crawlo 1.3.3__py3-none-any.whl → 1.3.5__py3-none-any.whl

crawlo/utils/batch_processor.py

@@ -1,260 +1,260 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-批处理操作工具
-提供批量操作的统一接口和优化实现
-"""
-import asyncio
-from functools import wraps
-from typing import List, Callable, Any, Optional, Dict
-
-from crawlo.utils.error_handler import ErrorHandler
-from crawlo.utils.log import get_logger
-
-
-class BatchProcessor:
-    """批处理处理器"""
-    
-    def __init__(self, batch_size: int = 100, max_concurrent_batches: int = 5):
-        self.batch_size = batch_size
-        self.max_concurrent_batches = max_concurrent_batches
-        self.logger = get_logger(self.__class__.__name__)
-        self.error_handler = ErrorHandler(self.__class__.__name__)
-    
-    async def process_batch(self, items: List[Any], processor_func: Callable, 
-                           *args, **kwargs) -> List[Any]:
-        """
-        处理一批数据项
-        
-        Args:
-            items: 要处理的数据项列表
-            processor_func: 处理函数
-            *args: 传递给处理函数的额外参数
-            **kwargs: 传递给处理函数的关键字参数
-            
-        Returns:
-            处理结果列表
-        """
-        results = []
-        semaphore = asyncio.Semaphore(self.max_concurrent_batches)
-        
-        async def process_item(item):
-            async with semaphore:
-                try:
-                    if asyncio.iscoroutinefunction(processor_func):
-                        return await processor_func(item, *args, **kwargs)
-                    else:
-                        return processor_func(item, *args, **kwargs)
-                except Exception as e:
-                    self.logger.error(f"处理单项失败: {e}")
-                    return None
-        
-        # 并发处理批次中的所有项
-        tasks = [process_item(item) for item in items]
-        results = await asyncio.gather(*tasks, return_exceptions=True)
-        
-        # 过滤掉异常结果
-        return [result for result in results if not isinstance(result, Exception)]
-    
-    async def process_in_batches(self, items: List[Any], processor_func: Callable,
-                                *args, **kwargs) -> List[Any]:
-        """
-        分批处理大量数据项
-        
-        Args:
-            items: 要处理的数据项列表
-            processor_func: 处理函数
-            *args: 传递给处理函数的额外参数
-            **kwargs: 传递给处理函数的关键字参数
-            
-        Returns:
-            所有处理结果的列表
-        """
-        all_results = []
-        
-        # 将数据分批处理
-        for i in range(0, len(items), self.batch_size):
-            batch = items[i:i + self.batch_size]
-            self.logger.debug(f"处理批次 {i//self.batch_size + 1}/{(len(items)-1)//self.batch_size + 1}")
-            
-            try:
-                batch_results = await self.process_batch(batch, processor_func, *args, **kwargs)
-                all_results.extend(batch_results)
-            except Exception as e:
-                self.logger.error(f"处理批次失败: {e}")
-                # 继续处理下一个批次而不是中断
-        
-        return all_results
-    
-    def batch_process_decorator(self, batch_size: Optional[int] = None):
-        """
-        装饰器：将函数转换为批处理函数
-        
-        Args:
-            batch_size: 批次大小（如果为None则使用实例的batch_size）
-        """
-        def decorator(func):
-            @wraps(func)
-            async def async_wrapper(items: List[Any], *args, **kwargs):
-                actual_batch_size = batch_size or self.batch_size
-                processor = BatchProcessor(actual_batch_size, self.max_concurrent_batches)
-                return await processor.process_in_batches(items, func, *args, **kwargs)
-            
-            @wraps(func)
-            def sync_wrapper(items: List[Any], *args, **kwargs):
-                # 同步版本使用事件循环运行异步函数
-                return asyncio.run(async_wrapper(items, *args, **kwargs))
-            
-            # 根据原函数是否为异步函数返回相应的包装器
-            import inspect
-            if inspect.iscoroutinefunction(func):
-                return async_wrapper
-            else:
-                return sync_wrapper
-        
-        return decorator
-
-
-class RedisBatchProcessor:
-    """Redis批处理处理器"""
-    
-    def __init__(self, redis_client, batch_size: int = 100):
-        self.redis_client = redis_client
