crawler-user-agents 1.0.156 → 1.0.158

package/__init__.py

@@ -1,8 +1,25 @@
 import re
 import json
+from functools import cached_property
 from pathlib import Path
 
 
+class CrawlerPatterns:
+    def __init__(self):
+        pass
+
+    @cached_property
+    def case_insensitive(self):
+        return re.compile(
+            "|".join(i["pattern"] for i in CRAWLER_USER_AGENTS_DATA),
+            re.IGNORECASE
+        )
+
+    @cached_property
+    def case_sensitive(self):
+        return re.compile("|".join(i["pattern"] for i in CRAWLER_USER_AGENTS_DATA))
+
+
 def load_json():
     cwd = Path(__file__).parent
     user_agents_file_path = cwd / "crawler-user-agents.json"
@@ -11,24 +28,24 @@ def load_json():
 
 
 CRAWLER_USER_AGENTS_DATA = load_json()
-CRAWLER_USER_AGENTS_REGEXP = re.compile(
-    "|".join(i["pattern"] for i in CRAWLER_USER_AGENTS_DATA)
-)
+CRAWLER_PATTERNS = CrawlerPatterns()
 
 
-def is_crawler(user_agent: str) -> bool:
+def is_crawler(user_agent: str, case_sensitive: bool = True) -> bool:
     """Return True if the given User-Agent matches a known crawler."""
-    return bool(CRAWLER_USER_AGENTS_REGEXP.search(user_agent))
+    if case_sensitive:
+        return bool(re.search(CRAWLER_PATTERNS.case_sensitive, user_agent))
+    return bool(re.search(CRAWLER_PATTERNS.case_insensitive, user_agent))
 
 
-def matching_crawlers(user_agent: str) -> list[int]:
+def matching_crawlers(user_agent: str, case_sensitive: bool = True) -> list[int]:
     """
     Return a list of the indices in CRAWLER_USER_AGENTS_DATA of any crawlers
     matching the given User-Agent.
     """
     result = []
-    if is_crawler(user_agent):
+    if is_crawler(user_agent, case_sensitive):
         for num, crawler_user_agent in enumerate(CRAWLER_USER_AGENTS_DATA):
-            if re.search(crawler_user_agent["pattern"], user_agent):
+            if re.search(crawler_user_agent["pattern"], user_agent, 0 if case_sensitive else re.IGNORECASE):
                 result.append(num)
     return result

package/crawler-user-agents.json

@@ -2780,7 +2780,7 @@
     "instances": [
       "Mozilla/5.0 (compatible; seoscanners.net/1; +spider@seoscanners.net)"
     ],
-    "url": "http://www.seoscanners.net/"
+    "url": "https://github.com/monperrus/crawler-user-agents/issues/384#issuecomment-2575367162"
   },
   {
     "pattern": "Hatena",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "crawler-user-agents",
-  "version": "1.0.156",
+  "version": "1.0.158",
   "main": "crawler-user-agents.json",
   "typings": "./index.d.ts",
   "author": "Martin Monperrus <martin.monperrus@gnieh.org>",

package/test_harness.py

@@ -5,28 +5,42 @@ Usage:
 $ pytest test_harness.py
 
 """
-from crawleruseragents import is_crawler, matching_crawlers
 
+from crawleruseragents import is_crawler, matching_crawlers
 
-def test_match():
-    assert is_crawler("test Googlebot/2.0 test") is True
 
 
 def test_nomatch():
     assert is_crawler("!!!!!!!!!!!!") is False
 
 
-def test_case():
+def test_case_sensitive():
     assert is_crawler("test googlebot/2.0 test") is False
 
 
-def test_matching_crawlers_match():
+def test_case_insensitive():
+    assert is_crawler("test googlebot/2.0 test", case_sensitive=False) is True
+
+
+def test_matching_crawlers_match_case_sensitive():
     result = matching_crawlers("test Googlebot/2.0 test")
     assert isinstance(result, list)
     assert len(result) > 0
     assert all(isinstance(val, int) for val in result)
 
 
+def test_matching_crawlers_match_case_insensitive():
+    result = matching_crawlers("test googlebot/2.0 test", False)
+    assert isinstance(result, list)
+    assert len(result) > 0
+    assert all(isinstance(val, int) for val in result)
+
+def test_matching_crawlers_match_lower_case_agent():
+    result = matching_crawlers("test googlebot/2.0 test")
+    assert isinstance(result, list)
+    assert len(result) == 0
+
+
 def test_matching_crawlers_nomatch():
     result = matching_crawlers("!!!!!!!!!!!!")
     assert isinstance(result, list)