crawlo 1.4.5__py3-none-any.whl → 1.4.7__py3-none-any.whl

crawlo/initialization/utils.py

@@ -0,0 +1,49 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+初始化工具模块 - 提供通用的初始化工具函数
+"""
+
+import time
+from typing import Optional, Dict, Any
+from .phases import PhaseResult, InitializationPhase
+
+
+def create_initialization_result(
+    phase: 'InitializationPhase',
+    success: bool, 
+    duration: float = 0.0,
+    artifacts: Optional[Dict[str, Any]] = None, 
+    error: Optional[Exception] = None
+) -> PhaseResult:
+    """
+    创建标准化的初始化结果
+    
+    Args:
+        phase: 初始化阶段
+        success: 是否成功
+        duration: 执行时长
+        artifacts: 产生的工件数据
+        error: 异常对象
+        
+    Returns:
+        PhaseResult: 标准化的初始化结果
+    """
+    return PhaseResult(
+        phase=phase,
+        success=success,
+        duration=duration,
+        artifacts=artifacts or {},
+        error=error
+    )
+
+
+class InitializationTimer:
+    """初始化计时器"""
+    
+    def __init__(self):
+        self.start_time = time.time()
+    
+    def get_duration(self) -> float:
+        """获取经过的时间"""
+        return time.time() - self.start_time

crawlo/interfaces.py

@@ -1,24 +1,24 @@
-from abc import ABC, abstractmethod
-from typing import List, Type, Protocol
-
-from crawlo.spider import Spider
-from crawlo.network.request import Request
-
-
-class ISpiderLoader(Protocol):
-    """Spider loader interface"""
-    
-    @abstractmethod
-    def load(self, spider_name: str) -> Type[Spider]:
-        """Load a spider by name"""
-        pass
-    
-    @abstractmethod
-    def list(self) -> List[str]:
-        """List all available spider names"""
-        pass
-    
-    @abstractmethod
-    def find_by_request(self, request: Request) -> List[str]:
-        """Find spider names that can handle the given request"""
+from abc import ABC, abstractmethod
+from typing import List, Type, Protocol
+
+from crawlo.spider import Spider
+from crawlo.network.request import Request
+
+
+class ISpiderLoader(Protocol):
+    """Spider loader interface"""
+    
+    @abstractmethod
+    def load(self, spider_name: str) -> Type[Spider]:
+        """Load a spider by name"""
+        pass
+    
+    @abstractmethod
+    def list(self) -> List[str]:
+        """List all available spider names"""
+        pass
+    
+    @abstractmethod
+    def find_by_request(self, request: Request) -> List[str]:
+        """Find spider names that can handle the given request"""
         pass

crawlo/items/__init__.py

@@ -1,23 +1,23 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-crawlo.items 包
-===============
-提供 Item 和 Field 类用于数据定义和验证。
-"""
-from .items import Item
-from .fields import Field
-from .base import ItemMeta
-
-from crawlo.exceptions import ItemInitError, ItemAttributeError
-
-__all__ = [
-    'Item',
-    'Field',
-    'ItemMeta',
-    'ItemInitError',
-    'ItemAttributeError'
-]
-
-
-
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+crawlo.items 包
+===============
+提供 Item 和 Field 类用于数据定义和验证。
+"""
+from .items import Item
+from .fields import Field
+from .base import ItemMeta
+
+from crawlo.exceptions import ItemInitError, ItemAttributeError
+
+__all__ = [
+    'Item',
+    'Field',
+    'ItemMeta',
+    'ItemInitError',
+    'ItemAttributeError'
+]
+
+
+

crawlo/items/base.py

@@ -1,23 +1,23 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-基础元类定义
-"""
-from abc import ABCMeta
-from .fields import Field
-
-
-class ItemMeta(ABCMeta):
-    def __new__(mcs, name, bases, attrs):
-        fields = {}
-        cls_attrs = {}
-
-        for attr_name, attr_value in attrs.items():
-            if isinstance(attr_value, Field):
-                fields[attr_name] = attr_value
-            else:
-                cls_attrs[attr_name] = attr_value
-
-        cls_instance = super().__new__(mcs, name, bases, cls_attrs)
-        cls_instance.FIELDS = fields
-        return cls_instance
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+基础元类定义
+"""
+from abc import ABCMeta
+from .fields import Field
+
+
+class ItemMeta(ABCMeta):
+    def __new__(mcs, name, bases, attrs):
+        fields = {}
+        cls_attrs = {}
+
+        for attr_name, attr_value in attrs.items():
+            if isinstance(attr_value, Field):
+                fields[attr_name] = attr_value
+            else:
+                cls_attrs[attr_name] = attr_value
+
+        cls_instance = super().__new__(mcs, name, bases, cls_attrs)
+        cls_instance.FIELDS = fields
+        return cls_instance