-        self.batch_size = batch_size
-        self.logger = get_logger(self.__class__.__name__)
-        self.error_handler = ErrorHandler(self.__class__.__name__)
-    
-    async def batch_set(self, items: List[Dict[str, Any]]) -> int:
-        """
-        批量设置Redis键值对
-        
-        Args:
-            items: 包含key和value的字典列表
-            
-        Returns:
-            成功设置的键值对数量
-        """
-        try:
-            pipe = self.redis_client.pipeline()
-            count = 0
-            
-            for item in items:
-                if 'key' in item and 'value' in item:
-                    pipe.set(item['key'], item['value'])
-                    count += 1
-                    
-                    # 每达到批次大小就执行一次
-                    if count % self.batch_size == 0:
-                        await pipe.execute()
-                        pipe = self.redis_client.pipeline()
-            
-            # 执行剩余的操作
-            if count % self.batch_size != 0:
-                await pipe.execute()
-            
-            self.logger.debug(f"批量设置 {count} 个键值对")
-            return count
-        except Exception as e:
-            self.error_handler.handle_error(
-                e, 
-                context="Redis批量设置失败", 
-                raise_error=False
-            )
-            return 0
-    
-    async def batch_get(self, keys: List[str]) -> Dict[str, Any]:
-        """
-        批量获取Redis键值
-        
-        Args:
-            keys: 要获取的键列表
-            
-        Returns:
-            键值对字典
-        """
-        try:
-            # 使用管道批量获取
-            pipe = self.redis_client.pipeline()
-            for key in keys:
-                pipe.get(key)
-            
-            results = await pipe.execute()
-            
-            # 构建结果字典
-            result_dict = {}
-            for i, key in enumerate(keys):
-                if results[i] is not None:
-                    result_dict[key] = results[i]
-            
-            self.logger.debug(f"批量获取 {len(result_dict)} 个键值对")
-            return result_dict
-        except Exception as e:
-            self.error_handler.handle_error(
-                e, 
-                context="Redis批量获取失败", 
-                raise_error=False
-            )
-            return {}
-    
-    async def batch_delete(self, keys: List[str]) -> int:
-        """
-        批量删除Redis键
-        
-        Args:
-            keys: 要删除的键列表
-            
-        Returns:
-            成功删除的键数量
-        """
-        try:
-            pipe = self.redis_client.pipeline()
-            count = 0
-            
-            for key in keys:
-                pipe.delete(key)
-                count += 1
-                
-                # 每达到批次大小就执行一次
-                if count % self.batch_size == 0:
-                    await pipe.execute()
-                    pipe = self.redis_client.pipeline()
-            
-            # 执行剩余的操作
-            if count % self.batch_size != 0:
-                await pipe.execute()
-            
-            self.logger.debug(f"批量删除 {count} 个键")
-            return count
-        except Exception as e:
-            self.error_handler.handle_error(
-                e, 
-                context="Redis批量删除失败", 
-                raise_error=False
-            )
-            return 0
-
-
-# 全局批处理器实例
-default_batch_processor = BatchProcessor()
-
-
-def batch_process(items: List[Any], processor_func: Callable, 
-                 batch_size: int = 100, max_concurrent_batches: int = 5,
-                 *args, **kwargs) -> List[Any]:
-    """
-    便捷函数：批处理数据项
-    
-    Args:
-        items: 要处理的数据项列表
-        processor_func: 处理函数
-        batch_size: 批次大小
-        max_concurrent_batches: 最大并发批次数量
-        *args: 传递给处理函数的额外参数
-        **kwargs: 传递给处理函数的关键字参数
-        
-    Returns:
-        所有处理结果的列表
-    """
-    processor = BatchProcessor(batch_size, max_concurrent_batches)
-    import asyncio
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+批处理操作工具
+提供批量操作的统一接口和优化实现
+"""
+import asyncio
+from functools import wraps
+from typing import List, Callable, Any, Optional, Dict
+
+from crawlo.utils.error_handler import ErrorHandler
+from crawlo.utils.log import get_logger
+
+
+class BatchProcessor:
