs": [] }, { "id": "flipboard-proxy", "name": "Flipboard Proxy", "operator": { "name": "Flipboard, Inc.", "url": "https://about.flipboard.com" }, "description": "Flipboard's proxy service, which fetches and prepares elements of a page (e.g. a social feed a user asked Flipboard to scan) for presentation in the Flipboard app. Flipboard's own docs say these requests currently originate from an Amazon EC2 cluster but publish no fixed IP list.", "docs": [ "https://about.flipboard.com/proxy-service/" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "FlipboardProxy/[\\d.]+" ], "instances": [ "Mozilla/5.0 (compatible; FlipboardProxy/1.2; +http://flipboard.com/browserproxy)", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:49.0) Gecko/20100101 Firefox/49.0 (FlipboardProxy/1.2; +http://flipboard.com/browserproxy)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-07-08T19:13:49.571Z", "resolved_cidrs": [] }, { "id": "google-feedfetcher", "name": "Feedfetcher-Google", "operator": { "name": "Google", "url": "https://www.google.com" }, "description": "Google's feed retrieval agent for RSS and Atom feeds used by Google News and WebSub. It fetches and periodically refreshes feeds that users of an app or service have explicitly subscribed to.", "docs": [ "https://developers.google.com/search/docs/crawling-indexing/feedfetcher" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Feedfetcher-Google" ], "instances": [ "Feedfetcher-Google; (+http://www.google.com/feedfetcher.html; 1 subscribers; feed-id=728742641706423)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [ { "type": "cidr_feed", "url": "https://developers.google.com/static/crawling/ipranges/user-triggered-fetchers-google.json", "format": "prefixes" } ], "tier": 1, "tier_label": "Fully verifiable", "first_seen": "2026-07-16T00:59:46.504Z", "resolved_cidrs": [ "142.250.32.0/27", "142.250.32.128/27", "142.250.32.160/27", "142.250.32.192/27", "142.250.32.224/27", "142.250.32.32/27", "142.250.32.64/27", "142.250.32.96/27", "142.250.33.0/27", "142.250.33.128/27", "142.250.33.32/27", "142.250.33.64/27", "142.250.33.96/27", "172.253.181.0/27", "172.253.181.128/27", "172.253.181.160/27", "172.253.181.192/27", "172.253.181.224/27", "172.253.181.32/27", "172.253.181.64/27", "172.253.181.96/27", "172.253.182.0/27", "172.253.182.128/27", "172.253.182.32/27", "172.253.182.64/27", "172.253.182.96/27", "172.253.183.0/27", "172.253.183.128/27", "172.253.183.160/27", "172.253.183.192/27", "172.253.183.224/27", "172.253.183.32/27", "172.253.183.64/27", "172.253.183.96/27", "192.178.10.0/27", "192.178.10.32/27", "192.178.10.64/27", "192.178.10.96/27", "192.178.11.0/27", "192.178.11.128/27", "192.178.11.160/27", "192.178.11.192/27", "192.178.11.224/27", "192.178.11.32/27", "192.178.11.64/27", "192.178.11.96/27", "192.178.12.0/27", "192.178.12.128/27", "192.178.12.160/27", "192.178.12.192/27", "192.178.12.32/27", "192.178.12.64/27", "192.178.12.96/27", "192.178.13.0/27", "192.178.13.128/27", "192.178.13.160/27", "192.178.13.192/27", "192.178.13.224/27", "192.178.13.32/27", "192.178.13.64/27", "192.178.13.96/27", "192.178.14.0/27", "192.178.15.0/27", "192.178.15.128/27", "192.178.15.160/27", "192.178.15.192/27", "192.178.15.224/27", "192.178.15.32/27", "192.178.15.64/27", "192.178.15.96/27", "192.178.8.0/27", "192.178.8.128/27", "192.178.8.32/27", "192.178