crawlo/items/fields.py

@@ -1,53 +1,53 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-Field 类定义
-"""
-from typing import Any, Optional, Type
-
-
-class Field:
-    """
-    字段定义类，用于定义 Item 的字段属性和验证规则
-    """
-    def __init__(
-        self,
-        nullable: bool = True,
-        *,
-        default: Any = None,
-        field_type: Optional[Type] = None,
-        max_length: Optional[int] = None,
-        description: str = ""
-    ):
-        self.nullable = nullable
-        self.default = default
-        self.field_type = field_type
-        self.max_length = max_length
-        self.description = description
-
-    def validate(self, value: Any, field_name: str = "") -> Any:
-        """
-        验证字段值是否符合规则
-        """
-        if value is None or (isinstance(value, str) and value.strip() == ""):
-            if self.default is not None:
-                return self.default
-            elif not self.nullable:
-                raise ValueError(
-                    f"字段 '{field_name}' 不允许为空。"
-                )
-
-        if value is not None and not (isinstance(value, str) and value.strip() == ""):
-            if self.field_type and not isinstance(value, self.field_type):
-                raise TypeError(
-                    f"字段 '{field_name}' 类型错误：期望类型 {self.field_type}, 得到 {type(value)}，值：{value!r}"
-                )
-            if self.max_length and len(str(value)) > self.max_length:
-                raise ValueError(
-                    f"字段 '{field_name}' 长度超限：最大长度 {self.max_length}，当前长度 {len(str(value))}，值：{value!r}"
-                )
-
-        return value
-
-    def __repr__(self):
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+Field 类定义
+"""
+from typing import Any, Optional, Type
+
+
+class Field:
+    """
+    字段定义类，用于定义 Item 的字段属性和验证规则
+    """
+    def __init__(
+        self,
+        nullable: bool = True,
+        *,
+        default: Any = None,
+        field_type: Optional[Type] = None,
+        max_length: Optional[int] = None,
+        description: str = ""
+    ):
+        self.nullable = nullable
+        self.default = default
+        self.field_type = field_type
+        self.max_length = max_length
+        self.description = description
+
+    def validate(self, value: Any, field_name: str = "") -> Any:
+        """
+        验证字段值是否符合规则
+        """
+        if value is None or (isinstance(value, str) and value.strip() == ""):
+            if self.default is not None:
+                return self.default
+            elif not self.nullable:
+                raise ValueError(
+                    f"字段 '{field_name}' 不允许为空。"
+                )
+
+        if value is not None and not (isinstance(value, str) and value.strip() == ""):
+            if self.field_type and not isinstance(value, self.field_type):
+                raise TypeError(
+                    f"字段 '{field_name}' 类型错误：期望类型 {self.field_type}, 得到 {type(value)}，值：{value!r}"
+                )
+            if self.max_length and len(str(value)) > self.max_length:
+                raise ValueError(
+                    f"字段 '{field_name}' 长度超限：最大长度 {self.max_length}，当前长度 {len(str(value))}，值：{value!r}"
+                )
+
+        return value
+
+    def __repr__(self):
         return f"<Field nullable={self.nullable} type={self.field_type} default={self.default}>"

