UrlCategorise 0.1.7 → 0.1.11
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.claude/settings.local.json +9 -2
- data/.gitignore +1 -0
- data/.rubocop.yml +56 -0
- data/.sublime-project +14 -0
- data/Gemfile +2 -2
- data/Gemfile.lock +89 -41
- data/README.md +167 -9
- data/Rakefile +1 -1
- data/bin/check_lists +124 -22
- data/bin/export_csv +45 -36
- data/bin/export_hosts +34 -24
- data/bin/generate_categorised_lists +533 -0
- data/bin/generate_social_media_lists +398 -0
- data/bin/generate_video_lists +303 -124
- data/bin/generate_video_lists_focused +381 -0
- data/correct_usage_example.rb +18 -18
- data/lib/url_categorise/active_record_client.rb +11 -11
- data/lib/url_categorise/client.rb +856 -226
- data/lib/url_categorise/constants.rb +148 -70
- data/lib/url_categorise/dataset_processor.rb +68 -64
- data/lib/url_categorise/iab_compliance.rb +111 -99
- data/lib/url_categorise/models.rb +15 -15
- data/lib/url_categorise/version.rb +1 -1
- data/lib/url_categorise.rb +14 -14
- data/lists/blogging_domains.hosts +62 -0
- data/lists/crypto_domains.hosts +46 -0
- data/lists/developer_domains.hosts +108 -0
- data/lists/forum_domains.hosts +65 -0
- data/lists/gaming_domains.hosts +99 -0
- data/lists/messaging_domains.hosts +96 -0
- data/lists/music_domains.hosts +62 -0
- data/lists/security_domains.hosts +48 -0
- data/lists/social_media_domains.hosts +443 -0
- data/lists/streaming_domains.hosts +41 -0
- data/lists/video_hosting_domains.hosts +203 -175
- data/lists/video_url_patterns.txt +15 -15
- data/url_categorise.gemspec +11 -9
- metadata +69 -20
|
@@ -0,0 +1,99 @@
|
|
|
1
|
+
# Gaming Platform Domains - PiHole Compatible Hosts File
|
|
2
|
+
# Generated on: 2026-05-22 11:06:15 UTC
|
|
3
|
+
# Sources:
|
|
4
|
+
# - Mr.Holmes OSINT tool (https://github.com/Lucksi/Mr.Holmes)
|
|
5
|
+
# - Manually curated domain lists
|
|
6
|
+
# Purpose: Identify and categorize gaming platforms and communities
|
|
7
|
+
# Format: 0.0.0.0 domain.com
|
|
8
|
+
#
|
|
9
|
+
|
|
10
|
+
0.0.0.0 api.mojang.com
|
|
11
|
+
0.0.0.0 www.api.mojang.com
|
|
12
|
+
0.0.0.0 battle.net
|
|
13
|
+
0.0.0.0 www.battle.net
|
|
14
|
+
0.0.0.0 blizzard.com
|
|
15
|
+
0.0.0.0 www.blizzard.com
|
|
16
|
+
0.0.0.0 chess.com
|
|
17
|
+
0.0.0.0 www.chess.com
|
|
18
|
+
0.0.0.0 clips.twitch.tv
|
|
19
|
+
0.0.0.0 www.clips.twitch.tv
|
|
20
|
+
0.0.0.0 crunchyroll.com
|
|
21
|
+
0.0.0.0 www.crunchyroll.com
|
|
22
|
+
0.0.0.0 ea.com
|
|
23
|
+
0.0.0.0 www.ea.com
|
|
24
|
+
0.0.0.0 epicgames.com
|
|
25
|
+