.8.64/27", "192.178.8.96/27", "192.178.9.0/27", "192.178.9.128/27", "192.178.9.160/27", "192.178.9.192/27", "192.178.9.224/27", "192.178.9.32/27", "192.178.9.64/27", "192.178.9.96/27", "2001:4860:4801:4004::/64", "2001:4860:4801:4008::/64", "2001:4860:4801:4009::/64", "2001:4860:4801:400f::/64", "2001:4860:4801:4010::/64", "2001:4860:4801:4015::/64", "2001:4860:4801:4016::/64", "2001:4860:4801:4017::/64", "2001:4860:4801:4018::/64", "2001:4860:4801:401a::/64", "2001:4860:4801:401b::/64", "2001:4860:4801:401c::/64", "2001:4860:4801:4020::/64", "2001:4860:4801:4021::/64", "2001:4860:4801:4022::/64", "2001:4860:4801:4023::/64", "2001:4860:4801:4024::/64", "2001:4860:4801:4025::/64", "2001:4860:4801:4026::/64", "2001:4860:4801:4027::/64", "2001:4860:4801:4028::/64", "2001:4860:4801:4029::/64", "2001:4860:4801:402a::/64", "2001:4860:4801:402b::/64", "2001:4860:4801:4030::/64", "2001:4860:4801:4031::/64", "2001:4860:4801:4032::/64", "2001:4860:4801:4033::/64", "2001:4860:4801:4034::/64", "2001:4860:4801:4035::/64", "2001:4860:4801:4036::/64", "2001:4860:4801:4037::/64", "2001:4860:4801:4038::/64", "2001:4860:4801:4039::/64", "2001:4860:4801:403a::/64", "2001:4860:4801:403b::/64", "2001:4860:4801:403c::/64", "2001:4860:4801:4040::/64", "2001:4860:4801:4041::/64", "2001:4860:4801:4042::/64", "2001:4860:4801:4043::/64", "2001:4860:4801:4044::/64", "2001:4860:4801:4045::/64", "2001:4860:4801:4046::/64", "2001:4860:4801:4047::/64", "2001:4860:4801:4048::/64", "2001:4860:4801:4049::/64", "2001:4860:4801:404a::/64", "2001:4860:4801:404b::/64", "2001:4860:4801:404c::/64", "2001:4860:4801:404d::/64", "2001:4860:4801:404e::/64", "2001:4860:4801:404f::/64", "2001:4860:4801:4050::/64", "2001:4860:4801:4051::/64", "2001:4860:4801:4052::/64", "2001:4860:4801:4053::/64", "2001:4860:4801:4054::/64", "2001:4860:4801:4055::/64", "2001:4860:4801:4056::/64", "2001:4860:4801:4057::/64", "2001:4860:4801:4058::/64", "2001:4860:4801:4059::/64", "2001:4860:4801:405a::/64", "2001:4860:4801:405b::/64", "2001:4860:4801:405c::/64", "2001:4860:4801:405d::/64", "2001:4860:4801:405e::/64", "2001:4860:4801:405f::/64", "2001:4860:4801:4060::/64", "2001:4860:4801:4061::/64", "2001:4860:4801:4062::/64", "2001:4860:4801:4063::/64", "2001:4860:4801:4064::/64", "2001:4860:4801:4065::/64", "2001:4860:4801:4066::/64", "2001:4860:4801:4067::/64", "2001:4860:4801:4068::/64", "2001:4860:4801:4069::/64", "2001:4860:4801:406a::/64", "2001:4860:4801:406b::/64", "2001:4860:4801:406c::/64", "2001:4860:4801:406d::/64", "2001:4860:4801:406e::/64", "2001:4860:4801:4070::/64", "2001:4860:4801:4071::/64", "2001:4860:4801:4072::/64", "2001:4860:4801:4073::/64", "2001:4860:4801:4074::/64", "2001:4860:4801:4075::/64", "2001:4860:4801:4076::/64", "2001:4860:4801:4077::/64", "2001:4860:4801:4078::/64", "2001:4860:4801:4079::/64", "2001:4860:4801:407a::/64", "2001:4860:4801:407b::/64", "2001:4860:4801:407c::/64", "2001:4860:4801:407d::/64", "2001:4860:4801:407e::/64", "2001:4860:4801:407f::/64", "2001:4860:4801:4080::/64", "2001:4860:4801:4081::/64", "2001:4860:4801:4082::/64", "2001:4860:4801:4083::/64", "2001:4860:4801:4084::/64", "2001:4860:4801:4085::/64", "2001:4860:4801:4086::/64", "2001:4860:4801:4087::/64", "2001:4860:4801:4088::/64", "2001:4860:4801:4089::/64", "2001:4860:4801:408a::/64", "2001:4860:4801:408b::/64", "2001:4860:4801:4090::/64