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

crawlo/tools/request_tools.py

@@ -1,83 +1,83 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-# @Time    : 2025-09-20 10:00
-# @Author  : crawl-coder
-# @Desc    : 请求处理工具
-"""
-from typing import Dict, Any, Optional
-from urllib.parse import urlparse, parse_qs, urlencode, urlunparse
-from copy import deepcopy
-
-
-def build_url(base_url: str, path: str = "", query_params: Optional[Dict[str, Any]] = None) -> str:
-    """
-    构建完整的URL
-    
-    :param base_url: 基础URL
-    :param path: 路径
-    :param query_params: 查询参数字典
-    :return: 完整的URL
-    """
-    # 解析基础URL
-    parsed = urlparse(base_url)
-    
-    # 合并路径
-    if path:
-        # 确保路径以/开头
-        if not path.startswith('/'):
-            path = '/' + path
-        # 合并路径
-        new_path = parsed.path.rstrip('/') + path
-    else:
-        new_path = parsed.path
-    
-    # 处理查询参数
-    if query_params:
-        # 解析现有查询参数
-        existing_params = parse_qs(parsed.query)
-        # 合并新参数
-        for key, value in query_params.items():
-            existing_params[key] = [str(value)]
-        # 编码查询参数
-        new_query = urlencode(existing_params, doseq=True)
-    else:
-        new_query = parsed.query
-    
-    # 构建新的URL
-    new_parsed = parsed._replace(path=new_path, query=new_query)
-    return urlunparse(new_parsed)
-
-
-def add_query_params(url: str, params: Dict[str, Any]) -> str:
-    """
-    向URL添加查询参数
-    
-    :param url: 原始URL
-    :param params: 要添加的参数字典
-    :return: 添加参数后的URL
-    """
-    parsed = urlparse(url)
-    # 解析现有查询参数
-    existing_params = parse_qs(parsed.query)
-    # 添加新参数
-    for key, value in params.items():
-        existing_params[key] = [str(value)]
-    # 编码查询参数
-    new_query = urlencode(existing_params, doseq=True)
-    # 构建新的URL
-    new_parsed = parsed._replace(query=new_query)
-    return urlunparse(new_parsed)
-
-
-def merge_headers(base_headers: Dict[str, str], additional_headers: Dict[str, str]) -> Dict[str, str]:
-    """
-    合并请求头
-    
-    :param base_headers: 基础请求头
-    :param additional_headers: 要添加的请求头
-    :return: 合并后的请求头
-    """
-    merged = deepcopy(base_headers)
-    merged.update(additional_headers)
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+# @Time    : 2025-09-20 10:00
+# @Author  : crawl-coder
+# @Desc    : 请求处理工具
+"""
+from typing import Dict, Any, Optional
+from urllib.parse import urlparse, parse_qs, urlencode, urlunparse
+from copy import deepcopy
+
+
+def build_url(base_url: str, path: str = "", query_params: Optional[Dict[str, Any]] = None) -> str:
+    """
+    构建完整的URL
+    
+    :param base_url: 基础URL
+    :param path: 路径
+    :param query_params: 查询参数字典
+    :return: 完整的URL
+    """
+    # 解析基础URL
+    parsed = urlparse(base_url)
+    
+    # 合并路径
+    if path:
+        # 确保路径以/开头
+        if not path.startswith('/'):
+            path = '/' + path
+        # 合并路径
+        new_path = parsed.path.rstrip('/') + path
+    else:
+        new_path = parsed.path
+    
+    # 处理查询参数
+    if query_params:
+        # 解析现有查询参数
+        existing_params = parse_qs(parsed.query)
+        # 合并新参数
+        for key, value in query_params.items():
+            existing_params[key] = [str(value)]
+        # 编码查询参数
+        new_query = urlencode(existing_params, doseq=True)
+    else:
+        new_query = parsed.query
+    
+    # 构建新的URL
+    new_parsed = parsed._replace(path=new_path, query=new_query)
+    return urlunparse(new_parsed)
+
+
+def add_query_params(url: str, params: Dict[str, Any]) -> str:
+    """
+    向URL添加查询参数
+    
+    :param url: 原始URL
+    :param params: 要添加的参数字典
+    :return: 添加参数后的URL
+    """
+    parsed = urlparse(url)
+    # 解析现有查询参数
+    existing_params = parse_qs(parsed.query)
+    # 添加新参数
+    for key, value in params.items():
+        existing_params[key] = [str(value)]
+    # 编码查询参数
+    new_query = urlencode(existing_params, doseq=True)
+    # 构建新的URL
+    new_parsed = parsed._replace(query=new_query)
+    return urlunparse(new_parsed)
+
+
+def merge_headers(base_headers: Dict[str, str], additional_headers: Dict[str, str]) -> Dict[str, str]:
+    """
+    合并请求头
+    
+    :param base_headers: 基础请求头
+    :param additional_headers: 要添加的请求头
+    :return: 合并后的请求头
+    """
+    merged = deepcopy(base_headers)
+    merged.update(additional_headers)
     return merged