0.0.0.0 www.epicgames.com
|
|
26
|
+
0.0.0.0 euw.op.gg
|
|
27
|
+
0.0.0.0 www.euw.op.gg
|
|
28
|
+
0.0.0.0 fandom.com
|
|
29
|
+
0.0.0.0 www.fandom.com
|
|
30
|
+
0.0.0.0 fortnitetracker.com
|
|
31
|
+
0.0.0.0 www.fortnitetracker.com
|
|
32
|
+
0.0.0.0 gamespot.com
|
|
33
|
+
0.0.0.0 www.gamespot.com
|
|
34
|
+
0.0.0.0 gog.com
|
|
35
|
+
0.0.0.0 www.gog.com
|
|
36
|
+
0.0.0.0 humblebundle.com
|
|
37
|
+
0.0.0.0 www.humblebundle.com
|
|
38
|
+
0.0.0.0 ign.com
|
|
39
|
+
0.0.0.0 www.ign.com
|
|
40
|
+
0.0.0.0 itch.io
|
|
41
|
+
0.0.0.0 www.itch.io
|
|
42
|
+
0.0.0.0 lichess.org
|
|
43
|
+
0.0.0.0 www.lichess.org
|
|
44
|
+
0.0.0.0 lolprofile.net
|
|
45
|
+
0.0.0.0 www.lolprofile.net
|
|
46
|
+
0.0.0.0 m.twitch.tv
|
|
47
|
+
0.0.0.0 www.m.twitch.tv
|
|
48
|
+
0.0.0.0 myanimelist.net
|
|
49
|
+
0.0.0.0 www.myanimelist.net
|
|
50
|
+
0.0.0.0 newgrounds.com
|
|
51
|
+
0.0.0.0 www.newgrounds.com
|
|
52
|
+
0.0.0.0 nintendo.com
|
|
53
|
+
0.0.0.0 www.nintendo.com
|
|
54
|
+
0.0.0.0 op.gg
|
|
55
|
+
0.0.0.0 www.op.gg
|
|
56
|
+
0.0.0.0 osu.ppy.sh
|
|
57
|
+
0.0.0.0 www.osu.ppy.sh
|
|
58
|
+
0.0.0.0 pokemonshowdown.com
|
|
59
|
+
0.0.0.0 www.pokemonshowdown.com
|
|
60
|
+
0.0.0.0 psnprofiles.com
|
|
61
|
+
0.0.0.0 www.psnprofiles.com
|
|
62
|
+
0.0.0.0 pubg.op.gg
|
|
63
|
+
0.0.0.0 www.pubg.op.gg
|
|
64
|
+
0.0.0.0 roblox.com
|
|
65
|
+
0.0.0.0 www.roblox.com
|
|
66
|
+
0.0.0.0 rockstargames.com
|
|
67
|
+
0.0.0.0 www.rockstargames.com
|
|
68
|
+
0.0.0.0 speedrun.com
|
|
69
|
+
0.0.0.0 www.speedrun.com
|
|
70
|
+
0.0.0.0 splits.io
|
|
71
|
+
0.0.0.0 www.splits.io
|
|
72
|
+
0.0.0.0 steamcommunity.com
|
|
73
|
+
0.0.0.0 www.steamcommunity.com
|
|
74
|
+
0.0.0.0 steampowered.com
|
|
75
|
+
0.0.0.0 www.steampowered.com
|
|
76
|
+
0.0.0.0 store.steampowered.com
|
|
77
|
+
0.0.0.0 www.store.steampowered.com
|
|
78
|
+
0.0.0.0 twitch.tv
|
|
79
|
+
0.0.0.0 www.twitch.tv
|
|
80
|
+
0.0.0.0 twitchtracker.com
|
|
81
|
+
0.0.0.0 www.twitchtracker.com
|
|
82
|
+
0.0.0.0 ubisoft.com
|
|
83
|
+
0.0.0.0 www.ubisoft.com
|
|
84
|
+
0.0.0.0 www.blizzard.com
|
|
85
|
+
0.0.0.0 www.chess.com
|
|
86
|
+
0.0.0.0 www.crunchyroll.com
|
|
87
|
+
0.0.0.0 www.ea.com
|
|
88
|
+
0.0.0.0 www.epicgames.com
|
|
89
|
+
0.0.0.0 www.fandom.com
|
|
90
|
+
0.0.0.0 www.gamespot.com
|
|
91
|
+
0.0.0.0 www.gog.com
|
|
92
|
+
0.0.0.0 www.humblebundle.com
|
|
93
|
+
0.0.0.0 www.ign.com
|
|
94
|
+
0.0.0.0 www.nintendo.com
|
|
95
|
+
0.0.0.0 www.roblox.com
|
|
96
|
+
0.0.0.0 www.rockstargames.com
|
|
97
|
+
0.0.0.0 www.speedrun.com
