crawlo 1.4.6__py3-none-any.whl → 1.4.8__py3-none-any.whl

crawlo/__init__.py

@@ -7,7 +7,7 @@ Crawlo - 一个异步爬虫框架
 # 为了向后兼容，从tools中导入cleaners相关的功能
 import crawlo.tools as cleaners
 from crawlo import tools
-from crawlo.crawler import CrawlerProcess
+from crawlo.crawler import Crawler, CrawlerProcess
 from crawlo.downloader import DownloaderBase
 from crawlo.items import Item, Field
 from crawlo.middleware import BaseMiddleware
@@ -82,6 +82,7 @@ __all__ = [
     'from_timestamp_with_tz',
     'cleaners',
     'tools',
+    'Crawler',
     'CrawlerProcess',
     'get_framework_initializer',
     'get_bootstrap_manager',

crawlo/__version__.py

@@ -1 +1 @@
-__version__ = '1.4.6'
+__version__ = '1.4.8'

crawlo/cli.py

@@ -4,12 +4,12 @@
 import sys
 import argparse
 from crawlo.commands import get_commands
-from crawlo.utils.env_config import get_version
+from crawlo.utils.config_manager import EnvConfigManager
 
 
 def main():
     # 获取框架版本号
-    VERSION = get_version()
+    VERSION = EnvConfigManager.get_version()
 
     # 获取所有可用命令
     commands = get_commands()

crawlo/commands/check.py

@@ -24,7 +24,7 @@ from watchdog.observers import Observer
 from watchdog.events import FileSystemEventHandler
 
 from crawlo.crawler import CrawlerProcess
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 
 
 logger = get_logger(__name__)

crawlo/commands/help.py

@@ -11,10 +11,10 @@ from rich.table import Table
 from rich.panel import Panel
 from rich.text import Text
 from rich import box
-from crawlo.utils.env_config import get_version
+from crawlo.utils.config_manager import EnvConfigManager
 
 # 获取框架版本号
-VERSION = get_version()
+VERSION = EnvConfigManager.get_version()
 
 console = Console()
 
@@ -85,11 +85,13 @@ def show_help():
     
     # run 命令
     console.print("[bold cyan]run[/bold cyan] - 运行爬虫")
-    console.print("  用法: crawlo run <spider_name>|all [--json] [--no-stats]")
+    console.print("  用法: crawlo run <spider_name>|all [--json] [--no-stats] [--log-level LEVEL] [--config CONFIG] [--concurrency NUM]")
     console.print("  示例:")
     console.print("    crawlo run myspider")
     console.print("    crawlo run all")
     console.print("    crawlo run all --json --no-stats")
+    console.print("    crawlo run myspider --log-level DEBUG")
+    console.print("    crawlo run myspider --concurrency 32")
     console.print()
     
 

crawlo/commands/list.py

@@ -16,7 +16,7 @@ from rich.text import Text
 from rich import box
 
 from crawlo.crawler import CrawlerProcess
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 from .utils import validate_project_environment, show_error_panel
 
 logger = get_logger(__name__)

crawlo/commands/run.py

@@ -24,7 +24,7 @@ from crawlo.project import get_settings, _find_project_root
 # 使用新的统一初始化系统
 from crawlo.initialization import initialize_framework
 from crawlo.core import get_framework_initializer
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 
 # 延迟获取logger，确保在日志系统配置之后获取
 _logger = None
@@ -89,7 +89,7 @@ def main(args):
     """
     主函数：运行指定爬虫
     用法:
-        crawlo run <spider_name>|all [--json] [--no-stats]
+        crawlo run <spider_name>|all [--json] [--no-stats] [--log-level LEVEL] [--config CONFIG] [--concurrency NUM]
     """
     # 确保框架已初始化
     init_manager = get_framework_initializer()
@@ -99,7 +99,7 @@ def main(args):
 
