crawlo 1.0.1__py3-none-any.whl → 1.0.3__py3-none-any.whl

crawlo/filters/memory_filter.py

@@ -1,203 +1,202 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-import os
-import threading
-from weakref import WeakSet
-from typing import Set, TextIO, Optional
-
-from crawlo import Request
-from crawlo.filters import BaseFilter
-from crawlo.utils.log import get_logger
-from crawlo.utils.request import request_fingerprint
-
-
-class MemoryFilter(BaseFilter):
-    """基于内存的高效请求去重过滤器，适用于单机爬虫"""
-
-    def __init__(self, crawler):
-        """
-        初始化内存过滤器
-
-        :param crawler: 爬虫实例，用于获取配置
-        """
-        self.fingerprints: Set[str] = set()  # 主指纹存储
-        self._temp_weak_refs = WeakSet()  # 弱引用临时存储（可选）
-
-        debug = crawler.settings.get_bool('FILTER_DEBUG', False)
-        logger = get_logger(
-            self.__class__.__name__,  # 使用类名替代字符串
-            crawler.settings.get('LOG_LEVEL', 'INFO')
-        )
-        super().__init__(logger, crawler.stats, debug)
-
-        # 性能计数器
-        self._dupe_count = 0
-        self._unique_count = 0
-
-    def add_fingerprint(self, fp: str) -> None:
-        """
-        添加请求指纹
-
-        :param fp: 请求指纹字符串
-        :raises TypeError: 如果指纹不是字符串类型
-        """
-        if not isinstance(fp, str):
-            raise TypeError(f"指纹必须是字符串类型，得到 {type(fp)}")
-
-        self.fingerprints.add(fp)
-        self._unique_count += 1
-        # self.logger.debug(f"添加指纹: {fp[:10]}...")  # 日志截断防止过长
-
-    def requested(self, request: Request) -> bool:
-        """
-        检查请求是否重复（主要接口）
-
-        :param request: 请求对象
-        :return: 是否重复
-        """
-        fp = request_fingerprint(request)
-        if fp in self:
-            self._dupe_count += 1
-            # self.logger.debug(f"发现重复请求: {fp[:10]}...")
-            return True
-
-        self.add_fingerprint(fp)
-        return False
-
-    def __contains__(self, item: str) -> bool:
-        """
-        支持 in 操作符检查
-
-        :param item: 要检查的指纹
-        :return: 是否已存在
-        """
-        return item in self.fingerprints
-
-    @property
-    def stats_summary(self) -> dict:
-        """获取过滤器统计信息"""
-        return {
-            'capacity': len(self.fingerprints),
-            'duplicates': self._dupe_count,
-            'uniques': self._unique_count,
-            'memory_usage': self._estimate_memory()
-        }
-
-    def _estimate_memory(self) -> str:
-        """估算内存使用量（近似值）"""
-        avg_item_size = sum(len(x) for x in self.fingerprints) / max(1, len(self.fingerprints))
-        total = len(self.fingerprints) * (avg_item_size + 50)  # 50字节额外开销
-        return f"{total / (1024 * 1024):.2f} MB"
-
-    def clear(self) -> None:
-        """清空所有指纹数据"""
-        self.fingerprints.clear()
-        self._dupe_count = 0
-        self._unique_count = 0
-        self.logger.info("已清空内存过滤器")
-
-    def close(self) -> None:
-        """关闭过滤器（清理资源）"""
-        self.clear()
-
-    # 兼容旧版异步接口
-    async def closed(self):
-        """兼容异步接口"""
-        self.close()
-
-
-class MemoryFileFilter(BaseFilter):
-    """基于内存的请求指纹过滤器，支持原子化文件持久化"""
-
-    def __init__(self, crawler):
-        """
-        初始化过滤器
-        :param crawler: Scrapy Crawler对象，用于获取配置
-        """
-        self.fingerprints: Set[str] = set()  # 主存储集合
-        self._lock = threading.RLock()  # 线程安全锁
-        self._file: Optional[TextIO] = None  # 文件句柄
-
-        debug = crawler.settings.get_bool("FILTER_DEBUG", False)
-        logger = get_logger(
-            self.__class__.__name__,  # 使用类名作为日志标识
-            crawler.settings.get("LOG_LEVEL", "INFO")
-        )
-        super().__init__(logger, crawler.stats, debug)
-
-        # 初始化文件存储
-        request_dir = crawler.settings.get("REQUEST_DIR")
-        if request_dir:
-            self._init_file_store(request_dir)
-
-    def _init_file_store(self, request_dir: str) -> None:
-        """原子化初始化文件存储"""
-        with self._lock:
-            try:
-                os.makedirs(request_dir, exist_ok=True)
-                file_path = os.path.join(request_dir, 'request_fingerprints.txt')
-
-                # 原子化操作：读取现有指纹
-                if os.path.exists(file_path):
-                    with open(file_path, 'r', encoding='utf-8') as f:
-                        self.fingerprints.update(
-                            line.strip() for line in f
-                            if line.strip()
-                        )
-
-                # 以追加模式打开文件
-                self._file = open(file_path, 'a+', encoding='utf-8')
-                self.logger.info(f"Initialized fingerprint file: {file_path}")
-
-            except Exception as e:
-                self.logger.error(f"Failed to init file store: {str(e)}")
-                raise
-
-    def add_fingerprint(self, fp: str) -> None:
-        """
-        线程安全的指纹添加操作
-        :param fp: 请求指纹字符串
-        """
-        with self._lock:
-            if fp not in self.fingerprints:
-                self.fingerprints.add(fp)
-                self._persist_fp(fp)
-
-    def _persist_fp(self, fp: str) -> None:
-        """持久化指纹到文件（需在锁保护下调用）"""
-        if self._file:
-            try:
-                self._file.write(f"{fp}\n")
-                self._file.flush()
-                os.fsync(self._file.fileno())  # 确保写入磁盘
-            except IOError as e:
-                self.logger.error(f"Failed to persist fingerprint: {str(e)}")
-
-    def __contains__(self, item: str) -> bool:
-        """
-        线程安全的指纹检查
-        :param item: 要检查的指纹
-        :return: 是否已存在
-        """
-        with self._lock:
-            return item in self.fingerprints
-
-    def close(self) -> None:
-        """安全关闭资源（同步方法）"""
-        with self._lock:
-            if self._file and not self._file.closed:
-                try:
-                    self._file.flush()
-                    os.fsync(self._file.fileno())
-                finally:
-                    self._file.close()
-                self.logger.info(f"Closed fingerprint file: {self._file.name}")
-
-    def __del__(self):
-        """析构函数双保险"""
-        self.close()
-
-    # 兼容异步接口
-    async def closed(self):
-        """标准的关闭入口"""
-        self.close()
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+import os
+import threading
+from weakref import WeakSet
+from typing import Set, TextIO, Optional
+
+from crawlo import Request
+from crawlo.filters import BaseFilter
+from crawlo.utils.log import get_logger
+from crawlo.utils.request import request_fingerprint
+
+
+class MemoryFilter(BaseFilter):
+    """基于内存的高效请求去重过滤器，适用于单机爬虫"""
+
+    def __init__(self, crawler):
+        """
+        初始化内存过滤器
+
+        :param crawler: 爬虫实例，用于获取配置
+        """
+        self.fingerprints: Set[str] = set()  # 主指纹存储
+        self._temp_weak_refs = WeakSet()  # 弱引用临时存储（可选）
+
+        debug = crawler.settings.get_bool('FILTER_DEBUG', False)
+        logger = get_logger(
+            self.__class__.__name__,  # 使用类名替代字符串
+            crawler.settings.get('LOG_LEVEL', 'INFO')
+        )
+        super().__init__(logger, crawler.stats, debug)
+
+        # 性能计数器
+        self._dupe_count = 0
+        self._unique_count = 0
+
+    def add_fingerprint(self, fp: str) -> None:
+        """
+        添加请求指纹
+
+        :param fp: 请求指纹字符串
+        :raises TypeError: 如果指纹不是字符串类型
+        """
+        if not isinstance(fp, str):
+            raise TypeError(f"指纹必须是字符串类型，得到 {type(fp)}")
+
+        self.fingerprints.add(fp)
+        self._unique_count += 1
+        # self.logger.debug(f"添加指纹: {fp[:10]}...")  # 日志截断防止过长
+
+    def requested(self, request: Request) -> bool:
+        """
+        检查请求是否重复（主要接口）
+
+        :param request: 请求对象
+        :return: 是否重复
+        """
+        fp = request_fingerprint(request)
+        if fp in self:
+            self._dupe_count += 1
+            # self.logger.debug(f"发现重复请求: {fp[:10]}...")