|
|
98
|
+
0.0.0.0 www.twitch.tv
|
|
99
|
+
0.0.0.0 www.ubisoft.com
|
|
@@ -0,0 +1,96 @@
|
|
|
1
|
+
# Messaging Platform Domains - PiHole Compatible Hosts File
|
|
2
|
+
# Generated on: 2026-05-22 11:06:15 UTC
|
|
3
|
+
# Sources:
|
|
4
|
+
# - Mr.Holmes OSINT tool (https://github.com/Lucksi/Mr.Holmes)
|
|
5
|
+
# - Manually curated domain lists
|
|
6
|
+
# Purpose: Identify and categorize messaging and chat platforms
|
|
7
|
+
# Format: 0.0.0.0 domain.com
|
|
8
|
+
#
|
|
9
|
+
|
|
10
|
+
0.0.0.0 community.signalusers.org
|
|
11
|
+
0.0.0.0 www.community.signalusers.org
|
|
12
|
+
0.0.0.0 discord.com
|
|
13
|
+
0.0.0.0 www.discord.com
|
|
14
|
+
0.0.0.0 discord.gg
|
|
15
|
+
0.0.0.0 www.discord.gg
|
|
16
|
+
0.0.0.0 disqus.com
|
|
17
|
+
0.0.0.0 www.disqus.com
|
|
18
|
+
0.0.0.0 element.io
|
|
19
|
+
0.0.0.0 www.element.io
|
|
20
|
+
0.0.0.0 facebook.com
|
|
21
|
+
0.0.0.0 www.facebook.com
|
|
22
|
+
0.0.0.0 instagram.com
|
|
23
|
+
0.0.0.0 www.instagram.com
|
|
24
|
+
0.0.0.0 kakaotalk.com
|
|
25
|
+
0.0.0.0 www.kakaotalk.com
|
|
26
|
+
0.0.0.0 kik.me
|
|
27
|
+
0.0.0.0 www.kik.me
|
|
28
|
+
0.0.0.0 line.me
|
|
29
|
+
0.0.0.0 www.line.me
|
|
30
|
+
0.0.0.0 m.twitch.tv
|
|
31
|
+
0.0.0.0 www.m.twitch.tv
|
|
32
|
+
0.0.0.0 matrix.org
|
|
33
|
+
0.0.0.0 www.matrix.org
|
|
34
|
+
0.0.0.0 mattermost.com
|
|
35
|
+
0.0.0.0 www.mattermost.com
|
|
36
|
+
0.0.0.0 meet.google.com
|
|
37
|
+
0.0.0.0 www.meet.google.com
|
|
38
|
+
0.0.0.0 messenger.com
|
|
39
|
+
0.0.0.0 www.messenger.com
|
|
40
|
+
0.0.0.0 mobile.twitter.com
|
|
41
|
+
0.0.0.0 www.mobile.twitter.com
|
|
42
|
+
0.0.0.0 myspace.com
|
|
43
|
+
0.0.0.0 www.myspace.com
|
|
44
|
+
0.0.0.0 nitter.net
|
|
45
|
+
0.0.0.0 www.nitter.net
|
|
46
|
+
0.0.0.0 picuki.com
|
|
47
|
+
0.0.0.0 www.picuki.com
|
|
48
|
+
0.0.0.0 rocket.chat
|
|
49
|
+
0.0.0.0 www.rocket.chat
|
|
50
|
+
0.0.0.0 signal.org
|
|
51
|
+
0.0.0.0 www.signal.org
|
|
52
|
+
0.0.0.0 skype.com
|
|
53
|
+
0.0.0.0 www.skype.com
|
|
54
|
+
0.0.0.0 slack.com
|
|
55
|
+
0.0.0.0 www.slack.com
|
|
56
|
+
0.0.0.0 t.me
|
|
57
|
+
0.0.0.0 www.t.me
|
|
58
|
+
0.0.0.0 teams.microsoft.com
|
|
59
|
+
0.0.0.0 www.teams.microsoft.com
|
|
60
|
+
0.0.0.0 telegram.org
|
|
61
|
+
0.0.0.0 www.telegram.org
|
|
62
|
+
0.0.0.0 tellonym.me
|
|
63
|
+
0.0.0.0 www.tellonym.me
|
|
64
|
+
0.0.0.0 threads.net
|
|
65
|
+
0.0.0.0 www.threads.net
|
|
66
|
+
0.0.0.0 twitch.tv
|
|
67
|
+
0.0.0.0 www.twitch.tv
|
|
68
|
+
0.0.0.0 twitchtracker.com
|
|
69
|
+
0.0.0.0 www.twitchtracker.com
