crawlo 1.1.1__py3-none-any.whl → 1.1.3__py3-none-any.whl

crawlo/pipelines/mysql_pipeline.py

@@ -1,195 +1,195 @@
-# -*- coding: utf-8 -*-
-import asyncio
-import aiomysql
-from typing import Optional
-from asyncmy import create_pool
-from crawlo.utils.log import get_logger
-from crawlo.exceptions import ItemDiscard
-from crawlo.utils.db_helper import make_insert_sql, logger
-
-
-class AsyncmyMySQLPipeline:
-    def __init__(self, crawler):
-        self.crawler = crawler
-        self.settings = crawler.settings
-        self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
-
-        # 使用异步锁和初始化标志确保线程安全
-        self._pool_lock = asyncio.Lock()
-        self._pool_initialized = False
-        self.pool = None
-        self.table_name = (
-                self.settings.get('MYSQL_TABLE') or
-                getattr(crawler.spider, 'mysql_table', None) or
-                f"{crawler.spider.name}_items"
-        )
-
-        # 注册关闭事件
-        crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
-
-    @classmethod
-    def from_crawler(cls, crawler):
-        return cls(crawler)
-
-    async def _ensure_pool(self):
-        """确保连接池已初始化（线程安全）"""
-        if self._pool_initialized:
-            return
-
-        async with self._pool_lock:
-            if not self._pool_initialized:  # 双重检查避免竞争条件
-                try:
-                    self.pool = await create_pool(
-                        host=self.settings.get('MYSQL_HOST', 'localhost'),
-                        port=self.settings.get_int('MYSQL_PORT', 3306),
-                        user=self.settings.get('MYSQL_USER', 'root'),
-                        password=self.settings.get('MYSQL_PASSWORD', ''),
-                        db=self.settings.get('MYSQL_DB', 'scrapy_db'),
-                        minsize=self.settings.get_int('MYSQL_POOL_MIN', 3),
-                        maxsize=self.settings.get_int('MYSQL_POOL_MAX', 10),
-                        echo=self.settings.get_bool('MYSQL_ECHO', False)
-                    )
-                    self._pool_initialized = True
-                    self.logger.debug(f"MySQL连接池初始化完成（表: {self.table_name}）")
-                except Exception as e:
-                    self.logger.error(f"MySQL连接池初始化失败: {e}")
-                    raise
-
-    async def process_item(self, item, spider, kwargs=None) -> Optional[dict]:
-        """处理item的核心方法"""
-        kwargs = kwargs or {}
-        spider_name = getattr(spider, 'name', 'unknown')  # 获取爬虫名称
-        try:
-            await self._ensure_pool()
-            item_dict = dict(item)
-            sql = make_insert_sql(table=self.table_name, data=item_dict, **kwargs)
-
-            rowcount = await self._execute_sql(sql=sql)
-            if rowcount > 1:
-                self.logger.info(
-                    f"爬虫 {spider_name} 成功插入 {rowcount} 条记录到表 {self.table_name}"
-                )
-            elif rowcount == 1:
-                self.logger.debug(
-                    f"爬虫 {spider_name} 成功插入单条记录到表 {self.table_name}"
-                )
-            else:
-                self.logger.warning(
-                    f"爬虫 {spider_name}: SQL执行成功但未插入新记录 - {sql[:100]}..."
