More robust domain detection

main
Bob Mottram 2025-02-28 12:56:15 +00:00
parent 252142b70f
commit 9781840173
5 changed files with 58 additions and 16 deletions

View File

@ -665,7 +665,11 @@
"thedreamkeeper.co", "thedreamkeeper.co",
"artprint.co", "artprint.co",
"/scrum.co", "/scrum.co",
">scrum.co",
".scrum.co",
"/iamfy.co", "/iamfy.co",
">iamfy.co",
".iamfy.co",
"diffusionart.co", "diffusionart.co",
"cameralyze.co", "cameralyze.co",
"midjourney.co", "midjourney.co",
@ -720,6 +724,8 @@
"ggpredict.io", "ggpredict.io",
"artimator.io", "artimator.io",
"/memo.tv", "/memo.tv",
">memo.tv",
".memo.tv",
"quasi.market", "quasi.market",
"diffusion.land", "diffusion.land",
"neural.love", "neural.love",

View File

@ -79,27 +79,43 @@
"disney.co.uk", "disney.co.uk",
"facebook.com", "facebook.com",
".ford.co.uk", ".ford.co.uk",
"/ford.co.uk",
">ford.co.uk",
".ford.com", ".ford.com",
"/ford.com",
">ford.com",
".ge.com", ".ge.com",
"/ge.com",
">ge.com",
"goldmansachs.com", "goldmansachs.com",
"google.com", "google.com",
"google.co.uk", "google.co.uk",
"harley-davidson.com", "harley-davidson.com",
".intel.com", ".intel.com",
"/intel.com",
">intel.com",
"deere.co.uk", "deere.co.uk",
"deere.com", "deere.com",
"jpmorgan.com", "jpmorgan.com",
".lowes.com", ".lowes.com",
"/lowes.com",
">lowes.com",
"mcdonalds.com", "mcdonalds.com",
"molsoncoors.com", "molsoncoors.com",
"morganstanley.com", "morganstanley.com",
".npr.org", ".npr.org",
"/npr.org",
">npr.org",
".pbs.org", ".pbs.org",
"/pbs.org",
">pbs.org",
"paypal.com", "paypal.com",
"paypal.co.uk", "paypal.co.uk",
"pepsi.com", "pepsi.com",
"pepsi.co.uk", "pepsi.co.uk",
".si.edu", ".si.edu",
"/si.edu",
">si.edu",
"tractorsupply.com", "tractorsupply.com",
"walmart.com", "walmart.com",
"wellsfargo.com", "wellsfargo.com",
@ -113,14 +129,20 @@
"gamer.network", "gamer.network",
"humblebundle.com", "humblebundle.com",
".ign.com", ".ign.com",
"/ign.com",
">ign.com",
"ipvanish.com", "ipvanish.com",
"lifehacker.com", "lifehacker.com",
"livedrive.com", "livedrive.com",
"mashable.com", "mashable.com",
".offers.com", ".offers.com",
"/offers.com",
">offers.com",
"pcmag.com", "pcmag.com",
"retailmenot.com", "retailmenot.com",
".smtp.com", ".smtp.com",
"/smtp.com",
">smtp.com",
"speedtest.net", "speedtest.net",
"spiceworks.com", "spiceworks.com",
"strongvpn.com", "strongvpn.com",

View File

@ -14,6 +14,7 @@
"pressassociation.com", "pressassociation.com",
"/news.co.uk", "/news.co.uk",
".news.co.uk", ".news.co.uk",
">news.co.uk",
" news.co.uk", " news.co.uk",
"newscorpaustralia.com", "newscorpaustralia.com",
"theaustralian.com.au", "theaustralian.com.au",
@ -45,6 +46,7 @@
"foxnewsgo.com", "foxnewsgo.com",
".fox.com", ".fox.com",
"/fox.com", "/fox.com",
">fox.com",
"foxbusiness.com", "foxbusiness.com",
"foxsports.com", "foxsports.com",
"fssta.com", "fssta.com",

View File

@ -5,6 +5,8 @@
"words": [], "words": [],
"domains": [ "domains": [
".rt.com", ".rt.com",
"/rt.com",
">rt.com",
"redfish.media", "redfish.media",
"ruptly.tv", "ruptly.tv",
"sputniknews.com", "sputniknews.com",
@ -22,17 +24,27 @@
"waronfakes.com", "waronfakes.com",
"themoscowtimes.com", "themoscowtimes.com",
".tass.com", ".tass.com",
"/tass.com",
">tass.com",
"meduza.io", "meduza.io",
"globalaffairs.ru", "globalaffairs.ru",
"desk-russie.eu", "desk-russie.eu",
"fine-news.ru", "fine-news.ru",
".ria.ru", ".ria.ru",
"/ria.ru",
">ria.ru",
"lenta.ru", "lenta.ru",
".kp.ru", ".kp.ru",
"/kp.ru",
">kp.ru",
"adigea.aif.ru", "adigea.aif.ru",
"nnews.nnov.ru", "nnews.nnov.ru",
".vm.ru", ".vm.ru",
"/vm.ru",
">vm.ru",
".ng.ru", ".ng.ru",
"/ng.ru",
">ng.ru",
"utro.ru", "utro.ru",
"province.ru", "province.ru",
"eg-online.ru", "eg-online.ru",

View File

@ -3,23 +3,23 @@
"warning": "UK Right Wing Think Tank", "warning": "UK Right Wing Think Tank",
"description": "Biased towards UK right wing agendas", "description": "Biased towards UK right wing agendas",
"words": [ "words": [
"Adam Smith Institute", "Adam Smith Institute",
"Bow Group", "Bow Group",
"Centre for Policy Studies", "Centre for Policy Studies",
"Centre for Social Justice", "Centre for Social Justice",
"Chatham House", "Chatham House",
"Institute of Economic Affairs", "Institute of Economic Affairs",
"Legatum Institute", "Legatum Institute",
"Policy Exchange" "Policy Exchange"
], ],
"domains": [ "domains": [
"adamsmith.org", "adamsmith.org",
"bowgroup.org", "bowgroup.org",
"cps.org.uk", "cps.org.uk",
"centreforsocialjustice.org.uk", "centreforsocialjustice.org.uk",
"chathamhouse.org", "chathamhouse.org",
"iea.org.uk", "iea.org.uk",
"https://li.com", "https://li.com",
"policyexchange.org.uk" "policyexchange.org.uk"
] ]
} }