|
|
70
|
+
0.0.0.0 twitter.com
|
|
71
|
+
0.0.0.0 www.twitter.com
|
|
72
|
+
0.0.0.0 viber.com
|
|
73
|
+
0.0.0.0 www.viber.com
|
|
74
|
+
0.0.0.0 vk.com
|
|
75
|
+
0.0.0.0 www.vk.com
|
|
76
|
+
0.0.0.0 web.telegram.org
|
|
77
|
+
0.0.0.0 www.web.telegram.org
|
|
78
|
+
0.0.0.0 web.whatsapp.com
|
|
79
|
+
0.0.0.0 www.web.whatsapp.com
|
|
80
|
+
0.0.0.0 webex.com
|
|
81
|
+
0.0.0.0 www.webex.com
|
|
82
|
+
0.0.0.0 whatsapp.com
|
|
83
|
+
0.0.0.0 www.whatsapp.com
|
|
84
|
+
0.0.0.0 www.discord.com
|
|
85
|
+
0.0.0.0 www.line.me
|
|
86
|
+
0.0.0.0 www.messenger.com
|
|
87
|
+
0.0.0.0 www.signal.org
|
|
88
|
+
0.0.0.0 www.skype.com
|
|
89
|
+
0.0.0.0 www.slack.com
|
|
90
|
+
0.0.0.0 www.telegram.org
|
|
91
|
+
0.0.0.0 www.viber.com
|
|
92
|
+
0.0.0.0 www.whatsapp.com
|
|
93
|
+
0.0.0.0 zoom.us
|
|
94
|
+
0.0.0.0 www.zoom.us
|
|
95
|
+
0.0.0.0 zulip.com
|
|
96
|
+
0.0.0.0 www.zulip.com
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
# Music Platform Domains - PiHole Compatible Hosts File
|
|
2
|
+
# Generated on: 2026-05-22 11:06:15 UTC
|
|
3
|
+
# Sources:
|
|
4
|
+
# - Mr.Holmes OSINT tool (https://github.com/Lucksi/Mr.Holmes)
|
|
5
|
+
# - Manually curated domain lists
|
|
6
|
+
# Purpose: Identify and categorize music streaming and sharing platforms
|
|
7
|
+
# Format: 0.0.0.0 domain.com
|
|
8
|
+
#
|
|
9
|
+
|
|
10
|
+
0.0.0.0 audiojungle.net
|
|
11
|
+
0.0.0.0 www.audiojungle.net
|
|
12
|
+
0.0.0.0 bandcamp.com
|
|
13
|
+
0.0.0.0 www.bandcamp.com
|
|
14
|
+
0.0.0.0 deezer.com
|
|
15
|
+
0.0.0.0 www.deezer.com
|
|
16
|
+
0.0.0.0 discogs.com
|
|
17
|
+
0.0.0.0 www.discogs.com
|
|
18
|
+
0.0.0.0 freesound.org
|
|
19
|
+
0.0.0.0 www.freesound.org
|
|
20
|
+
0.0.0.0 genius.com
|
|
21
|
+
0.0.0.0 www.genius.com
|
|
22
|
+
0.0.0.0 house-mixes.com
|
|
23
|
+
0.0.0.0 www.house-mixes.com
|
|
24
|
+
0.0.0.0 last.fm
|
|
25
|
+
0.0.0.0 www.last.fm
|
|
26
|
+
0.0.0.0 mixcloud.com
|
|
27
|
+
0.0.0.0 www.mixcloud.com
|
|
28
|
+
0.0.0.0 music.amazon.com
|
|
29
|
+
0.0.0.0 www.music.amazon.com
|
|
30
|
+
0.0.0.0 music.apple.com
|
|
31
|
+
0.0.0.0 www.music.apple.com
|
|
32
|
+
0.0.0.0 musicbrainz.org
|
|
33
|
+
0.0.0.0 www.musicbrainz.org
|
|
34
|
+
0.0.0.0 musixmatch.com
|
|
35
|
+
0.0.0.0 www.musixmatch.com
|
|
36
|
+
0.0.0.0 open.spotify.com
|
|
37
|
+
0.0.0.0 www.open.spotify.com
|
|
38
|
+
0.0.0.0 ourdjtalk.com
|
|
39
|
+
0.0.0.0 www.ourdjtalk.com
|
|
40
|
+
0.0.0.0 pandora.com
|
|
41
|
+
0.0.0.0 www.pandora.com
|
|
42
|
+
0.0.0.0 rateyourmusic.com
|
|
43
|
+