-                )
-
-            return item
-
-        except Exception as e:
-            self.logger.error(f"处理item时发生错误: {e}")
-            raise ItemDiscard(f"处理失败: {e}")
-
-    async def _execute_sql(self, sql: str, values: list = None) -> int:
-        """执行SQL语句并处理结果"""
-        async with self.pool.acquire() as conn:
-            async with conn.cursor() as cursor:
-                try:
-                    # 根据是否有参数值选择不同的执行方法
-                    if values is not None:
-                        rowcount = await cursor.execute(sql, values)
-                    else:
-                        rowcount = await cursor.execute(sql)
-
-                    await conn.commit()
-                    self.crawler.stats.inc_value('mysql/insert_success')
-                    return rowcount
-                except Exception as e:
-                    await conn.rollback()
-                    self.crawler.stats.inc_value('mysql/insert_failed')
-                    raise ItemDiscard(f"MySQL插入失败: {e}")
-
-    async def spider_closed(self):
-        """关闭爬虫时清理资源"""
-        if self.pool:
-            self.pool.close()
-            await self.pool.wait_closed()
-            self.logger.info("MySQL连接池已关闭")
-
-
-class AiomysqlMySQLPipeline:
-    def __init__(self, crawler):
-        self.crawler = crawler
-        self.settings = crawler.settings
-        self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
-
-        # 使用异步锁和初始化标志
-        self._pool_lock = asyncio.Lock()
-        self._pool_initialized = False
-        self.pool = None
-        self.table_name = (
-                self.settings.get('MYSQL_TABLE') or
-                getattr(crawler.spider, 'mysql_table', None) or
-                f"{crawler.spider.name}_items"
-        )
-
-        crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
-
-    @classmethod
-    def create_instance(cls, crawler):
-        return cls(crawler)
-
-    async def _init_pool(self):
-        """延迟初始化连接池（线程安全）"""
-        if self._pool_initialized:
-            return
-
-        async with self._pool_lock:
-            if not self._pool_initialized:
-                try:
-                    self.pool = await aiomysql.create_pool(
-                        host=self.settings.get('MYSQL_HOST', 'localhost'),
-                        port=self.settings.getint('MYSQL_PORT', 3306),
-                        user=self.settings.get('MYSQL_USER', 'root'),
-                        password=self.settings.get('MYSQL_PASSWORD', ''),
-                        db=self.settings.get('MYSQL_DB', 'scrapy_db'),
-                        minsize=self.settings.getint('MYSQL_POOL_MIN', 2),
-                        maxsize=self.settings.getint('MYSQL_POOL_MAX', 5),
-                        cursorclass=aiomysql.DictCursor,
-                        autocommit=False
-                    )
-                    self._pool_initialized = True
-                    self.logger.debug(f"aiomysql连接池已初始化（表: {self.table_name}）")
-                except Exception as e:
-                    self.logger.error(f"aiomysql连接池初始化失败: {e}")
-                    raise
-
-    async def process_item(self, item, spider) -> Optional[dict]:
-        """处理item方法"""
-        try:
-            await self._init_pool()
-
-            item_dict = dict(item)
-            sql = f"""
-            INSERT INTO `{self.table_name}` 
-            ({', '.join([f'`{k}`' for k in item_dict.keys()])})
-            VALUES ({', '.join(['%s'] * len(item_dict))})
-            """
-
-            async with self.pool.acquire() as conn:
-                async with conn.cursor() as cursor:
-                    try:
-                        await cursor.execute(sql, list(item_dict.values()))
-                        await conn.commit()
-                        self.crawler.stats.inc_value('mysql/insert_success')
-                    except aiomysql.Error as e:
-                        await conn.rollback()
-                        self.crawler.stats.inc_value('mysql/insert_failed')
-                        raise ItemDiscard(f"MySQL错误: {e.args[1]}")
-
-            return item
-
-        except Exception as e:
-            self.logger.error(f"Pipeline处理异常: {e}")
-            raise ItemDiscard(f"处理失败: {e}")
-
-    async def spider_closed(self):
-        """资源清理"""
-        if self.pool:
-            self.pool.close()
-            await self.pool.wait_closed()
-            self.logger.info("aiomysql连接池已释放")
+# -*- coding: utf-8 -*-
+import asyncio
+import aiomysql
+from typing import Optional
+from asyncmy import create_pool
+from crawlo.utils.log import get_logger