+            return True
+
+        self.add_fingerprint(fp)
+        return False
+
+    def __contains__(self, item: str) -> bool:
+        """
+        支持 in 操作符检查
+
+        :param item: 要检查的指纹
+        :return: 是否已存在
+        """
+        return item in self.fingerprints
+
+    @property
+    def stats_summary(self) -> dict:
+        """获取过滤器统计信息"""
+        return {
+            'capacity': len(self.fingerprints),
+            'duplicates': self._dupe_count,
+            'uniques': self._unique_count,
+            'memory_usage': self._estimate_memory()
+        }
+
+    def _estimate_memory(self) -> str:
+        """估算内存使用量（近似值）"""
+        avg_item_size = sum(len(x) for x in self.fingerprints) / max(1, len(self.fingerprints))
+        total = len(self.fingerprints) * (avg_item_size + 50)  # 50字节额外开销
+        return f"{total / (1024 * 1024):.2f} MB"
+
+    def clear(self) -> None:
+        """清空所有指纹数据"""
+        self.fingerprints.clear()
+        self._dupe_count = 0
+        self._unique_count = 0
+
+    def close(self) -> None:
+        """关闭过滤器（清理资源）"""
+        self.clear()
+
+    # 兼容旧版异步接口
+    async def closed(self):
+        """兼容异步接口"""
+        self.close()
+
+
+class MemoryFileFilter(BaseFilter):
+    """基于内存的请求指纹过滤器，支持原子化文件持久化"""
+
+    def __init__(self, crawler):
+        """
+        初始化过滤器
+        :param crawler: Scrapy Crawler对象，用于获取配置
+        """
+        self.fingerprints: Set[str] = set()  # 主存储集合
+        self._lock = threading.RLock()  # 线程安全锁
+        self._file: Optional[TextIO] = None  # 文件句柄
+
+        debug = crawler.settings.get_bool("FILTER_DEBUG", False)
+        logger = get_logger(
+            self.__class__.__name__,  # 使用类名作为日志标识
+            crawler.settings.get("LOG_LEVEL", "INFO")
+        )
+        super().__init__(logger, crawler.stats, debug)
+
+        # 初始化文件存储
+        request_dir = crawler.settings.get("REQUEST_DIR")
+        if request_dir:
+            self._init_file_store(request_dir)
+
+    def _init_file_store(self, request_dir: str) -> None:
+        """原子化初始化文件存储"""
+        with self._lock:
+            try:
+                os.makedirs(request_dir, exist_ok=True)
+                file_path = os.path.join(request_dir, 'request_fingerprints.txt')
+
+                # 原子化操作：读取现有指纹
+                if os.path.exists(file_path):
+                    with open(file_path, 'r', encoding='utf-8') as f:
+                        self.fingerprints.update(
+                            line.strip() for line in f
+                            if line.strip()
+                        )
+
+                # 以追加模式打开文件
+                self._file = open(file_path, 'a+', encoding='utf-8')
+                self.logger.info(f"Initialized fingerprint file: {file_path}")
+
+            except Exception as e:
+                self.logger.error(f"Failed to init file store: {str(e)}")
+                raise
+
+    def add_fingerprint(self, fp: str) -> None:
+        """
+        线程安全的指纹添加操作
+        :param fp: 请求指纹字符串
+        """
+        with self._lock:
+            if fp not in self.fingerprints:
+                self.fingerprints.add(fp)
+                self._persist_fp(fp)
+
+    def _persist_fp(self, fp: str) -> None:
+        """持久化指纹到文件（需在锁保护下调用）"""
+        if self._file:
+            try:
+                self._file.write(f"{fp}\n")
+                self._file.flush()
+                os.fsync(self._file.fileno())  # 确保写入磁盘
+            except IOError as e:
+                self.logger.error(f"Failed to persist fingerprint: {str(e)}")
+
+    def __contains__(self, item: str) -> bool:
+        """
+        线程安全的指纹检查
+        :param item: 要检查的指纹
+        :return: 是否已存在
+        """
+        with self._lock:
+            return item in self.fingerprints
+
+    def close(self) -> None:
+        """安全关闭资源（同步方法）"""
+        with self._lock:
+            if self._file and not self._file.closed:
+                try:
+                    self._file.flush()