     if len(args) < 1:
         console.print(
-            "[bold red]用法:[/bold red] [blue]crawlo run[/blue] <爬虫名称>|all [bold yellow][--json] [--no-stats][/bold yellow]")
+            "[bold red]用法:[/bold red] [blue]crawlo run[/blue] <爬虫名称>|all [bold yellow][--json] [--no-stats] [--log-level LEVEL] [--config CONFIG] [--concurrency NUM][/bold yellow]")
         console.print("示例:")
         console.print("   [blue]crawlo run baidu[/blue]")
         console.print("   [blue]crawlo run all[/blue]")
@@ -110,6 +110,36 @@ def main(args):
     spider_arg = args[0]
     show_json = "--json" in args
     no_stats = "--no-stats" in args
+    
+    # 解析日志级别参数
+    log_level = None
+    if "--log-level" in args:
+        try:
+            log_level_index = args.index("--log-level")
+            if log_level_index + 1 < len(args):
+                log_level = args[log_level_index + 1]
+        except (ValueError, IndexError):
+            pass
+    
+    # 解析配置文件参数
+    config_file = None
+    if "--config" in args:
+        try:
+            config_index = args.index("--config")
+            if config_index + 1 < len(args):
+                config_file = args[config_index + 1]
+        except (ValueError, IndexError):
+            pass
+    
+    # 解析并发数参数
+    concurrency = None
+    if "--concurrency" in args:
+        try:
+            concurrency_index = args.index("--concurrency")
+            if concurrency_index + 1 < len(args):
+                concurrency = int(args[concurrency_index + 1])
+        except (ValueError, IndexError, TypeError):
+            pass
 
     try:
         # 1. 查找项目根目录
@@ -171,7 +201,14 @@ def main(args):
                 return 1
 
         # 4. 启动框架并加载 settings
-        settings = initialize_framework()
+        # 如果指定了日志级别，则添加到自定义设置中
+        custom_settings = {}
+        if log_level:
+            custom_settings['LOG_LEVEL'] = log_level
+        if concurrency:
+            custom_settings['CONCURRENCY'] = concurrency
+        
+        settings = initialize_framework(custom_settings if custom_settings else None)
 
         # 检查Redis连接（如果是分布式模式）
         if not check_redis_connection(settings):
@@ -183,7 +220,7 @@ def main(args):
 
         # 从配置中获取SPIDER_MODULES
         spider_modules = settings.get('SPIDER_MODULES', [f"{project_package}.spiders"])
-        logger().debug(f"SPIDER_MODULES from settings: {spider_modules}")
+        # 合并重复的调试信息
         process = CrawlerProcess(settings=settings, spider_modules=spider_modules)
         
         # 不再需要手动导入爬虫模块，框架内部会自动处理
@@ -191,11 +228,11 @@ def main(args):
         from crawlo.spider import get_global_spider_registry
         registry = get_global_spider_registry()
         spider_names = list(registry.keys())
-        logger().debug(f"Registered spiders after import: {spider_names}")
-        
-        # 调试信息
-        logger().debug(f"SPIDER_MODULES: {spider_modules}")
-        logger().debug(f"Available spiders: {process.get_spider_names()}")
+        # 减少重复的调试日志输出
+        # logger().debug(f"SPIDER_MODULES from settings: {spider_modules}")
+        # logger().debug(f"Registered spiders after import: {spider_names}")
+        # logger().debug(f"SPIDER_MODULES: {spider_modules}")
+        # logger().debug(f"Available spiders: {process.get_spider_names()}")
 
         # === 情况1：运行所有爬虫 ===
         if spider_arg.lower() == "all":
@@ -260,7 +297,8 @@ def main(args):
                     panel_content.append("\n可用爬虫:\n")
                     for name in sorted(available):
                         cls = process.get_spider_class(name)
-                        panel_content.append(f"  • [cyan]{name}[/cyan] ([green]{cls.__name__}[/green])\n")
+                        class_name = cls.__name__ if cls else 'Unknown'
+                        panel_content.append(f"  • [cyan]{name}[/cyan] ([green]{class_name}[/green])\n")
                 else:
                     panel_content.append("\n未找到爬虫。请检查爬虫模块。")
 

crawlo/commands/stats.py

@@ -16,7 +16,7 @@ from rich.panel import Panel
 from rich.text import Text
 from rich import box
 