+from crawlo.exceptions import ItemDiscard
+from crawlo.utils.db_helper import make_insert_sql, logger
+
+
+class AsyncmyMySQLPipeline:
+    def __init__(self, crawler):
+        self.crawler = crawler
+        self.settings = crawler.settings
+        self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
+
+        # 使用异步锁和初始化标志确保线程安全
+        self._pool_lock = asyncio.Lock()
+        self._pool_initialized = False
+        self.pool = None
+        self.table_name = (
+                self.settings.get('MYSQL_TABLE') or
+                getattr(crawler.spider, 'mysql_table', None) or
+                f"{crawler.spider.name}_items"
+        )
+
+        # 注册关闭事件
+        crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        return cls(crawler)
+
+    async def _ensure_pool(self):
+        """确保连接池已初始化（线程安全）"""
+        if self._pool_initialized:
+            return
+
+        async with self._pool_lock:
+            if not self._pool_initialized:  # 双重检查避免竞争条件
+                try:
+                    self.pool = await create_pool(
+                        host=self.settings.get('MYSQL_HOST', 'localhost'),
+                        port=self.settings.get_int('MYSQL_PORT', 3306),
+                        user=self.settings.get('MYSQL_USER', 'root'),
+                        password=self.settings.get('MYSQL_PASSWORD', ''),
+                        db=self.settings.get('MYSQL_DB', 'scrapy_db'),
+                        minsize=self.settings.get_int('MYSQL_POOL_MIN', 3),
+                        maxsize=self.settings.get_int('MYSQL_POOL_MAX', 10),
+                        echo=self.settings.get_bool('MYSQL_ECHO', False)
+                    )
+                    self._pool_initialized = True
+                    self.logger.debug(f"MySQL连接池初始化完成（表: {self.table_name}）")
+                except Exception as e:
+                    self.logger.error(f"MySQL连接池初始化失败: {e}")
+                    raise
+
+    async def process_item(self, item, spider, kwargs=None) -> Optional[dict]:
+        """处理item的核心方法"""
+        kwargs = kwargs or {}
+        spider_name = getattr(spider, 'name', 'unknown')  # 获取爬虫名称
+        try:
+            await self._ensure_pool()
+            item_dict = dict(item)
+            sql = make_insert_sql(table=self.table_name, data=item_dict, **kwargs)
+
+            rowcount = await self._execute_sql(sql=sql)
+            if rowcount > 1:
+                self.logger.info(
+                    f"爬虫 {spider_name} 成功插入 {rowcount} 条记录到表 {self.table_name}"
+                )
+            elif rowcount == 1:
+                self.logger.debug(
+                    f"爬虫 {spider_name} 成功插入单条记录到表 {self.table_name}"
+                )
+            else:
+                self.logger.warning(
+                    f"爬虫 {spider_name}: SQL执行成功但未插入新记录 - {sql[:100]}..."
+                )
+
+            return item
+
+        except Exception as e:
+            self.logger.error(f"处理item时发生错误: {e}")
+            raise ItemDiscard(f"处理失败: {e}")
+
+    async def _execute_sql(self, sql: str, values: list = None) -> int:
+        """执行SQL语句并处理结果"""
+        async with self.pool.acquire() as conn:
+            async with conn.cursor() as cursor:
+                try:
+                    # 根据是否有参数值选择不同的执行方法
+                    if values is not None:
+                        rowcount = await cursor.execute(sql, values)
+                    else:
+                        rowcount = await cursor.execute(sql)
+
+                    await conn.commit()
+                    self.crawler.stats.inc_value('mysql/insert_success')
+                    return rowcount
+                except Exception as e:
+                    await conn.rollback()
+                    self.crawler.stats.inc_value('mysql/insert_failed')
+                    raise ItemDiscard(f"MySQL插入失败: {e}")
+
+    async def spider_closed(self):
+        """关闭爬虫时清理资源"""
+        if self.pool:
+            self.pool.close()
+            await self.pool.wait_closed()
+            self.logger.info("MySQL连接池已关闭")
+
+
+class AiomysqlMySQLPipeline:
+    def __init__(self, crawler):
+        self.crawler = crawler
+        self.settings = crawler.settings
+        self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
+
+        # 使用异步锁和初始化标志
+        self._pool_lock = asyncio.Lock()
+        self._pool_initialized = False
+        self.pool = None
+        self.table_name = (
+                self.settings.get('MYSQL_TABLE') or
+                getattr(crawler.spider, 'mysql_table', None) or
+                f"{crawler.spider.name}_items"
+        )
+
+        crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
