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/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",
+  ]