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 
 
 logger = get_logger(__name__)

crawlo/config.py

@@ -23,7 +23,7 @@ from typing import Dict, Any, Optional
 
 from crawlo.config_validator import validate_config
 from crawlo.mode_manager import standalone_mode, distributed_mode, auto_mode, from_env
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 
 
 class CrawloConfig:
@@ -51,13 +51,21 @@ class CrawloConfig:
         return self.settings.get(key, default)
     
     def set(self, key: str, value: Any) -> 'CrawloConfig':
-        """设置配置项（链式调用）"""
+        """设置配置项（链式调用）
+        
+        注意：设置后会自动验证配置合法性
+        """
         self.settings[key] = value
+        self._validate_settings()  # 自动验证
         return self
     
     def update(self, settings: Dict[str, Any]) -> 'CrawloConfig':
-        """更新配置（链式调用）"""
+        """更新配置（链式调用）
+        
+        注意：更新后会自动验证配置合法性
+        """
         self.settings.update(settings)
+        self._validate_settings()  # 自动验证
         return self
     
     def set_concurrency(self, concurrency: int) -> 'CrawloConfig':
@@ -95,7 +103,7 @@ class CrawloConfig:
             'auto': '自动检测模式'
         }
         
-        queue_type = self.settings.get('QUEUE_TYPE', 'memory')
+        queue_type = self.settings.get('QUEUE_TYPE', 'auto')
         filter_class = self.settings.get('FILTER_CLASS', '').split('.')[-1]
         concurrency = self.settings.get('CONCURRENCY', 8)
         

crawlo/config_validator.py

@@ -7,7 +7,7 @@
 """
 from typing import Dict, Any, List, Tuple
 
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 
 
 class ConfigValidator:

crawlo/core/engine.py

@@ -9,13 +9,13 @@ from crawlo import Request, Item
 from crawlo.core.processor import Processor
 from crawlo.core.scheduler import Scheduler
 from crawlo.downloader import DownloaderBase
-from crawlo.event import spider_opened, spider_error, request_scheduled
+from crawlo.event import CrawlerEvent
 from crawlo.exceptions import OutputError
 from crawlo.utils.misc import load_object
 from crawlo.spider import Spider
 from crawlo.task_manager import TaskManager
 from crawlo.utils.func_tools import transform
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 
 
 class Engine(object):
@@ -94,6 +94,17 @@ class Engine(object):
             else:
                 # DownloaderBase.open() 是同步方法，直接调用而不是await
                 self.downloader.open()
+        
+        # 注册下载器到资源管理器
+        if hasattr(self.crawler, '_resource_manager') and self.downloader:
+            from crawlo.utils.resource_manager import ResourceType
+            self.crawler._resource_manager.register(
+                self.downloader,
+                lambda d: d.close() if hasattr(d, 'close') else None,
+                ResourceType.DOWNLOADER,
+                name=f"downloader.{downloader_cls.__name__}"
+            )
+            self.logger.debug(f"Downloader registered to resource manager: {downloader_cls.__name__}")
 
         self.processor = Processor(self.crawler)
         if hasattr(self.processor, 'open'):
@@ -188,11 +199,13 @@ class Engine(object):
         while self.running:
             try:
                 start_request = next(self.start_requests)
-                self.logger.debug(f"获取到请求: {getattr(start_request, 'url', 'Unknown URL')}")
+                # 将过于频繁的debug日志合并，减少输出
+                # self.logger.debug(f"获取到请求: {getattr(start_request, 'url', 'Unknown URL')}")
                 # 请求入队
                 await self.enqueue_request(start_request)
                 processed_count += 1
-                self.logger.debug(f"已处理请求数量: {processed_count}")
+                # 减少过于频繁的日志输出
+                # self.logger.debug(f"已处理请求数量: {processed_count}")
             except StopIteration:
                 self.logger.debug("所有起始请求处理完成")
                 self.start_requests = None
@@ -306,7 +319,7 @@ class Engine(object):
             wait_time = min(wait_time * 1.1, max_wait)
 
     async def _open_spider(self):
-        asyncio.create_task(self.crawler.subscriber.notify(spider_opened))
+        asyncio.create_task(self.crawler.subscriber.notify(CrawlerEvent.SPIDER_OPENED))
         # 直接调用crawl方法而不是创建任务，确保等待完成
         await self.crawl()
 