+
+    @classmethod
+    def create_instance(cls, crawler):
+        return cls(crawler)
+
+    async def _init_pool(self):
+        """延迟初始化连接池（线程安全）"""
+        if self._pool_initialized:
+            return
+
+        async with self._pool_lock:
+            if not self._pool_initialized:
+                try:
+                    self.pool = await aiomysql.create_pool(
+                        host=self.settings.get('MYSQL_HOST', 'localhost'),
+                        port=self.settings.getint('MYSQL_PORT', 3306),
+                        user=self.settings.get('MYSQL_USER', 'root'),
+                        password=self.settings.get('MYSQL_PASSWORD', ''),
+                        db=self.settings.get('MYSQL_DB', 'scrapy_db'),
+                        minsize=self.settings.getint('MYSQL_POOL_MIN', 2),
+                        maxsize=self.settings.getint('MYSQL_POOL_MAX', 5),
+                        cursorclass=aiomysql.DictCursor,
+                        autocommit=False
+                    )
+                    self._pool_initialized = True
+                    self.logger.debug(f"aiomysql连接池已初始化（表: {self.table_name}）")
+                except Exception as e:
+                    self.logger.error(f"aiomysql连接池初始化失败: {e}")
+                    raise
+
+    async def process_item(self, item, spider) -> Optional[dict]:
+        """处理item方法"""
+        try:
+            await self._init_pool()
+
+            item_dict = dict(item)
+            sql = f"""
+            INSERT INTO `{self.table_name}` 
+            ({', '.join([f'`{k}`' for k in item_dict.keys()])})
+            VALUES ({', '.join(['%s'] * len(item_dict))})
+            """
+
+            async with self.pool.acquire() as conn:
+                async with conn.cursor() as cursor:
+                    try:
+                        await cursor.execute(sql, list(item_dict.values()))
+                        await conn.commit()
+                        self.crawler.stats.inc_value('mysql/insert_success')
+                    except aiomysql.Error as e:
+                        await conn.rollback()
+                        self.crawler.stats.inc_value('mysql/insert_failed')
+                        raise ItemDiscard(f"MySQL错误: {e.args[1]}")
+
+            return item
+
+        except Exception as e:
+            self.logger.error(f"Pipeline处理异常: {e}")
+            raise ItemDiscard(f"处理失败: {e}")
+
+    async def spider_closed(self):
+        """资源清理"""
+        if self.pool:
+            self.pool.close()
+            await self.pool.wait_closed()
+            self.logger.info("aiomysql连接池已释放")

crawlo/pipelines/pipeline_manager.py

@@ -1,56 +1,56 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-from typing import List
-from pprint import pformat
-from asyncio import create_task
-
-
-from crawlo.utils.log import get_logger
-from crawlo.event import item_successful, item_discard
-from crawlo.project import load_class, common_call
-from crawlo.exceptions import PipelineInitError, ItemDiscard, InvalidOutputError
-
-
-class PipelineManager:
-
-    def __init__(self, crawler):
-        self.crawler = crawler
-        self.pipelines: List = []
-        self.methods: List = []
-
-        self.logger = get_logger(self.__class__.__name__, self.crawler.settings.get('LOG_LEVEL'))
-        pipelines = self.crawler.settings.get_list('PIPELINES')
-        self._add_pipelines(pipelines)
-        self._add_methods()
-
-    @classmethod
-    def from_crawler(cls, *args, **kwargs):
-        o = cls(*args, **kwargs)
-        return o
-
-    def _add_pipelines(self, pipelines):
-        for pipeline in pipelines:
-            pipeline_cls = load_class(pipeline)
-            if not hasattr(pipeline_cls, 'from_crawler'):
-                raise PipelineInitError(
-                    f"Pipeline init failed, must inherit from `BasePipeline` or have a `create_instance` method"
-                )
-            self.pipelines.append(pipeline_cls.from_crawler(self.crawler))
-        if pipelines:
-            self.logger.info(f"enabled pipelines: \n {pformat(pipelines)}")
-
-    def _add_methods(self):
-        for pipeline in self.pipelines:
-            if hasattr(pipeline, 'process_item'):
-                self.methods.append(pipeline.process_item)
-
-    async def process_item(self, item):
-        try:
-            for method in self.methods:
-                item = await common_call(method, item, self.crawler.spider)
-                if item is None:
-                    raise InvalidOutputError(f"{method.__qualname__} return None is not supported.")
