实现日志记录以增强调试和监控

在`guard.py`和`link_filter.py`模块中集成日志记录功能，以促进更好的调试和运行时监控。添加了`logger`实例，并在关键操作中散布日志条目，记录消息处理、链接过滤决策和配置加载等活动。

src/guard.py

@@ -7,6 +7,11 @@ from collections import deque
 import time
 from link_filter import LinkFilter
 from bot_commands import handle_command
+import logging
+
+# 设置日志
+logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+logger = logging.getLogger('TeleGuard')
 
 # 环境变量
 BOT_TOKEN = os.environ.get('BOT_TOKEN')
@@ -50,16 +55,18 @@ async def delete_message_after_delay(client, chat, message, delay):
 
 async def process_message(event, client):
     if not event.is_private:
+        logger.debug(f"Processing message: {event.message.text}")
         should_filter, new_links = link_filter.should_filter(event.message.text)
         if should_filter:
+            logger.info(f"Message should be filtered: {event.message.text}")
             if event.sender_id != ADMIN_ID:
                 await event.delete()
                 notification = await event.respond("已撤回该消息。注:包含关键词或重复发送的非白名单链接会被自动撤回。")
                 asyncio.create_task(delete_message_after_delay(client, event.chat_id, notification, 3 * 60))
             return
         if new_links:
-            # 可以在这里添加日志记录或其他操作
-            pass
+            logger.info(f"New non-whitelisted links found: {new_links}")
+
 
 async def command_handler(event, link_filter):
     if event.is_private and event.sender_id == ADMIN_ID:

src/link_filter.py

@@ -2,6 +2,10 @@ import re
 import json
 import tldextract
 import urllib.parse
+import logging
+
+logger = logging.getLogger('TeleGuard.LinkFilter')
+
 
 class LinkFilter:
     def __init__(self, keywords_file, whitelist_file):
@@ -16,15 +20,17 @@ class LinkFilter:
             (?:
                 (?:https?://)?                     # http:// or https:// (optional)
                 (?:(?:www\.)?                      # www. (optional)
-                   (?:[a-zA-Z0-9-]+\.)+            # domain
-                   [a-zA-Z]{2,}                    # TLD
-                   |                               # or
-                   (?:t\.me|telegram\.me)          # Telegram links
+                (?:[a-zA-Z0-9-]+\.)+            # domain
+                [a-zA-Z]{2,}                    # TLD
+                |                               # or
+                (?:t\.me|telegram\.me)          # Telegram links
                 )
                 (?:/[^\s]*)?                       # optional path and query string
             )
             \b
         ''', re.VERBOSE | re.IGNORECASE)
+        logger.info(f"LinkFilter initialized with keywords file: {keywords_file} and whitelist file: {whitelist_file}")
+
 
     def load_json(self, file_path):
         try:
@@ -50,12 +56,17 @@ class LinkFilter:
     def normalize_link(self, link):
         link = re.sub(r'^https?://', '', link)
         parsed = urllib.parse.urlparse(f"http://{link}")
-        return urllib.parse.urlunparse(('', parsed.netloc, parsed.path, parsed.params, parsed.query, '')).rstrip('/')
+        normalized = urllib.parse.urlunparse(('', parsed.netloc, parsed.path, parsed.params, parsed.query, ''))
+        result = normalized.rstrip('/')
+        logger.debug(f"Normalized link: {link} -> {result}")
+        return result
 
     def is_whitelisted(self, link):
         extracted = tldextract.extract(link)
         domain = f"{extracted.domain}.{extracted.suffix}"
-        return domain in self.whitelist
+        result = domain in self.whitelist
+        logger.debug(f"Whitelist check for {link}: {'Passed' if result else 'Failed'}")
+        return result
 
     def add_keyword(self, keyword):
         if self.link_pattern.match(keyword):
@@ -63,6 +74,9 @@ class LinkFilter:
         if keyword not in self.keywords:
             self.keywords.append(keyword)
             self.save_keywords()
+            logger.info(f"New keyword added: {keyword}")
+        else:
+            logger.debug(f"Keyword already exists: {keyword}")
 
     def remove_keyword(self, keyword):
         if self.link_pattern.match(keyword):
@@ -74,18 +88,25 @@ class LinkFilter:
         return False
 
     def should_filter(self, text):
+        logger.debug(f"Checking text: {text}")
         if any(keyword.lower() in text.lower() for keyword in self.keywords):
+            logger.info(f"Text contains keyword: {text}")
             return True, []
 
         links = self.link_pattern.findall(text)
+        logger.debug(f"Found links: {links}")
         new_non_whitelisted_links = []
         for link in links:
             normalized_link = self.normalize_link(link)
             if not self.is_whitelisted(normalized_link):
+                logger.debug(f"Link not whitelisted: {normalized_link}")
                 if normalized_link not in self.keywords:
                     new_non_whitelisted_links.append(normalized_link)
                     self.add_keyword(normalized_link)
                 else:
+                    logger.info(f"Existing keyword found: {normalized_link}")
                     return True, []
         
+        if new_non_whitelisted_links:
+            logger.info(f"New non-whitelisted links found: {new_non_whitelisted_links}")
         return False, new_non_whitelisted_links