", "2001:4860:4801:4091::/64", "2001:4860:4801:4092::/64", "2001:4860:4801:4093::/64", "2001:4860:4801:4094::/64", "2001:4860:4801:4095::/64", "2001:4860:4801:4096::/64", "2001:4860:4801:40a0::/64", "2001:4860:4801:40a1::/64", "2001:4860:4801:40a2::/64", "2001:4860:4801:40a3::/64", "2001:4860:4801:40a4::/64", "2001:4860:4801:40b0::/64", "2001:4860:4801:40b1::/64", "2001:4860:4801:40b2::/64", "2001:4860:4801:40b3::/64", "2001:4860:4801:40b4::/64", "2001:4860:4801:40b5::/64", "2001:4860:4801:40b6::/64", "2001:4860:4801:40b7::/64", "2001:4860:4801:40b8::/64", "2001:4860:4801:40b9::/64", "2001:4860:4801:40ba::/64", "2001:4860:4801:40c0::/64", "2001:4860:4801:40c1::/64", "2001:4860:4801:40c2::/64", "2001:4860:4801:40c3::/64", "2001:4860:4801:40c4::/64", "2001:4860:4801:40c5::/64", "2001:4860:4801:40c6::/64", "2001:4860:4801:40d0::/64", "2001:4860:4801:40d1::/64", "2001:4860:4801:40d2::/64", "2001:4860:4801:40d3::/64", "2001:4860:4801:40d4::/64", "2001:4860:4801:40d5::/64", "2001:4860:4801:40d6::/64", "2001:4860:4801:40d7::/64", "2001:4860:4801:40d8::/64", "2001:4860:4801:40d9::/64", "2001:4860:4801:40da::/64", "2001:4860:4801:40db::/64", "2001:4860:4801:40dc::/64", "2001:4860:4801:40dd::/64", "2001:4860:4801:40de::/64", "2001:4860:4801:40df::/64", "2001:4860:4801:40e0::/64", "2001:4860:4801:40e1::/64", "2001:4860:4801:40e2::/64", "2001:4860:4801:40e3::/64", "2001:4860:4801:40f0::/64", "2001:4860:4801:40f1::/64", "2001:4860:4801:40f2::/64", "2001:4860:4801:40f3::/64", "2001:4860:4801:40f4::/64", "2001:4860:4801:40f5::/64", "2001:4860:4801:40f6::/64", "2001:4860:4801:40f7::/64", "2001:4860:4801:40f8::/64", "2001:4860:4801:40f9::/64", "2001:4860:4801:40fa::/64", "2001:4860:4801:40fb::/64", "2001:4860:4801:40fc::/64", "2001:4860:4801:40fd::/64", "2001:4860:4801:40fe::/64", "2001:4860:4801:40ff::/64", "2001:4860:4801:4100::/64", "2001:4860:4801:4101::/64", "2001:4860:4801:4102::/64", "2001:4860:4801:4103::/64", "2001:4860:4801:4104::/64", "2001:4860:4801:4105::/64", "2001:4860:4801:4106::/64", "2001:4860:4801:4107::/64", "2001:4860:4801:4110::/64", "2001:4860:4801:4111::/64", "2001:4860:4801:4112::/64", "2001:4860:4801:4113::/64", "2001:4860:4801:4120::/64", "2001:4860:4801:4121::/64", "2001:4860:4801:4122::/64", "2001:4860:4801:4123::/64", "2001:4860:4801:4124::/64", "2001:4860:4801:4125::/64", "2001:4860:4801:4126::/64", "2001:4860:4801:4127::/64", "2001:4860:4801:4128::/64", "2001:4860:4801:4129::/64", "2001:4860:4801:412a::/64", "2001:4860:4801:412b::/64", "2001:4860:4801:412c::/64", "2001:4860:4801:412d::/64", "2001:4860:4801:412e::/64", "2001:4860:4801:412f::/64", "2001:4860:4801:4130::/64", "2001:4860:4801:4131::/64", "2001:4860:4801:4132::/64", "2001:4860:4801:4133::/64", "2001:4860:4801:4134::/64", "2001:4860:4801:4135::/64", "2001:4860:4801:4136::/64", "2001:4860:4801:4140::/64", "2001:4860:4801:4141::/64", "2001:4860:4801:4142::/64", "2001:4860:4801:4143::/64", "2001:4860:4801:4144::/64", "2001:4860:4801:4145::/64", "2001:4860:4801:4146::/64", "2001:4860:4801:4147::/64", "2001:4860:4801:4150::/64", "2001:4860:4801:4151::/64", "2001:4860:4801:4152::/64", "2001:4860:4801:4153::/64", "2001:4860:4801:4154::/64", "2001:4860:4801:4155::/64", "2001:4860:4801:4156::/64", "2001:4860:4801:4157::/64", "2001:4860:4801:4158::/64", "2001:4860:4801:4159::/64", "2001:4860:4801:415a::/64", "2001:4860:4