+    """批处理处理器"""
+    
+    def __init__(self, batch_size: int = 100, max_concurrent_batches: int = 5):
+        self.batch_size = batch_size
+        self.max_concurrent_batches = max_concurrent_batches
+        self.logger = get_logger(self.__class__.__name__)
+        self.error_handler = ErrorHandler(self.__class__.__name__)
+    
+    async def process_batch(self, items: List[Any], processor_func: Callable, 
+                           *args, **kwargs) -> List[Any]:
+        """
+        处理一批数据项
+        
+        Args:
+            items: 要处理的数据项列表
+            processor_func: 处理函数
+            *args: 传递给处理函数的额外参数
+            **kwargs: 传递给处理函数的关键字参数
+            
+        Returns:
+            处理结果列表
+        """
+        results = []
+        semaphore = asyncio.Semaphore(self.max_concurrent_batches)
+        
+        async def process_item(item):
+            async with semaphore:
+                try:
+                    if asyncio.iscoroutinefunction(processor_func):
+                        return await processor_func(item, *args, **kwargs)
+                    else:
+                        return processor_func(item, *args, **kwargs)
+                except Exception as e:
+                    self.logger.error(f"处理单项失败: {e}")
+                    return None
+        
+        # 并发处理批次中的所有项
+        tasks = [process_item(item) for item in items]
+        results = await asyncio.gather(*tasks, return_exceptions=True)
+        
+        # 过滤掉异常结果
+        return [result for result in results if not isinstance(result, Exception)]
+    
+    async def process_in_batches(self, items: List[Any], processor_func: Callable,
+                                *args, **kwargs) -> List[Any]:
+        """
+        分批处理大量数据项
+        
+        Args:
+            items: 要处理的数据项列表
+            processor_func: 处理函数
+            *args: 传递给处理函数的额外参数
+            **kwargs: 传递给处理函数的关键字参数
+            
+        Returns:
+            所有处理结果的列表
+        """
+        all_results = []
+        
+        # 将数据分批处理
+        for i in range(0, len(items), self.batch_size):
+            batch = items[i:i + self.batch_size]
+            self.logger.debug(f"处理批次 {i//self.batch_size + 1}/{(len(items)-1)//self.batch_size + 1}")
+            
+            try:
+                batch_results = await self.process_batch(batch, processor_func, *args, **kwargs)
+                all_results.extend(batch_results)
+            except Exception as e:
+                self.logger.error(f"处理批次失败: {e}")
+                # 继续处理下一个批次而不是中断
+        
+        return all_results
+    
+    def batch_process_decorator(self, batch_size: Optional[int] = None):
+        """
+        装饰器：将函数转换为批处理函数
+        
+        Args:
+            batch_size: 批次大小（如果为None则使用实例的batch_size）
+        """
+        def decorator(func):
+            @wraps(func)
+            async def async_wrapper(items: List[Any], *args, **kwargs):
+                actual_batch_size = batch_size or self.batch_size
+                processor = BatchProcessor(actual_batch_size, self.max_concurrent_batches)
+                return await processor.process_in_batches(items, func, *args, **kwargs)
+            
+            @wraps(func)
+            def sync_wrapper(items: List[Any], *args, **kwargs):
+                # 同步版本使用事件循环运行异步函数
+                return asyncio.run(async_wrapper(items, *args, **kwargs))
+            
+            # 根据原函数是否为异步函数返回相应的包装器
+            import inspect
+            if inspect.iscoroutinefunction(func):
+                return async_wrapper
+            else:
+                return sync_wrapper
+        
+        return decorator
+
+
+class RedisBatchProcessor:
+    """Redis批处理处理器"""
+    
+    def __init__(self, redis_client, batch_size: int = 100):
+        self.redis_client = redis_client
+        self.batch_size = batch_size
+        self.logger = get_logger(self.__class__.__name__)
+        self.error_handler = ErrorHandler(self.__class__.__name__)
+    
+    async def batch_set(self, items: List[Dict[str, Any]]) -> int:
+        """
+        批量设置Redis键值对
+        
+        Args:
+            items: 包含key和value的字典列表
+            
+        Returns:
+            成功设置的键值对数量
+        """
+        try:
