crawlo 1.1.0__py3-none-any.whl → 1.1.2__py3-none-any.whl

crawlo/pipelines/mongo_pipeline.py

@@ -1,117 +1,117 @@
-# -*- coding: utf-8 -*-
-from typing import Optional
-from motor.motor_asyncio import AsyncIOMotorClient
-from pymongo.errors import PyMongoError
-from crawlo.utils.log import get_logger
-from crawlo.exceptions import ItemDiscard
-
-
-class MongoPipeline:
-    def __init__(self, crawler):
-        self.crawler = crawler
-        self.settings = crawler.settings
-        self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
-
-        # 初始化连接参数
-        self.client = None
-        self.db = None
-        self.collection = None
-
-        # 配置默认值
-        self.mongo_uri = self.settings.get('MONGO_URI', 'mongodb://localhost:27017')
-        self.db_name = self.settings.get('MONGO_DATABASE', 'scrapy_db')
-        self.collection_name = self.settings.get('MONGO_COLLECTION', crawler.spider.name)
-
-        # 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_connection(self):
-        """确保连接已建立"""
-        if self.client is None:
-            self.client = AsyncIOMotorClient(self.mongo_uri)
-            self.db = self.client[self.db_name]
-            self.collection = self.db[self.collection_name]
-            self.logger.info(f"MongoDB连接建立 (集合: {self.collection_name})")
-
-    async def process_item(self, item, spider) -> Optional[dict]:
-        """处理item的核心方法"""
-        try:
-            await self._ensure_connection()
-
-            item_dict = dict(item)
-            result = await self.collection.insert_one(item_dict)
-
-            # 统计计数
-            self.crawler.stats.inc_value('mongodb/inserted')
-            self.logger.debug(f"插入文档ID: {result.inserted_id}")
-
-            return item
-
-        except Exception as e:
-            self.crawler.stats.inc_value('mongodb/failed')
-            self.logger.error(f"MongoDB插入失败: {e}")
-            raise ItemDiscard(f"MongoDB操作失败: {e}")
-
-    async def spider_closed(self):
-        """关闭爬虫时清理资源"""
-        if self.client:
-            self.client.close()
-            self.logger.info("MongoDB连接已关闭")
-
-
-class MongoPoolPipeline:
-    def __init__(self, crawler):
-        self.crawler = crawler
-        self.settings = crawler.settings
-        self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
-
-        # 连接池配置
-        self.client = AsyncIOMotorClient(
-            self.settings.get('MONGO_URI', 'mongodb://localhost:27017'),
-            maxPoolSize=self.settings.getint('MONGO_MAX_POOL_SIZE', 100),
-            minPoolSize=self.settings.getint('MONGO_MIN_POOL_SIZE', 10),
-            connectTimeoutMS=5000,
-            socketTimeoutMS=30000
-        )
-
-        self.db = self.client[self.settings.get('MONGO_DATABASE', 'scrapy_db')]
-        self.collection = self.db[self.settings.get('MONGO_COLLECTION', crawler.spider.name)]
-
-        crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
-        self.logger.info(f"MongoDB连接池已初始化 (集合: {self.collection.name})")
-
-    @classmethod
-    def create_instance(cls, crawler):
-        return cls(crawler)
-
-    async def process_item(self, item, spider) -> Optional[dict]:
-        """处理item方法（带重试机制）"""
-        try:
-            item_dict = dict(item)
-
-            # 带重试的插入操作
-            for attempt in range(3):
-                try:
-                    result = await self.collection.insert_one(item_dict)
-                    self.crawler.stats.inc_value('mongodb/insert_success')
-                    self.logger.debug(f"插入成功 [attempt {attempt + 1}]: {result.inserted_id}")
-                    return item
-                except PyMongoError as e:
-                    if attempt == 2:  # 最后一次尝试仍失败
-                        raise
-                    self.logger.warning(f"插入重试中 [attempt {attempt + 1}]: {e}")
-
-        except Exception as e:
-            self.crawler.stats.inc_value('mongodb/insert_failed')
-            self.logger.error(f"MongoDB操作最终失败: {e}")
-            raise ItemDiscard(f"MongoDB操作失败: {e}")
-
-    async def spider_closed(self):
-        """资源清理"""
-        if hasattr(self, 'client'):
-            self.client.close()
+# -*- coding: utf-8 -*-