0.0.0.0 www.rateyourmusic.com
|
|
44
|
+
0.0.0.0 smule.com
|
|
45
|
+
0.0.0.0 www.smule.com
|
|
46
|
+
0.0.0.0 songkick.com
|
|
47
|
+
0.0.0.0 www.songkick.com
|
|
48
|
+
0.0.0.0 soundcloud.com
|
|
49
|
+
0.0.0.0 www.soundcloud.com
|
|
50
|
+
0.0.0.0 spotify.com
|
|
51
|
+
0.0.0.0 www.spotify.com
|
|
52
|
+
0.0.0.0 tidal.com
|
|
53
|
+
0.0.0.0 www.tidal.com
|
|
54
|
+
0.0.0.0 www.bandcamp.com
|
|
55
|
+
0.0.0.0 www.deezer.com
|
|
56
|
+
0.0.0.0 www.discogs.com
|
|
57
|
+
0.0.0.0 www.house-mixes.com
|
|
58
|
+
0.0.0.0 www.last.fm
|
|
59
|
+
0.0.0.0 www.pandora.com
|
|
60
|
+
0.0.0.0 www.smule.com
|
|
61
|
+
0.0.0.0 www.soundcloud.com
|
|
62
|
+
0.0.0.0 www.tidal.com
|
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
# Security Community Domains - PiHole Compatible Hosts File
|
|
2
|
+
# Generated on: 2026-05-22 11:06:15 UTC
|
|
3
|
+
# Sources:
|
|
4
|
+
# - Mr.Holmes OSINT tool (https://github.com/Lucksi/Mr.Holmes)
|
|
5
|
+
# - Manually curated domain lists
|
|
6
|
+
# Purpose: Identify and categorize security research, bug bounty, and hacking community platforms
|
|
7
|
+
# Format: 0.0.0.0 domain.com
|
|
8
|
+
#
|
|
9
|
+
|
|
10
|
+
0.0.0.0 app.hackthebox.com
|
|
11
|
+
0.0.0.0 www.app.hackthebox.com
|
|
12
|
+
0.0.0.0 bugcrowd.com
|
|
13
|
+
0.0.0.0 www.bugcrowd.com
|
|
14
|
+
0.0.0.0 censys.io
|
|
15
|
+
0.0.0.0 www.censys.io
|
|
16
|
+
0.0.0.0 cobalt.io
|
|
17
|
+
0.0.0.0 www.cobalt.io
|
|
18
|
+
0.0.0.0 cvedetails.com
|
|
19
|
+
0.0.0.0 www.cvedetails.com
|
|
20
|
+
0.0.0.0 exploit-db.com
|
|
21
|
+
0.0.0.0 www.exploit-db.com
|
|
22
|
+
0.0.0.0 forum.hackthebox.eu
|
|
23
|
+
0.0.0.0 www.forum.hackthebox.eu
|
|
24
|
+
0.0.0.0 hackerone.com
|
|
25
|
+
0.0.0.0 www.hackerone.com
|
|
26
|
+
0.0.0.0 hackthebox.eu
|
|
27
|
+
0.0.0.0 www.hackthebox.eu
|
|
28
|
+
0.0.0.0 intigriti.com
|
|
29
|
+
0.0.0.0 www.intigriti.com
|
|
30
|
+
0.0.0.0 otx.alienvault.com
|
|
31
|
+
0.0.0.0 www.otx.alienvault.com
|
|
32
|
+
0.0.0.0 portswigger.net
|
|
33
|
+
0.0.0.0 www.portswigger.net
|
|
34
|
+
0.0.0.0 shodan.io
|
|
35
|
+
0.0.0.0 www.shodan.io
|
|
36
|
+
0.0.0.0 synack.com
|
|
37
|
+
0.0.0.0 www.synack.com
|
|
38
|
+
0.0.0.0 tryhackme.com
|
|
39
|
+
0.0.0.0 www.tryhackme.com
|
|
40
|
+
0.0.0.0 urlscan.io
|
|
41
|
+
0.0.0.0 www.urlscan.io
|
|
42
|
+
0.0.0.0 virustotal.com
|
|
43
|
+
0.0.0.0 www.virustotal.com
|
|
44
|
+
0.0.0.0 vulnhub.com
|
|
45
|
+
0.0.0.0 www.vulnhub.com
|
|
46
|
+
0.0.0.0 www.hackthebox.eu
|
|
47
|
+
0.0.0.0 yeswehack.com
|
|
48
|
+
0.0.0.0 www.yeswehack.com
|