crawlo/items/items.py

@@ -1,105 +1,105 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-Item 类定义
-"""
-from copy import deepcopy
-from pprint import pformat
-from typing import Any, Iterator, Dict
-from collections.abc import MutableMapping
-
-from .base import ItemMeta
-from crawlo.exceptions import ItemInitError, ItemAttributeError
-
-
-class Item(MutableMapping, metaclass=ItemMeta):
-    """
-    数据项基类，用于定义结构化数据
-    """
-    FIELDS: Dict[str, Any] = {}
-
-    def __init__(self, *args, **kwargs):
-        if args:
-            raise ItemInitError(f"{self.__class__.__name__} 不支持位置参数：{args}，请使用关键字参数初始化。")
-
-        self._values: Dict[str, Any] = {}
-
-        # 初始化字段，默认值填充
-        for field_name, field_obj in self.FIELDS.items():
-            if field_obj.default is not None:
-                self._values[field_name] = field_obj.default
-
-        # 覆盖默认值或设置新值
-        for key, value in kwargs.items():
-            self[key] = value
-
-    def __getitem__(self, item: str) -> Any:
-        return self._values[item]
-
-    def __setitem__(self, key: str, value: Any) -> None:
-        if key not in self.FIELDS:
-            raise KeyError(f"{self.__class__.__name__} 不包含字段：{key}")
-
-        field = self.FIELDS[key]
-        try:
-            validated_value = field.validate(value, field_name=key)
-            self._values[key] = validated_value
-        except Exception as e:
-            error_lines = [
-                "",
-                "【字段校验失败】",
-                f"字段名称: {key}",
-                f"数据类型: {type(value)}",
-                f"原始值:   {repr(value)}",
-                f"是否允许空值: {field.nullable}",
-                f"错误原因: {str(e)}",
-                ""
-            ]
-            detailed_error = "\n".join(error_lines)
-            raise type(e)(detailed_error) from e
-
-    def __delitem__(self, key: str) -> None:
-        del self._values[key]
-
-    def __setattr__(self, key: str, value: Any) -> None:
-        if not key.startswith("_"):
-            raise AttributeError(
-                f"设置字段值请使用 item[{key!r}] = {value!r}"
-            )
-        super().__setattr__(key, value)
-
-    def __getattr__(self, item: str) -> Any:
-        raise AttributeError(
-            f"{self.__class__.__name__} 不支持字段：{item}。"
-            f"请先在 `{self.__class__.__name__}` 中声明该字段，再通过 item[{item!r}] 获取。"
-        )
-
-    def __getattribute__(self, item: str) -> Any:
-        try:
-            field = super().__getattribute__("FIELDS")
-            if isinstance(field, dict) and item in field:
-                raise ItemAttributeError(
-                    f"获取字段值请使用 item[{item!r}]"
-                )
-        except AttributeError:
-            pass  # 如果 FIELDS 尚未定义，继续执行后续逻辑
-        return super().__getattribute__(item)
-
-    def __repr__(self) -> str:
-        return pformat(dict(self))
-
-    __str__ = __repr__
-
-    def __iter__(self) -> Iterator[str]:
-        return iter(self._values)
-
-    def __len__(self) -> int:
-        return len(self._values)
-
-    def to_dict(self) -> Dict[str, Any]:
-        """转换为字典"""
-        return dict(self)
-
-    def copy(self) -> "Item":
-        """深拷贝当前 Item"""
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+Item 类定义
+"""
+from copy import deepcopy
+from pprint import pformat
+from typing import Any, Iterator, Dict
+from collections.abc import MutableMapping
+
+from .base import ItemMeta
+from crawlo.exceptions import ItemInitError, ItemAttributeError
+
+
+class Item(MutableMapping, metaclass=ItemMeta):
+    """
+    数据项基类，用于定义结构化数据
+    """
+    FIELDS: Dict[str, Any] = {}
+
+    def __init__(self, *args, **kwargs):
+        if args:
+            raise ItemInitError(f"{self.__class__.__name__} 不支持位置参数：{args}，请使用关键字参数初始化。")
+
+        self._values: Dict[str, Any] = {}
+
+        # 初始化字段，默认值填充
+        for field_name, field_obj in self.FIELDS.items():
+            if field_obj.default is not None:
+                self._values[field_name] = field_obj.default
+
+        # 覆盖默认值或设置新值
+        for key, value in kwargs.items():
+            self[key] = value
+
+    def __getitem__(self, item: str) -> Any:
+        return self._values[item]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        if key not in self.FIELDS:
+            raise KeyError(f"{self.__class__.__name__} 不包含字段：{key}")
+
+        field = self.FIELDS[key]
+        try:
+            validated_value = field.validate(value, field_name=key)
+            self._values[key] = validated_value
+        except Exception as e:
+            error_lines = [
+                "",
+                "【字段校验失败】",
+                f"字段名称: {key}",
+                f"数据类型: {type(value)}",
+                f"原始值:   {repr(value)}",
+                f"是否允许空值: {field.nullable}",
+                f"错误原因: {str(e)}",
+                ""
+            ]
+            detailed_error = "\n".join(error_lines)
+            raise type(e)(detailed_error) from e
+
+    def __delitem__(self, key: str) -> None:
+        del self._values[key]
+
+    def __setattr__(self, key: str, value: Any) -> None:
+        if not key.startswith("_"):
+            raise AttributeError(
+                f"设置字段值请使用 item[{key!r}] = {value!r}"
+            )
+        super().__setattr__(key, value)
+
+    def __getattr__(self, item: str) -> Any:
+        raise AttributeError(
+            f"{self.__class__.__name__} 不支持字段：{item}。"
+            f"请先在 `{self.__class__.__name__}` 中声明该字段，再通过 item[{item!r}] 获取。"
+        )
+
+    def __getattribute__(self, item: str) -> Any:
+        try:
+            field = super().__getattribute__("FIELDS")
+            if isinstance(field, dict) and item in field:
+                raise ItemAttributeError(
+                    f"获取字段值请使用 item[{item!r}]"
+                )
+        except AttributeError:
+            pass  # 如果 FIELDS 尚未定义，继续执行后续逻辑
+        return super().__getattribute__(item)
+
+    def __repr__(self) -> str:
+        return pformat(dict(self))
+
+    __str__ = __repr__
+
+    def __iter__(self) -> Iterator[str]:
+        return iter(self._values)
+
+    def __len__(self) -> int:
+        return len(self._values)
+
+    def to_dict(self) -> Dict[str, Any]:
+        """转换为字典"""
+        return dict(self)
+
+    def copy(self) -> "Item":
+        """深拷贝当前 Item"""
         return deepcopy(self)

