From 54a2b553f46df6dc98a4b8410788e35165e0fa3e Mon Sep 17 00:00:00 2001
From: mggh0139 <223163273+mggh0139@users.noreply.github.com>
Date: Mon, 28 Jul 2025 01:03:01 -0400
Subject: [PATCH] [fix] tracker pattern: let startup continue if url fetch
 fails (#5055)

Use Python exception to prevent startup crash in case of fetch ClearURL
failure. Also add some logs.

Closes: https://github.com/searxng/searxng/issues/5054
---
 searx/data/tracker_patterns.py | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/searx/data/tracker_patterns.py b/searx/data/tracker_patterns.py
index 31b0af9b1..544031f4e 100644
--- a/searx/data/tracker_patterns.py
+++ b/searx/data/tracker_patterns.py
@@ -10,6 +10,8 @@ import re
 from collections.abc import Iterator
 from urllib.parse import urlparse, urlunparse, parse_qsl, urlencode
 
+from httpx import HTTPError
+
 from searx.data.core import get_cache, log
 from searx.network import get as http_get
 
@@ -70,10 +72,19 @@ class TrackerPatternsDB:
     def iter_clear_list(self) -> Iterator[RuleType]:
         resp = None
         for url in self.CLEAR_LIST_URL:
-            resp = http_get(url, timeout=3)
-            if resp.status_code == 200:
-                break
-            log.warning(f"TRACKER_PATTERNS: ClearURL ignore HTTP {resp.status_code} {url}")
+            log.debug("TRACKER_PATTERNS: Trying to fetch %s...", url)
+            try:
+                resp = http_get(url, timeout=3)
+
+            except HTTPError as exc:
+                log.warning("TRACKER_PATTERNS: HTTPError (%s) occured while fetching %s", url, exc)
+                continue
+
+            if resp.status_code != 200:
+                log.warning(f"TRACKER_PATTERNS: ClearURL ignore HTTP {resp.status_code} {url}")
+                continue
+
+            break
 
         if resp is None:
             log.error("TRACKER_PATTERNS: failed fetching ClearURL rule lists")