801:415b::/64", "2001:4860:4801:415c::/64", "2001:4860:4801:415d::/64", "2001:4860:4801:415e::/64", "2001:4860:4801:4160::/64", "2001:4860:4801:4161::/64", "2001:4860:4801:4162::/64", "2001:4860:4801:4163::/64", "2001:4860:4801:4164::/64", "2001:4860:4801:4165::/64", "2001:4860:4801:4166::/64", "2001:4860:4801:4167::/64", "2001:4860:4801:4168::/64", "2001:4860:4801:4169::/64", "2001:4860:4801:416a::/64", "2001:4860:4801:416b::/64", "64.233.172.0/27", "64.233.172.128/27", "64.233.172.160/27", "64.233.172.192/27", "64.233.172.224/27", "64.233.172.32/27", "64.233.172.64/27", "64.233.172.96/27", "64.233.173.0/27", "64.233.173.128/27", "64.233.173.160/27", "64.233.173.192/27", "64.233.173.224/27", "64.233.173.32/27", "64.233.173.64/27", "64.233.173.96/27", "66.102.6.0/27", "66.102.6.128/27", "66.102.6.160/27", "66.102.6.192/27", "66.102.6.224/27", "66.102.6.32/27", "66.102.6.64/27", "66.102.6.96/27", "66.102.7.0/27", "66.102.7.128/27", "66.102.7.160/27", "66.102.7.192/27", "66.102.7.224/27", "66.102.7.32/27", "66.102.7.64/27", "66.102.7.96/27", "66.102.8.0/27", "66.102.8.128/27", "66.102.8.160/27", "66.102.8.192/27", "66.102.8.224/27", "66.102.8.32/27", "66.102.8.64/27", "66.102.8.96/27", "66.102.9.0/27", "66.102.9.128/27", "66.102.9.160/27", "66.102.9.192/27", "66.102.9.224/27", "66.102.9.32/27", "66.102.9.64/27", "66.102.9.96/27", "66.249.80.0/27", "66.249.80.128/27", "66.249.80.160/27", "66.249.80.192/27", "66.249.80.224/27", "66.249.80.32/27", "66.249.80.64/27", "66.249.80.96/27", "66.249.81.0/27", "66.249.81.128/27", "66.249.81.160/27", "66.249.81.192/27", "66.249.81.224/27", "66.249.81.32/27", "66.249.81.64/27", "66.249.81.96/27", "66.249.82.0/27", "66.249.82.128/27", "66.249.82.160/27", "66.249.82.192/27", "66.249.82.224/27", "66.249.82.32/27", "66.249.82.64/27", "66.249.82.96/27", "66.249.83.0/27", "66.249.83.128/27", "66.249.83.160/27", "66.249.83.192/27", "66.249.83.224/27", "66.249.83.32/27", "66.249.83.64/27", "66.249.83.96/27", "66.249.84.0/27", "66.249.84.128/27", "66.249.84.160/27", "66.249.84.192/27", "66.249.84.224/27", "66.249.84.32/27", "66.249.84.64/27", "66.249.84.96/27", "66.249.85.0/27", "66.249.85.128/27", "66.249.85.160/27", "66.249.85.32/27", "66.249.85.64/27", "66.249.85.96/27", "66.249.88.0/27", "66.249.88.128/27", "66.249.88.160/27", "66.249.88.192/27", "66.249.88.224/27", "66.249.88.32/27", "66.249.88.64/27", "66.249.88.96/27", "66.249.93.0/27", "66.249.93.128/27", "66.249.93.160/27", "66.249.93.192/27", "66.249.93.224/27", "66.249.93.32/27", "66.249.93.64/27", "66.249.93.96/27", "74.125.208.0/27", "74.125.208.128/27", "74.125.208.160/27", "74.125.208.192/27", "74.125.208.224/27", "74.125.208.32/27", "74.125.208.64/27", "74.125.208.96/27", "74.125.209.0/27", "74.125.209.128/27", "74.125.209.160/27", "74.125.209.192/27", "74.125.209.32/27", "74.125.209.64/27", "74.125.209.96/27", "74.125.210.0/27", "74.125.210.128/27", "74.125.210.160/27", "74.125.210.192/27", "74.125.210.224/27", "74.125.210.32/27", "74.125.210.64/27", "74.125.210.96/27", "74.125.211.0/27", "74.125.211.32/27", "74.125.211.64/27", "74.125.211.96/27", "74.125.212.0/27", "74.125.212.128/27", "74.125.212.160/27", "74.125.212.192/27", "74.125.212.224/27", "74.125.212.32/27", "74.125.212.64/27", "74.125.212.96/27", "74.125.213.0/27", "74.125.213.32/27", "74.125.213.64/27", "74.125.213.96/27", "74.125.214.0/27", "74.125.214.128/27", "74.125.214.160/27", "74.125.214.192/27", "74.125.214.224/27", "74.125.214.32/27", "74.125.214.64/27", "74.125.214.96/27", "74.125.215.0/27", "74.125.215.128/27", "74.125.215.160/27", "74.125.215.192/27", "74.125.215.224/27", "74.125.215.32/27", "74.125.215.64/27", "74.125.215.96/27" ] }, { "id": "hatena-russia-crawler", "name": "Hatena::Russia::Crawler", "operator": { "name": "Hatena