Add IP mapped Perplexity user agents (#1393)

Perplexity has some proper documentation available for their crawlers,
with published IP addresses: https://docs.perplexity.ai/guides/bots.

Signed-off-by: Timon de Groot <timon.degroot@team.blue>

data/clients/ai.yaml

@@ -4,5 +4,5 @@
 #  - Claude-User: No published IP allowlist
 - name: "ai-clients"
   user_agent_regex: >-
-    ChatGPT-User|Claude-User|MistralAI-User
+    ChatGPT-User|Claude-User|MistralAI-User|Perplexity-User
   action: DENY

data/clients/perplexity-user.yaml

@@ -0,0 +1,12 @@
+# Acts on behalf of user requests
+# https://docs.perplexity.ai/guides/bots
+- name: perplexity-user
+  user_agent_regex: Perplexity-User/.+; \+https\://perplexity\.ai/perplexity-user
+  action: ALLOW
+  # https://www.perplexity.com/perplexity-user.json
+  remote_addresses: [
+    "44.208.221.197/32",
+    "34.193.163.52/32",
+    "18.97.21.0/30",
+    "18.97.43.80/29",
+  ]

data/crawlers/ai-search.yaml

@@ -4,5 +4,5 @@
 #  - Claude-SearchBot: No published IP allowlist
 - name: "ai-crawlers-search"
   user_agent_regex: >-
-    OAI-SearchBot|Claude-SearchBot
+    OAI-SearchBot|Claude-SearchBot|PerplexityBot
   action: DENY

data/crawlers/perplexitybot.yaml

@@ -0,0 +1,16 @@
+# Indexing for search, does not collect training data
+# https://docs.perplexity.ai/guides/bots
+- name: perplexitybot
+  user_agent_regex: PerplexityBot/.+; \+https\://perplexity\.ai/perplexitybot
+  action: ALLOW
+  # https://www.perplexity.com/perplexitybot.json
+  remote_addresses: [
+    "107.20.236.150/32",
+    "3.224.62.45/32",
+    "18.210.92.235/32",
+    "3.222.232.239/32",
+    "3.211.124.183/32",
+    "3.231.139.107/32",
+    "18.97.1.228/30",
+    "18.97.9.96/29",
+  ]

data/meta/ai-block-moderate.yaml

@@ -3,5 +3,7 @@
 - import: (data)/bots/ai-catchall.yaml
 - import: (data)/crawlers/ai-training.yaml
 - import: (data)/crawlers/openai-searchbot.yaml
+- import: (data)/crawlers/perplexitybot.yaml
 - import: (data)/clients/openai-chatgpt-user.yaml
-- import: (data)/clients/mistral-mistralai-user.yaml
+- import: (data)/clients/mistral-mistralai-user.yaml
+- import: (data)/clients/perplexity-user.yaml

data/meta/ai-block-permissive.yaml

@@ -2,5 +2,7 @@
 - import: (data)/bots/ai-catchall.yaml
 - import: (data)/crawlers/openai-searchbot.yaml
 - import: (data)/crawlers/openai-gptbot.yaml
+- import: (data)/crawlers/perplexitybot.yaml
 - import: (data)/clients/openai-chatgpt-user.yaml
-- import: (data)/clients/mistral-mistralai-user.yaml
+- import: (data)/clients/mistral-mistralai-user.yaml
+- import: (data)/clients/perplexity-user.yaml