-        except ItemDiscard as exc:
-            create_task(self.crawler.subscriber.notify(item_discard, item, exc, self.crawler.spider))
-        else:
-            create_task(self.crawler.subscriber.notify(item_successful, item, self.crawler.spider))
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+from typing import List
+from pprint import pformat
+from asyncio import create_task
+
+
+from crawlo.utils.log import get_logger
+from crawlo.event import item_successful, item_discard
+from crawlo.project import load_class, common_call
+from crawlo.exceptions import PipelineInitError, ItemDiscard, InvalidOutputError
+
+
+class PipelineManager:
+
+    def __init__(self, crawler):
+        self.crawler = crawler
+        self.pipelines: List = []
+        self.methods: List = []
+
+        self.logger = get_logger(self.__class__.__name__, self.crawler.settings.get('LOG_LEVEL'))
+        pipelines = self.crawler.settings.get_list('PIPELINES')
+        self._add_pipelines(pipelines)
+        self._add_methods()
+
+    @classmethod
+    def from_crawler(cls, *args, **kwargs):
+        o = cls(*args, **kwargs)
+        return o
+
+    def _add_pipelines(self, pipelines):
+        for pipeline in pipelines:
+            pipeline_cls = load_class(pipeline)
+            if not hasattr(pipeline_cls, 'from_crawler'):
+                raise PipelineInitError(
+                    f"Pipeline init failed, must inherit from `BasePipeline` or have a `create_instance` method"
+                )
+            self.pipelines.append(pipeline_cls.from_crawler(self.crawler))
+        if pipelines:
+            self.logger.info(f"enabled pipelines: \n {pformat(pipelines)}")
+
+    def _add_methods(self):
+        for pipeline in self.pipelines:
+            if hasattr(pipeline, 'process_item'):
+                self.methods.append(pipeline.process_item)
+
+    async def process_item(self, item):
+        try:
+            for method in self.methods:
+                item = await common_call(method, item, self.crawler.spider)
+                if item is None:
+                    raise InvalidOutputError(f"{method.__qualname__} return None is not supported.")
+        except ItemDiscard as exc:
+            create_task(self.crawler.subscriber.notify(item_discard, item, exc, self.crawler.spider))
+        else:
+            create_task(self.crawler.subscriber.notify(item_successful, item, self.crawler.spider))

crawlo/pipelines/redis_dedup_pipeline.py

@@ -0,0 +1,163 @@
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+基于 Redis 的数据项去重管道
+========================
+提供分布式环境下的数据项去重功能，防止保存重复的数据记录。
+
+特点:
+- 分布式支持: 多节点共享去重数据
+- 高性能: 使用 Redis 集合进行快速查找
+- 可配置: 支持自定义 Redis 连接参数
+- 容错设计: 网络异常时不会丢失数据
+"""
+
+import hashlib
+from typing import Dict, Any, Optional
+import redis
+
+from crawlo import Item
+from crawlo.spider import Spider
+from crawlo.utils.log import get_logger
+from crawlo.exceptions import DropItem
+
+
+class RedisDedupPipeline:
+    """基于 Redis 的数据项去重管道"""
+
+    def __init__(
+            self,
+            redis_host: str = 'localhost',
+            redis_port: int = 6379,
+            redis_db: int = 0,
+            redis_password: Optional[str] = None,
+            redis_key: str = 'crawlo:item_fingerprints',
+            log_level: str = "INFO"
+    ):
+        """
+        初始化 Redis 去重管道
+        
+        :param redis_host: Redis 主机地址
+        :param redis_port: Redis 端口
+        :param redis_db: Redis 数据库编号
+        :param redis_password: Redis 密码
+        :param redis_key: 存储指纹的 Redis 键名
+        :param log_level: 日志级别
+        """
+        self.logger = get_logger(self.__class__.__name__, log_level)
+        
+        # 初始化 Redis 连接
+        try:
+            self.redis_client = redis.Redis(
+                host=redis_host,
+                port=redis_port,
