patterns json: add support for GroupMe bot (#359)

__init__.py

@@ -1,22 +1,25 @@
-import crawleruseragents
 import re
 import json
-from importlib import resources 
-
+from pathlib import Path
+
+
 def load_json():
-  return json.loads(resources.read_text(crawleruseragents,"crawler-user-agents.json"))
+    cwd = Path(__file__).parent
+    user_agents_file_path = cwd / "crawler-user-agents.json"
+    with user_agents_file_path.open() as patterns_file:
+        return json.load(patterns_file)
 
-DATA = load_json()
 
-def is_crawler(s):
-  # print(s)
-  for i in DATA:
-    test=re.search(i["pattern"],s,re.IGNORECASE)
-    if test:
-      return True
-  return False
+CRAWLER_USER_AGENTS_DATA = load_json()
 
-def is_crawler2(s):
-  regexp = re.compile("|".join([i["pattern"] for i in DATA]))
-  return regexp.search(s) != None
 
+def is_crawler(user_agent: str) -> bool:
+    for crawler_user_agent in CRAWLER_USER_AGENTS_DATA:
+        if re.search(crawler_user_agent["pattern"], user_agent, re.IGNORECASE):
+            return True
+    return False
+
+
+def is_crawler2(s):
+    regexp = re.compile("|".join([i["pattern"] for i in CRAWLER_USER_AGENTS_DATA]))
+    return regexp.search(s) is not None

crawler-user-agents.json

@@ -12,8 +12,7 @@
       "Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.96 Mobile Safari/537.36 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)",
       "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Googlebot/2.1; +http://www.google.com/bot.html) Safari/537.36"
     ]
-  }
-  ,
+  },
   {
     "pattern": "Googlebot-Mobile",
     "instances": [
@@ -5314,5 +5313,11 @@
     "addition_date": "2024/05/14",
     "instances": ["Mozilla/5.0 (compatible; Monsidobot/2.2; +http://monsido.com/bot.html; [email protected])"],
     "url": "http://monsido.com/bot.html"
+  },
+  {
+    "pattern": "GroupMeBot",
+    "addition_date": "2024/05/19",
+    "instances": ["GroupMeBot/1.0"],
+    "url": "https://groupme.com/"
   }
 ]