+            pipe = self.redis_client.pipeline()
+            count = 0
+            
+            for item in items:
+                if 'key' in item and 'value' in item:
+                    pipe.set(item['key'], item['value'])
+                    count += 1
+                    
+                    # 每达到批次大小就执行一次
+                    if count % self.batch_size == 0:
+                        await pipe.execute()
+                        pipe = self.redis_client.pipeline()
+            
+            # 执行剩余的操作
+            if count % self.batch_size != 0:
+                await pipe.execute()
+            
+            self.logger.debug(f"批量设置 {count} 个键值对")
+            return count
+        except Exception as e:
+            self.error_handler.handle_error(
+                e, 
+                context="Redis批量设置失败", 
+                raise_error=False
+            )
+            return 0
+    
+    async def batch_get(self, keys: List[str]) -> Dict[str, Any]:
+        """
+        批量获取Redis键值
+        
+        Args:
+            keys: 要获取的键列表
+            
+        Returns:
+            键值对字典
+        """
+        try:
+            # 使用管道批量获取
+            pipe = self.redis_client.pipeline()
+            for key in keys:
+                pipe.get(key)
+            
+            results = await pipe.execute()
+            
+            # 构建结果字典
+            result_dict = {}
+            for i, key in enumerate(keys):
+                if results[i] is not None:
+                    result_dict[key] = results[i]
+            
+            self.logger.debug(f"批量获取 {len(result_dict)} 个键值对")
+            return result_dict
+        except Exception as e:
+            self.error_handler.handle_error(
+                e, 
+                context="Redis批量获取失败", 
+                raise_error=False
+            )
+            return {}
+    
+    async def batch_delete(self, keys: List[str]) -> int:
+        """
+        批量删除Redis键
+        
+        Args:
+            keys: 要删除的键列表
+            
+        Returns:
+            成功删除的键数量
+        """
+        try:
+            pipe = self.redis_client.pipeline()
+            count = 0
+            
+            for key in keys:
+                pipe.delete(key)
+                count += 1
+                
+                # 每达到批次大小就执行一次
+                if count % self.batch_size == 0:
+                    await pipe.execute()
+                    pipe = self.redis_client.pipeline()
+            
+            # 执行剩余的操作
+            if count % self.batch_size != 0:
+                await pipe.execute()
+            
+            self.logger.debug(f"批量删除 {count} 个键")
+            return count
+        except Exception as e:
+            self.error_handler.handle_error(
+                e, 
+                context="Redis批量删除失败", 
+                raise_error=False
+            )
+            return 0
+
+
+# 全局批处理器实例
+default_batch_processor = BatchProcessor()
+
+
+def batch_process(items: List[Any], processor_func: Callable, 
+                 batch_size: int = 100, max_concurrent_batches: int = 5,
+                 *args, **kwargs) -> List[Any]:
+    """
+    便捷函数：批处理数据项
+    
+    Args:
+        items: 要处理的数据项列表
+        processor_func: 处理函数
+        batch_size: 批次大小
+        max_concurrent_batches: 最大并发批次数量
+        *args: 传递给处理函数的额外参数
+        **kwargs: 传递给处理函数的关键字参数
+        
+    Returns:
+        所有处理结果的列表
+    """
+    processor = BatchProcessor(batch_size, max_concurrent_batches)
+    import asyncio
     return asyncio.run(processor.process_in_batches(items, processor_func, *args, **kwargs))

crawlo/utils/class_loader.py

@@ -0,0 +1,26 @@
+# -*- coding: UTF-8 -*-
+"""
+类加载器工具模块
+==============
+提供动态类加载功能，避免循环依赖问题。
+"""
+import importlib
+from typing import Any
+
+
+def load_class(path: str) -> Any:
+    """
+    动态加载类
+    
+    Args:
+        path: 类的完整路径，如 'package.module.ClassName'
+        
+    Returns:
+        加载的类对象
+    """
+    try:
+        module_path, class_name = path.rsplit('.', 1)
+        module = importlib.import_module(module_path)
+        return getattr(module, class_name)
+    except (ValueError, ImportError, AttributeError) as e:
+        raise ImportError(f"无法加载类 '{path}': {e}")