+from typing import Optional
+from motor.motor_asyncio import AsyncIOMotorClient
+from pymongo.errors import PyMongoError
+from crawlo.utils.log import get_logger
+from crawlo.exceptions import ItemDiscard
+
+
+class MongoPipeline:
+    def __init__(self, crawler):
+        self.crawler = crawler
+        self.settings = crawler.settings
+        self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
+
+        # 初始化连接参数
+        self.client = None
+        self.db = None
+        self.collection = None
+
+        # 配置默认值
+        self.mongo_uri = self.settings.get('MONGO_URI', 'mongodb://localhost:27017')
+        self.db_name = self.settings.get('MONGO_DATABASE', 'scrapy_db')
+        self.collection_name = self.settings.get('MONGO_COLLECTION', crawler.spider.name)
+
+        # 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_connection(self):
+        """确保连接已建立"""
+        if self.client is None:
+            self.client = AsyncIOMotorClient(self.mongo_uri)
+            self.db = self.client[self.db_name]
+            self.collection = self.db[self.collection_name]
+            self.logger.info(f"MongoDB连接建立 (集合: {self.collection_name})")
+
+    async def process_item(self, item, spider) -> Optional[dict]:
+        """处理item的核心方法"""
+        try:
+            await self._ensure_connection()
+
+            item_dict = dict(item)
+            result = await self.collection.insert_one(item_dict)
+
+            # 统计计数
+            self.crawler.stats.inc_value('mongodb/inserted')
+            self.logger.debug(f"插入文档ID: {result.inserted_id}")
+
+            return item
+
+        except Exception as e:
+            self.crawler.stats.inc_value('mongodb/failed')
+            self.logger.error(f"MongoDB插入失败: {e}")
+            raise ItemDiscard(f"MongoDB操作失败: {e}")
+
+    async def spider_closed(self):
+        """关闭爬虫时清理资源"""
+        if self.client:
+            self.client.close()
+            self.logger.info("MongoDB连接已关闭")
+
+
+class MongoPoolPipeline:
+    def __init__(self, crawler):
+        self.crawler = crawler
+        self.settings = crawler.settings
+        self.logger = get_logger(self.__class__.__name__, self.settings.get('LOG_LEVEL'))
+
+        # 连接池配置
+        self.client = AsyncIOMotorClient(
+            self.settings.get('MONGO_URI', 'mongodb://localhost:27017'),
+            maxPoolSize=self.settings.getint('MONGO_MAX_POOL_SIZE', 100),
+            minPoolSize=self.settings.getint('MONGO_MIN_POOL_SIZE', 10),
+            connectTimeoutMS=5000,
+            socketTimeoutMS=30000
+        )
+
+        self.db = self.client[self.settings.get('MONGO_DATABASE', 'scrapy_db')]
+        self.collection = self.db[self.settings.get('MONGO_COLLECTION', crawler.spider.name)]
+
+        crawler.subscriber.subscribe(self.spider_closed, event='spider_closed')
+        self.logger.info(f"MongoDB连接池已初始化 (集合: {self.collection.name})")
+
+    @classmethod
+    def create_instance(cls, crawler):
+        return cls(crawler)
+
+    async def process_item(self, item, spider) -> Optional[dict]:
+        """处理item方法（带重试机制）"""
+        try:
+            item_dict = dict(item)
+
+            # 带重试的插入操作
+            for attempt in range(3):
+                try:
+                    result = await self.collection.insert_one(item_dict)
+                    self.crawler.stats.inc_value('mongodb/insert_success')
+                    self.logger.debug(f"插入成功 [attempt {attempt + 1}]: {result.inserted_id}")
+                    return item
+                except PyMongoError as e:
+                    if attempt == 2:  # 最后一次尝试仍失败
+                        raise
+                    self.logger.warning(f"插入重试中 [attempt {attempt + 1}]: {e}")
+
+        except Exception as e:
+            self.crawler.stats.inc_value('mongodb/insert_failed')
+            self.logger.error(f"MongoDB操作最终失败: {e}")
+            raise ItemDiscard(f"MongoDB操作失败: {e}")
+
+    async def spider_closed(self):
+        """资源清理"""
+        if hasattr(self, 'client'):
+            self.client.close()
             self.logger.info("MongoDB连接池已释放")

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")