Co., Ltd. (Hatelabo)", "url": "https://hatelabo.jp/" }, "description": "The fetcher behind Daichecker, the antenna service run on Hatelabo, Hatena's experimental-services lab. It checks the pages and feeds that users have registered for updates. Hatena documents that it parses only the robots.txt groups that name this user agent directly and does not apply the User-agent: * group, so a wildcard rule will not stop it. Hatena notes the name comes from an internal code name for RSS-reader development and has no connection to the country.", "docs": [ "https://labo.hatenastaff.com/page/user-agent-russia-crawler" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Hatena::Russia::Crawler" ], "instances": [ "Hatena::Russia::Crawler/0.01" ] }, "behavior": { "respects_robots_txt": false, "robots_token": "Hatena::Russia::Crawler" }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-08-08T14:42:27.853Z", "resolved_cidrs": [] }, { "id": "innguma-fetcher", "name": "Innguma Fetcher", "operator": { "name": "Innguma", "url": "https://www.innguma.com" }, "description": "Innguma's feed fetcher. It retrieves RSS and Atom feeds that users have added to Innguma or to another application built on the Innguma cloud, and refreshes them roughly once an hour. The operator states that because the requests follow explicit action by human users rather than automated crawling, the fetcher does not follow robots.txt, and documents serving an error status to the Innguma/1.0 user agent as the opt-out.", "docs": [ "https://factory.innguma.com/fetcher/" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Innguma/[\\d.]+" ], "instances": [ "Innguma/1.0 (+https://factory.innguma.com/fetcher/)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-08-27T13:23:13.415Z", "resolved_cidrs": [] }, { "id": "inoreader", "name": "Inoreader Fetcher", "operator": { "name": "Innologica", "url": "https://www.inoreader.com" }, "description": "Inoreader's feed fetcher, which retrieves RSS/Atom feeds that Inoreader users have subscribed to. Its own docs state it does not read robots.txt because it fetches specific, user-requested feed URLs rather than crawling a site, and it publishes a live list of its backend fetcher IPs.", "docs": [ "https://www.inoreader.com/feed-fetcher" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Inoreader/[\\d.]+" ], "instances": [ "Inoreader/1.0 (+http://www.inoreader.com/feed-fetcher; 3 subscribers; )", "Mozilla/5.0 (compatible; inoreader.com; 1 subscribers)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [ { "type": "cidr_feed", "url": "https://www.inoreader.com/.well-known/ip_list.txt", "format": "text_lines" } ], "tier": 1, "tier_label": "Fully verifiable", "first_seen": "2026-07-08T19:13:49.571Z", "resolved_cidrs": [ "144.202.49.4/32", "149.28.114.120/32", "45.76.28.241/32", "84.242.180.248/29", "88.203.186.16/28", "92.247.179.240/28", "92.247.181.0/26" ] }, { "id": "miniflux-feedfetcher", "name": "Miniflux", "operator": { "name": "Miniflux", "url": "https://miniflux.app/" }, "description": "Miniflux