+                    os.fsync(self._file.fileno())
+                finally:
+                    self._file.close()
+                self.logger.info(f"Closed fingerprint file: {self._file.name}")
+
+    def __del__(self):
+        """析构函数双保险"""
+        self.close()
+
+    # 兼容异步接口
+    async def closed(self):
+        """标准的关闭入口"""
+        self.close()

crawlo/filters/redis_filter.py

@@ -1,120 +1,120 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-import redis
-
-from crawlo import Request
-from crawlo.filters import BaseFilter
-from crawlo.utils.log import get_logger
-from crawlo.utils.request import request_fingerprint
-
-
-class RedisFilter(BaseFilter):
-    """使用Redis集合实现的同步请求去重过滤器"""
-
-    def __init__(
-            self,
-            redis_key: str,
-            client: redis.Redis,
-            stats: dict,
-            debug: bool,
-            log_level: str,
-            save_fp: bool
-    ):
-        """
-        初始化过滤器
-
-        :param redis_key: Redis存储键名
-        :param client: redis客户端实例
-        :param stats: 统计字典
-        :param debug: 是否启用调试模式
-        :param log_level: 日志级别
-        :param save_fp: 是否保留指纹数据
-        """
-        self.logger = get_logger(self.__class__.__name__, log_level)
-        super().__init__(self.logger, stats, debug)
-
-        self.redis_key = redis_key
-        self.redis = client
-        self.save_fp = save_fp
-
-    @classmethod
-    def create_instance(cls, crawler) -> 'BaseFilter':
-        """工厂方法创建实例"""
-        redis_url = crawler.settings.get('REDIS_URL', 'redis://localhost:6379')
-        decode_responses = crawler.settings.get_bool('DECODE_RESPONSES', True)
-
-        try:
-            # 添加连接池配置
-            redis_client = redis.from_url(
-                redis_url,
-                decode_responses=decode_responses,
-                socket_timeout=5,  # 超时设置
-                socket_connect_timeout=5,
-                max_connections=20  # 连接池大小
-            )
-            # 测试连接是否有效
-            redis_client.ping()
-        except redis.RedisError as e:
-            raise RuntimeError(f"Redis连接失败: {str(e)}")
-
-        return cls(
-            redis_key=f"{crawler.settings.get('PROJECT_NAME')}:{crawler.settings.get('REDIS_KEY', 'request_fingerprints')}",
-            client=redis_client,
-            stats=crawler.stats,
-            save_fp=crawler.settings.get_bool('SAVE_FP', False),
-            debug=crawler.settings.get_bool('FILTER_DEBUG', False),
-            log_level=crawler.settings.get('LOG_LEVEL', 'INFO')
-        )
-
-    def requested(self, request: Request) -> bool:
-        """
-        检查请求是否已存在
-
-        :param request: 请求对象
-        :return: 是否重复
-        """
-        fp = request_fingerprint(request)
-        try:
-            if self.redis.sismember(self.redis_key, fp):
-                self.logger.debug(f"重复请求: {fp}")
-                return True
-
-            self.add_fingerprint(fp)
-            return False
-        except redis.RedisError as e:
-            self.logger.error(f"Redis操作失败: {str(e)}")
-            raise
-
-    def add_fingerprint(self, fp: str) -> None:
-        """添加指纹到Redis集合"""
-        try:
-            self.redis.sadd(self.redis_key, fp)
-            self.logger.debug(f"新增指纹: {fp}")
-        except redis.RedisError as e:
-            self.logger.error(f"指纹添加失败: {str(e)}")
-            raise
-
-    def __contains__(self, item) -> bool:
-        """支持 in 操作符检查 (必须返回bool类型)"""
-        try:
-            # 显式将redis返回的0/1转换为bool
-            return bool(self.redis.sismember(self.redis_key, item))
-        except redis.RedisError as e:
-            self.logger.error(f"Redis查询失败: {str(e)}")
-            raise
-
-    def close(self) -> None:
-        """同步清理方法（注意不是异步的closed）"""
-        if not self.save_fp:
-            try:
-                count = self.redis.delete(self.redis_key)
-                self.logger.info(f"已清理Redis键 {self.redis_key}, 删除数量: {count}")
-            except redis.RedisError as e:
-                self.logger.error(f"清理失败: {str(e)}")
-            finally:
-                # 同步客户端需要手动关闭连接池
-                self.redis.close()
-
-    async def closed(self):
-        """兼容异步接口的同步实现"""
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+import redis
+
+from crawlo import Request
+from crawlo.filters import BaseFilter
+from crawlo.utils.log import get_logger
+from crawlo.utils.request import request_fingerprint
+
+
+class RedisFilter(BaseFilter):
+    """使用Redis集合实现的同步请求去重过滤器"""
+
+    def __init__(
+            self,
+            redis_key: str,
+            client: redis.Redis,
+            stats: dict,
+            debug: bool,
+            log_level: str,
+            save_fp: bool
+    ):
+        """
+        初始化过滤器
+
+        :param redis_key: Redis存储键名
+        :param client: redis客户端实例
+        :param stats: 统计字典
+        :param debug: 是否启用调试模式
+        :param log_level: 日志级别
+        :param save_fp: 是否保留指纹数据
+        """
+        self.logger = get_logger(self.__class__.__name__, log_level)
+        super().__init__(self.logger, stats, debug)
+
+        self.redis_key = redis_key
+        self.redis = client
+        self.save_fp = save_fp
+
+    @classmethod
+    def create_instance(cls, crawler) -> 'BaseFilter':
+        """工厂方法创建实例"""
+        redis_url = crawler.settings.get('REDIS_URL', 'redis://localhost:6379')
+        decode_responses = crawler.settings.get_bool('DECODE_RESPONSES', True)
+
+        try:
+            # 添加连接池配置
+            redis_client = redis.from_url(
+                redis_url,
+                decode_responses=decode_responses,
+                socket_timeout=5,  # 超时设置
+                socket_connect_timeout=5,
+                max_connections=20  # 连接池大小
+            )
+            # 测试连接是否有效
+            redis_client.ping()
+        except redis.RedisError as e:
+            raise RuntimeError(f"Redis连接失败: {str(e)}")
+
+        return cls(
+            redis_key=f"{crawler.settings.get('PROJECT_NAME')}:{crawler.settings.get('REDIS_KEY', 'request_fingerprints')}",
+            client=redis_client,
+            stats=crawler.stats,
+            save_fp=crawler.settings.get_bool('SAVE_FP', False),
+            debug=crawler.settings.get_bool('FILTER_DEBUG', False),
+            log_level=crawler.settings.get('LOG_LEVEL', 'INFO')
+        )
+
+    def requested(self, request: Request) -> bool:
+        """
+        检查请求是否已存在
+
+        :param request: 请求对象
+        :return: 是否重复
+        """
+        fp = request_fingerprint(request)
+        try:
+            if self.redis.sismember(self.redis_key, fp):
+                self.logger.debug(f"重复请求: {fp}")
+                return True
+
+            self.add_fingerprint(fp)
+            return False
+        except redis.RedisError as e:
+            self.logger.error(f"Redis操作失败: {str(e)}")
+            raise
+
+    def add_fingerprint(self, fp: str) -> None:
+        """添加指纹到Redis集合"""
+        try:
+            self.redis.sadd(self.redis_key, fp)
+            self.logger.debug(f"新增指纹: {fp}")
+        except redis.RedisError as e:
+            self.logger.error(f"指纹添加失败: {str(e)}")
+            raise
+
+    def __contains__(self, item) -> bool:
+        """支持 in 操作符检查 (必须返回bool类型)"""
+        try:
+            # 显式将redis返回的0/1转换为bool
+            return bool(self.redis.sismember(self.redis_key, item))
+        except redis.RedisError as e:
+            self.logger.error(f"Redis查询失败: {str(e)}")
+            raise
+
+    def close(self) -> None:
+        """同步清理方法（注意不是异步的closed）"""
+        if not self.save_fp:
+            try:
+                count = self.redis.delete(self.redis_key)
+                self.logger.info(f"已清理Redis键 {self.redis_key}, 删除数量: {count}")
+            except redis.RedisError as e:
+                self.logger.error(f"清理失败: {str(e)}")
+            finally:
+                # 同步客户端需要手动关闭连接池
+                self.redis.close()
+
+    async def closed(self):
+        """兼容异步接口的同步实现"""
         self.close()