@@ -364,7 +377,7 @@ class Engine(object):
     async def _schedule_request(self, request):
         # TODO 去重
         if await self.scheduler.enqueue_request(request):
-            asyncio.create_task(self.crawler.subscriber.notify(request_scheduled, request, self.crawler.spider))
+            asyncio.create_task(self.crawler.subscriber.notify(CrawlerEvent.REQUEST_SCHEDULED, request, self.crawler.spider))
 
     async def _get_next_request(self):
         return await self.scheduler.next_request()
@@ -375,7 +388,7 @@ class Engine(object):
                 await self.processor.enqueue(spider_output)
             elif isinstance(spider_output, Exception):
                 asyncio.create_task(
-                    self.crawler.subscriber.notify(spider_error, spider_output, self.spider)
+                    self.crawler.subscriber.notify(CrawlerEvent.SPIDER_ERROR, spider_output, self.spider)
                 )
                 raise spider_output
             else:

crawlo/core/processor.py

@@ -4,7 +4,7 @@ from asyncio import Queue, create_task
 from typing import Union, Optional
 
 from crawlo import Request, Item
-from crawlo.event import item_discard
+from crawlo.event import CrawlerEvent
 from crawlo.exceptions import ItemDiscard
 from crawlo.pipelines.pipeline_manager import PipelineManager
 

crawlo/core/scheduler.py

@@ -3,7 +3,7 @@
 import traceback
 from typing import Optional, Callable
 
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 from crawlo.utils.request import set_request
 from crawlo.utils.error_handler import ErrorHandler
 from crawlo.utils.misc import load_object
@@ -13,13 +13,13 @@ from crawlo.queue.queue_manager import QueueManager, QueueConfig, QueueType
 
 
 class Scheduler:
-    def __init__(self, crawler, dupe_filter, stats, log_level, priority):
+    def __init__(self, crawler, dupe_filter, stats, priority):
         self.crawler = crawler
         self.queue_manager: Optional[QueueManager] = None
         self.request_serializer = RequestSerializer()
 
-        self.logger = get_logger(name=self.__class__.__name__, level=log_level)
-        self.error_handler = ErrorHandler(self.__class__.__name__, log_level)
+        self.logger = get_logger(self.__class__.__name__)
+        self.error_handler = ErrorHandler(self.__class__.__name__)
         self.stats = stats
         self.dupe_filter = dupe_filter
         self.priority = priority
@@ -31,7 +31,6 @@ class Scheduler:
             crawler=crawler,
             dupe_filter=filter_cls.create_instance(crawler),
             stats=crawler.stats,
-            log_level=crawler.settings.get('LOG_LEVEL'),
             priority=crawler.settings.get('DEPTH_PRIORITY')
         )
         return o

crawlo/crawler.py

@@ -1,14 +1,19 @@
 #!/usr/bin/python
 # -*- coding: UTF-8 -*-
 """
-重构后的Crawler系统
-==================
+Crawler系统
+==========
+
+核心组件：
+- Crawler: 爬虫核心控制器，负责单个爬虫的生命周期管理
+- CrawlerProcess: 爬虫进程管理器，支持单个/多个爬虫运行
 
 设计原则：
 1. 单一职责 - 每个类只负责一个明确的功能
 2. 依赖注入 - 通过工厂创建组件，便于测试
 3. 状态管理 - 清晰的状态转换和生命周期
 4. 错误处理 - 优雅的错误处理和恢复机制
+5. 资源管理 - 统一的资源注册和清理机制
 """
 
 import asyncio
@@ -21,6 +26,7 @@ from typing import Optional, Type, Dict, Any, List
 from crawlo.logging import get_logger
 from crawlo.factories import get_component_registry
 from crawlo.initialization import initialize_framework, is_framework_ready
+from crawlo.utils.resource_manager import ResourceManager, ResourceType
 
 
 class CrawlerState(Enum):
@@ -55,15 +61,16 @@ class CrawlerMetrics:
         return (self.success_count / total * 100) if total > 0 else 0.0
 
 
-class ModernCrawler:
+class Crawler:
     """
-    现代化的Crawler实现
+    爬虫核心控制器
     
     特点：
     1. 清晰的状态管理
     2. 依赖注入
     3. 组件化架构
     4. 完善的错误处理
+    5. 统一的资源管理
     """
     
     def __init__(self, spider_cls: Type, settings=None):
@@ -82,6 +89,9 @@ class ModernCrawler:
         # 指标
         self._metrics = CrawlerMetrics()
         
+        # 资源管理器
+        self._resource_manager = ResourceManager(name=f"crawler.{spider_cls.__name__ if spider_cls else 'unknown'}")
+        
         # 日志
         self._logger = get_logger(f'crawler.{spider_cls.__name__ if spider_cls else "unknown"}')
         
@@ -209,6 +219,14 @@ class ModernCrawler:
             