is a minimalist, open-source, self-hosted feed reader. User-run instances fetch the RSS and Atom feeds their subscribers add, identifying themselves with a Miniflux User-Agent.", "docs": [ "https://miniflux.app/" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Miniflux\\/" ], "instances": [ "Mozilla/5.0 (compatible; Miniflux/2.0.3; +https://miniflux.net)", "Mozilla/5.0 (compatible; Miniflux/2.0.x-dev; +https://miniflux.net)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-07-16T01:14:20.999Z", "resolved_cidrs": [] }, { "id": "newsblur", "name": "NewsBlur Feed Fetcher", "operator": { "name": "NewsBlur", "url": "https://www.newsblur.com" }, "description": "NewsBlur's open-source feed fetcher, which polls RSS/Atom feeds on behalf of subscribed users. Its user agent embeds the live subscriber count and the feed's permalink; NewsBlur publishes no fixed IP range for it.", "docs": [ "https://github.com/samuelclay/NewsBlur/blob/main/apps/rss_feeds/models.py" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "NewsBlur Feed Fetcher" ], "instances": [ "NewsBlur Feed Fetcher - 1 subscriber - http://www.newsblur.com/site/0000000/webpage (Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0.1 Safari/605.1.15)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-07-08T19:13:49.571Z", "resolved_cidrs": [] }, { "id": "productsup-crawler", "name": "Productsup Website Crawler", "operator": { "name": "Productsup", "url": "https://www.productsup.com" }, "description": "Crawler behind Productsup's website data-import source, which reads pages of a site a Productsup customer has configured and turns them into a product data feed. Productsup documents the default user agent, and notes that customers may append a hash to it for their own filtering.", "docs": [ "https://help.productsup.com/docs/help-center/import-data-feeds/import-data-from-internal-systems/import-web-data-with-website-crawler" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "productsup\\.io/crawler" ], "instances": [ "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.1.6) Gecko/20070802 SeaMonkey/1.1.4 (productsup.io/crawler)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-08-29T13:18:16.426Z", "resolved_cidrs": [] }, { "id": "rakuten-usa-image-bot", "name": "rakutenusabot-image", "operator": { "name": "Rakuten", "url": "https://www.rakuten.com" }, "description": "Rakuten's image-extraction bot, which retrieves product images from merchant sites that have partnered with Rakuten. Its bot page names the identifying token that appears in the user-agent string and gives an abuse contact.", "docs": [ "https://product-image.ebates.com/item-gsp/rakutenusabot.html" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "rakutenusabot-image/[\\d.]