crawlo/logging/__init__.py

@@ -1,46 +1,42 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-Crawlo统一日志系统
-=================
-
-设计原则：
-1. 简单优先 - 避免过度设计
-2. 性能优先 - 减少锁竞争和复杂逻辑  
-3. 一致性 - 统一的日志接口
-4. 可靠性 - 确保日志始终可用
-"""
-
-from .manager import LogManager
-from .factory import LoggerFactory
-from .config import LogConfig
-from .monitor import LogPerformanceMonitor
-
-# 统一的公共接口
-def get_logger(name: str = 'default'):
-    """获取logger实例"""
-    return LoggerFactory.get_logger(name)
-
-def configure_logging(settings=None, **kwargs):
-    """配置日志系统"""
-    return LogManager().configure(settings, **kwargs)
-
-def is_configured() -> bool:
-    """检查日志系统是否已配置"""
-    return LogManager().is_configured
-
-def get_monitor() -> LogPerformanceMonitor:
-    """获取日志性能监控器"""
-    from .monitor import get_monitor as _get_monitor
-    return _get_monitor()
-
-__all__ = [
-    'LogManager',
-    'LoggerFactory', 
-    'LogConfig',
-    'LogPerformanceMonitor',
-    'get_logger',
-    'configure_logging',
-    'is_configured',
-    'get_monitor'
-]
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+Crawlo统一日志系统
+=================
+
+设计原则：
+1. 简单优先 - 避免过度设计
+2. 性能优先 - 减少锁竞争和复杂逻辑  
+3. 一致性 - 统一的日志接口
+4. 可靠性 - 确保日志始终可用
+"""
+
+from .manager import LogManager
+from .factory import LoggerFactory
+from .config import LogConfig
+
+
+# 统一的公共接口
+def get_logger(name: str = 'default'):
+    """获取logger实例"""
+    return LoggerFactory.get_logger(name)
+
+
+def configure_logging(settings=None, **kwargs):
+    """配置日志系统"""
+    return LogManager().configure(settings, **kwargs)
+
+
+def is_configured() -> bool:
+    """检查日志系统是否已配置"""
+    return LogManager().is_configured
+
+
+__all__ = [
+    'LogManager',
+    'LoggerFactory',
+    'LogConfig',
+    'get_logger',
+    'configure_logging',
+    'is_configured'
+]