             # 创建Engine（需要crawler参数）
             self._engine = registry.create('engine', crawler=self)
+            # 注册Engine到资源管理器
+            if self._engine and hasattr(self._engine, 'close'):
+                self._resource_manager.register(
+                    self._engine,
+                    lambda e: e.close() if hasattr(e, 'close') else None,
+                    ResourceType.OTHER,
+                    name="engine"
+                )
             
             # 创建Stats（需要crawler参数）
             self._stats = registry.create('stats', crawler=self)
@@ -291,7 +309,15 @@ class ModernCrawler:
                 self._state = CrawlerState.CLOSING
         
         try:
-            # 关闭各个组件
+            # 使用资源管理器统一清理
+            self._logger.debug("开始清理Crawler资源...")
+            cleanup_result = await self._resource_manager.cleanup_all()
+            self._logger.debug(
+                f"资源清理完成: {cleanup_result['success']}成功, "
+                f"{cleanup_result['errors']}失败, 耗时{cleanup_result['duration']:.2f}s"
+            )
+            
+            # 关闭各个组件（继续兼容旧逻辑）
             if self._engine and hasattr(self._engine, 'close'):
                 try:
                     await self._engine.close()
@@ -318,7 +344,9 @@ class ModernCrawler:
             
             # 触发spider_closed事件，通知所有订阅者（包括扩展）
             # 传递reason参数，这里使用默认的'finished'作为reason
-            await self.subscriber.notify("spider_closed", reason='finished')
+            if self.subscriber:
+                from crawlo.event import CrawlerEvent
+                await self.subscriber.notify(CrawlerEvent.SPIDER_CLOSED, reason='finished')
             
             if self._stats and hasattr(self._stats, 'close'):
                 try:
@@ -348,7 +376,7 @@ class CrawlerProcess:
         # 初始化框架配置
         self._settings = settings or initialize_framework()
         self._max_concurrency = max_concurrency
-        self._crawlers: List[ModernCrawler] = []
+        self._crawlers: List[Crawler] = []
         self._semaphore = asyncio.Semaphore(max_concurrency)
         self._logger = get_logger('crawler.process')
         
@@ -497,7 +525,7 @@ class CrawlerProcess:
         logger.info(f"Starting spider: {spider_cls.name}")
         
         merged_settings = self._merge_settings(settings)
-        crawler = ModernCrawler(spider_cls, merged_settings)
+        crawler = Crawler(spider_cls, merged_settings)
         
         async with self._semaphore:
             await crawler.crawl()
@@ -526,7 +554,7 @@ class CrawlerProcess:
             tasks = []
             for spider_cls in spider_classes:
                 merged_settings = self._merge_settings(settings)
-                crawler = ModernCrawler(spider_cls, merged_settings)
+                crawler = Crawler(spider_cls, merged_settings)
                 self._crawlers.append(crawler)
                 
                 task = asyncio.create_task(self._run_with_semaphore(crawler))
@@ -543,12 +571,25 @@ class CrawlerProcess:
             return results
             
         finally:
+            # 清理所有crawler，防止资源累积
+            self._logger.debug(f"Cleaning up {len(self._crawlers)} crawler(s)...")
+            for crawler in self._crawlers:
+                try:
+                    # 确保每个crawler都被清理
+                    if hasattr(crawler, '_resource_manager'):
+                        await crawler._resource_manager.cleanup_all()
+                except Exception as e:
+                    self._logger.warning(f"Failed to cleanup crawler: {e}")
+            
+            # 清空crawlers列表，释放引用
+            self._crawlers.clear()
+            
             self._end_time = time.time()
             if self._start_time:
                 duration = self._end_time - self._start_time
                 self._logger.info(f"Total execution time: {duration:.2f}s")
     
-    async def _run_with_semaphore(self, crawler: ModernCrawler):
+    async def _run_with_semaphore(self, crawler: Crawler):
         """在信号量控制下运行爬虫"""
         async with self._semaphore:
             await crawler.crawl()

crawlo/downloader/__init__.py

@@ -18,7 +18,7 @@ from abc import abstractmethod, ABCMeta
 from typing import Final, Set, Optional, TYPE_CHECKING
 from contextlib import asynccontextmanager
 