+                db=redis_db,
+                password=redis_password,
+                decode_responses=True,
+                socket_connect_timeout=5,
+                socket_timeout=5
+            )
+            # 测试连接
+            self.redis_client.ping()
+            self.logger.info(f"Redis 连接成功: {redis_host}:{redis_port}/{redis_db}")
+        except Exception as e:
+            self.logger.error(f"Redis 连接失败: {e}")
+            raise RuntimeError(f"Redis 连接失败: {e}")
+
+        self.redis_key = redis_key
+        self.dropped_count = 0
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        """从爬虫配置创建管道实例"""
+        settings = crawler.settings
+        
+        return cls(
+            redis_host=settings.get('REDIS_HOST', 'localhost'),
+            redis_port=settings.getint('REDIS_PORT', 6379),
+            redis_db=settings.getint('REDIS_DB', 0),
+            redis_password=settings.get('REDIS_PASSWORD') or None,
+            redis_key=settings.get('REDIS_DEDUP_KEY', 'crawlo:item_fingerprints'),
+            log_level=settings.get('LOG_LEVEL', 'INFO')
+        )
+
+    def process_item(self, item: Item, spider: Spider) -> Item:
+        """
+        处理数据项，进行去重检查
+        
+        :param item: 要处理的数据项
+        :param spider: 爬虫实例
+        :return: 处理后的数据项或抛出 DropItem 异常
+        """
+        try:
+            # 生成数据项指纹
+            fingerprint = self._generate_item_fingerprint(item)
+            
+            # 使用 Redis 的 SADD 命令检查并添加指纹
+            # 如果指纹已存在，SADD 返回 0；如果指纹是新的，SADD 返回 1
+            is_new = self.redis_client.sadd(self.redis_key, fingerprint)
+            
+            if not is_new:
+                # 如果指纹已存在，丢弃这个数据项
+                self.dropped_count += 1
+                self.logger.debug(f"丢弃重复数据项: {fingerprint[:20]}...")
+                raise DropItem(f"重复的数据项: {fingerprint}")
+            else:
+                # 如果是新数据项，继续处理
+                self.logger.debug(f"处理新数据项: {fingerprint[:20]}...")
+                return item
+                
+        except redis.RedisError as e:
+            self.logger.error(f"Redis 错误: {e}")
+            # 在 Redis 错误时继续处理，避免丢失数据
+            return item
+        except Exception as e:
+            self.logger.error(f"处理数据项时出错: {e}")
+            # 在其他错误时继续处理
+            return item
+
+    def _generate_item_fingerprint(self, item: Item) -> str:
+        """
+        生成数据项指纹
+        
+        基于数据项的所有字段生成唯一指纹，用于去重判断。
+        
+        :param item: 数据项
+        :return: 指纹字符串
+        """
+        # 将数据项转换为可序列化的字典
+        try:
+            item_dict = item.to_dict()
+        except AttributeError:
+            # 兼容没有to_dict方法的Item实现
+            item_dict = dict(item)
+        
+        # 对字典进行排序以确保一致性
+        sorted_items = sorted(item_dict.items())
+        
+        # 生成指纹字符串
+        fingerprint_string = '|'.join([f"{k}={v}" for k, v in sorted_items if v is not None])
+        
+        # 使用 SHA256 生成固定长度的指纹
+        return hashlib.sha256(fingerprint_string.encode('utf-8')).hexdigest()
+
+    def close_spider(self, spider: Spider) -> None:
+        """
+        爬虫关闭时的清理工作
+        
+        :param spider: 爬虫实例
+        """
+        try:
+            # 获取去重统计信息
+            total_items = self.redis_client.scard(self.redis_key)
+            self.logger.info(f"爬虫 {spider.name} 关闭:")
+            self.logger.info(f"  - 丢弃的重复数据项: {self.dropped_count}")
+            self.logger.info(f"  - Redis 中存储的指纹数: {total_items}")
+            
+            # 注意：默认情况下不清理 Redis 中的指纹
+            # 如果需要清理，可以在设置中配置
+            if spider.crawler.settings.getbool('REDIS_DEDUP_CLEANUP', False):
+                deleted = self.redis_client.delete(self.redis_key)
+                self.logger.info(f"  - 清理的指纹数: {deleted}")
+        except Exception as e:
+            self.logger.error(f"关闭爬虫时出错: {e}")