+" ], "instances": [ "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; rakutenusabot-image/1.0; +https://product-image.ebates.com/item-gsp/rakutenusabot.html) Chrome/114.0.0.0 Safari/537.36", "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; rakutenusabot-image/1.0) Chrome/114.0.0.0 Safari/537.36" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-08-29T13:18:16.426Z", "resolved_cidrs": [] }, { "id": "scour-rss-bot", "name": "ScourRSSBot", "operator": { "name": "Scour (Evan Schwartz)", "url": "https://scour.ing" }, "description": "Feed fetcher for Scour, a personalized content feed service in which users subscribe to RSS, Atom and JSON feeds and topics of interest. It polls each subscribed feed once every 900 seconds regardless of subscriber count, uses conditional requests, rate-limits itself to two requests per second per registrable domain, and backs off on error responses.", "docs": [ "https://scour.ing/bot" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "ScourRSSBot/[\\d.]+" ], "instances": [ "ScourRSSBot/1.0 (+https://scour.ing/bot)" ] }, "behavior": { "respects_robots_txt": false }, "verification": [], "tier": 3, "tier_label": "Listed only", "first_seen": "2026-08-27T13:23:13.415Z", "resolved_cidrs": [] }, { "id": "superfeedr", "name": "Superfeedr", "operator": { "name": "Superfeedr", "url": "https://superfeedr.com" }, "description": "Superfeedr's PubSubHubbub feed-polling infrastructure, which fetches feed URLs that publishers or subscribers have registered with the service. Its docs publish a list of current node IPs but warn it changes as they add or remove cloud capacity.", "docs": [ "https://documentation.superfeedr.com/misc.html" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "Superfeedr" ], "instances": [ "Superfeedr bot/2.0 http://superfeedr.com - Make your feeds realtime: get in touch - feed-id:1162088860" ] }, "behavior": { "respects_robots_txt": false }, "verification": [ { "type": "static_cidrs", "cidrs": [ "50.116.28.209/32", "50.116.30.23/32", "198.58.96.215/32", "198.58.99.82/32", "198.58.102.49/32", "198.58.102.95/32", "198.58.102.96/32", "198.58.102.117/32", "198.58.102.155/32", "198.58.102.156/32", "198.58.102.158/32", "198.58.103.28/32", "198.58.103.36/32", "198.58.103.91/32", "198.58.103.92/32", "198.58.103.102/32", "198.58.103.114/32", "198.58.103.115/32", "198.58.103.158/32", "198.58.103.160/32" ] } ], "tier": 2, "tier_label": "Verifiable", "first_seen": "2026-07-08T19:13:49.571Z", "resolved_cidrs": [ "198.58.102.117/32", "198.58.102.155/32", "198.58.102.156/32", "198.58.102.158/32", "198.58.102.49/32", "198.58.102.95/32", "198.58.102.96/32", "198.58.103.102/32", "198.58.103.114/32", "198.58.103.115/32", "198.58.103.158/32", "198.58.103.160/32", "198.58.103.28/32", "198.58.103.36/32", "198.58.103.91/32", "198.58.103.92/32", "198.58.96.215/32", "198.58.99.82/32", "50.116.28.209/32", "50.116.30.23/32" ] }, { "id": "w3c-feed-validator", "name": "W3C Feed Validation Service", "operator": { "name": "World Wide Web Consortium (W3C)", "url": "https://www.w3.org" }, "description": "W3C's feed validator, which fetches a user-submitted RSS or Atom feed to check it against the feed specifications. It is a one-off conformance check rather than a subscription fetcher, and W3C publishes its user agent and the shared validator source addresses.", "docs": [ "https://validator.w3.org/services" ], "category": "feed-fetcher", "user_agents": { "patterns": [ "FeedValidator/[\\d.]+" ], "instances": [ "FeedValidator/1.3" ] }, "behavior": { "respects_robots_txt": false }, "verification": [ { "type": "static_cidrs", "cidrs": [ "52.22.66.203/32", "2600:1f18:7d7a:2700::/56" ] } ], "tier": 2, "tier_label": "Verifiable", "first_seen": "2026-09-01T13:17:25.816Z", "resolved_cidrs": [ "2600:1f18:7d7a:2700::/56", "52.22.66.203/32" ] } ] }