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 from crawlo.middleware.middleware_manager import MiddlewareManager
 
 if TYPE_CHECKING:
@@ -68,12 +68,16 @@ class ActivateRequestManager:
     
     def get_stats(self) -> dict:
         """获取请求统计信息"""
+        completed = self._completed_requests + self._failed_requests
         return {
             'active_requests': len(self._active),
             'total_requests': self._total_requests,
             'completed_requests': self._completed_requests,
             'failed_requests': self._failed_requests,
-            'success_rate': self._completed_requests / max(1, self._total_requests - len(self._active))
+            'success_rate': (
+                self._completed_requests / completed * 100 
+                if completed > 0 else 100.0  # 无完成请求时返回100%
+            )
         }
     
     def reset_stats(self):
@@ -104,7 +108,7 @@ class DownloaderBase(metaclass=DownloaderMeta):
         self.crawler = crawler
         self._active = ActivateRequestManager()
         self.middleware: Optional[MiddlewareManager] = None
-        self.logger = get_logger(self.__class__.__name__, crawler.settings.get("LOG_LEVEL"))
+        self.logger = get_logger(self.__class__.__name__)
         self._closed = False
         self._stats_enabled = crawler.settings.get_bool("DOWNLOADER_STATS", True)
 

crawlo/downloader/aiohttp_downloader.py

@@ -1,5 +1,6 @@
 #!/usr/bin/python
 # -*- coding: UTF-8 -*-
+import asyncio
 from yarl import URL
 from typing import Optional
 from aiohttp import (
@@ -13,7 +14,7 @@ from aiohttp import (
 )
 
 from crawlo.network.response import Response
-from crawlo.utils.log import get_logger
+from crawlo.logging import get_logger
 from crawlo.downloader import DownloaderBase
 
 
@@ -31,7 +32,7 @@ class AioHttpDownloader(DownloaderBase):
         super().__init__(crawler)
         self.session: Optional[ClientSession] = None
         self.max_download_size: int = 0
-        self.logger = get_logger(self.__class__.__name__, crawler.settings.get("LOG_LEVEL"))
+        self.logger = get_logger(self.__class__.__name__)
 
     def open(self):
         super().open()
@@ -80,9 +81,6 @@ class AioHttpDownloader(DownloaderBase):
         # 输出下载器配置摘要
         spider_name = getattr(self.crawler.spider, 'name', 'Unknown')
         concurrency = self.crawler.settings.get('CONCURRENCY', 4)
-        # self.logger.debug(f"下载器初始化完成 [爬虫: {spider_name}, 类型: {self.__class__.__name__}, 并发数: {concurrency}]")  # 注释掉重复的日志
-
-        # self.logger.debug("AioHttpDownloader initialized.")  # 注释掉重复的日志
 
     async def download(self, request) -> Optional[Response]:
         """下载请求并返回响应"""
@@ -206,28 +204,30 @@ class AioHttpDownloader(DownloaderBase):
     # --- 请求追踪日志 ---
     async def _on_request_start(self, session, trace_config_ctx, params):
         """请求开始时的回调。"""
-        # proxy = getattr(params, "proxy", None)
-        # proxy_info = f" via {proxy}" if proxy else ""
-        # self.logger.debug(f"Requesting: {params.method} {params.url}{proxy_info}")  # 注释掉过于详细的日志
+        pass
 
     async def _on_request_end(self, session, trace_config_ctx, params):
         """请求成功结束时的回调。"""
-        # response = params.response
-        # self.logger.debug(
-        #     f"Finished: {params.method} {params.url} with status {response.status}"
-        # )  # 注释掉过于详细的日志
+        pass
 
     async def _on_request_exception(self, session, trace_config_ctx, params):
         """请求发生异常时的回调。"""
-        # exc = params.exception
-        # self.logger.warning(
-        #     f"Failed: {params.method} {params.url} with exception {type(exc).__name__}: {exc}"
-        # )  # 注释掉过于详细的日志
+        pass
 
     async def close(self) -> None:
         """关闭会话资源"""
         if self.session and not self.session.closed:
-            # 恢复关键的下载器关闭信息为INFO级别
             self.logger.info("Closing AioHttpDownloader session...")
-            await self.session.close()
+            try:
+                # 关闭 session
+                await self.session.close()
+                
+                # 等待一小段时间确保连接完全关闭
+                # 参考: https://docs.aiohttp.org/en/stable/client_advanced.html#graceful-shutdown
+                await asyncio.sleep(0.25)
+            except Exception as e:
+                self.logger.warning(f"Error during session close: {e}")
+            finally:
+                self.session = None
+        
         self.logger.debug("AioHttpDownloader closed.")