crawlo/tools/retry_mechanism.py

@@ -1,224 +1,224 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-# @Time    : 2025-09-10 22:00
-# @Author  : crawl-coder
-# @Desc    : 重试机制工具
-"""
-
-import time
-import random
-import asyncio
-from typing import Callable, Any, Optional, Tuple, Set
-from functools import wraps
-
-
-class RetryMechanism:
-    """重试机制工具类"""
-
-    # 默认应该重试的HTTP状态码
-    DEFAULT_RETRY_STATUS_CODES = {429, 500, 502, 503, 504}
-
-    # 默认应该重试的异常类型
-    DEFAULT_RETRY_EXCEPTIONS = (
-        ConnectionError,
-        TimeoutError,
-        asyncio.TimeoutError,
-    )
-
-    def __init__(self, max_retries: int = 3,
-                 retry_status_codes: Optional[Set[int]] = None,
-                 retry_exceptions: Optional[Tuple[type, ...]] = None):
-        """
-        初始化重试机制
-        
-        Args:
-            max_retries (int): 最大重试次数
-            retry_status_codes (Optional[Set[int]]): 应该重试的HTTP状态码
-            retry_exceptions (Optional[Tuple[type, ...]]): 应该重试的异常类型
-        """
-        self.max_retries = max_retries
-        self.retry_status_codes = retry_status_codes or self.DEFAULT_RETRY_STATUS_CODES
-        self.retry_exceptions = retry_exceptions or self.DEFAULT_RETRY_EXCEPTIONS
-
-    def should_retry(self, status_code: Optional[int] = None,
-                     exception: Optional[Exception] = None) -> bool:
-        """
-        判断是否应该重试
-        
-        Args:
-            status_code (Optional[int]): HTTP状态码
-            exception (Optional[Exception]): 异常对象
-            
-        Returns:
-            bool: 是否应该重试
-        """
-        # 如果有状态码，检查是否在重试列表中
-        if status_code is not None and status_code in self.retry_status_codes:
-            return True
-
-        # 如果有异常，检查是否在重试列表中
-        if exception is not None and isinstance(exception, self.retry_exceptions):
-            return True
-
-        return False
-
-    def exponential_backoff(self, attempt: int, base_delay: float = 1.0,
-                            max_delay: float = 60.0) -> float:
-        """
-        计算指数退避延迟时间
-        
-        Args:
-            attempt (int): 当前重试次数
-            base_delay (float): 基础延迟时间（秒）
-            max_delay (float): 最大延迟时间（秒）
-            
-        Returns:
-            float: 延迟时间（秒）
-        """
-        # 计算基本延迟：base_delay * (2 ^ attempt)
-        delay = base_delay * (2 ** attempt)
-
-        # 添加随机抖动，避免惊群效应
-        jitter = random.uniform(0, 0.1) * delay
-
-        # 返回最终延迟时间，不超过最大延迟
-        return min(delay + jitter, max_delay)
-
-    async def async_retry(self, func: Callable, *args, **kwargs) -> Any:
-        """
-        异步重试执行函数
-        
-        Args:
-            func (Callable): 要执行的函数
-            *args: 函数参数
-            **kwargs: 函数关键字参数
-            
-        Returns:
-            Any: 函数执行结果
-            
-        Raises:
-            Exception: 如果超过最大重试次数仍未成功，则抛出最后一个异常
-        """
-        last_exception = None
-
-        for attempt in range(self.max_retries + 1):
-            try:
-                result = await func(*args, **kwargs)
-
-                # 如果函数返回状态码，检查是否需要重试
-                if hasattr(result, 'status') and self.should_retry(status_code=result.status):
-                    if attempt < self.max_retries:
-                        delay = self.exponential_backoff(attempt)
-                        await asyncio.sleep(delay)
-                        continue
-                    else:
-                        raise Exception(f"HTTP {result.status} after {self.max_retries} retries")
-
-                return result
-
-            except Exception as e:
-                last_exception = e
-
-                # 检查是否应该重试
-                if self.should_retry(exception=e) and attempt < self.max_retries:
-                    delay = self.exponential_backoff(attempt)
-                    await asyncio.sleep(delay)
-                    continue
-                else:
-                    raise e
-
-        # 如果到达这里，说明所有重试都失败了
-        raise last_exception
-
-    def sync_retry(self, func: Callable, *args, **kwargs) -> Any:
-        """
-        同步重试执行函数
-        
-        Args:
-            func (Callable): 要执行的函数
-            *args: 函数参数
-            **kwargs: 函数关键字参数
-            
-        Returns:
-            Any: 函数执行结果
-            
-        Raises:
-            Exception: 如果超过最大重试次数仍未成功，则抛出最后一个异常
-        """
-        last_exception = None
-
-        for attempt in range(self.max_retries + 1):
-            try:
-                result = func(*args, **kwargs)
-
-                # 如果函数返回状态码，检查是否需要重试
-                if hasattr(result, 'status') and self.should_retry(status_code=result.status):
-                    if attempt < self.max_retries:
-                        delay = self.exponential_backoff(attempt)
-                        time.sleep(delay)
-                        continue
-                    else:
-                        raise Exception(f"HTTP {result.status} after {self.max_retries} retries")
-
-                return result
-
-            except Exception as e:
-                last_exception = e
-
-                # 检查是否应该重试
-                if self.should_retry(exception=e) and attempt < self.max_retries:
-                    delay = self.exponential_backoff(attempt)
-                    time.sleep(delay)
-                    continue
-                else:
-                    raise e
-
-        # 如果到达这里，说明所有重试都失败了
-        raise last_exception
-
-
-def retry(max_retries: int = 3,
-          retry_status_codes: Optional[Set[int]] = None,
-          retry_exceptions: Optional[Tuple[type, ...]] = None):
-    """
-    重试装饰器
-    
-    Args:
-        max_retries (int): 最大重试次数
-        retry_status_codes (Optional[Set[int]]): 应该重试的HTTP状态码
-        retry_exceptions (Optional[Tuple[type, ...]]): 应该重试的异常类型
-    """
-
-    def decorator(func: Callable) -> Callable:
-        retry_mechanism = RetryMechanism(max_retries, retry_status_codes, retry_exceptions)
-
-        if asyncio.iscoroutinefunction(func):
-            @wraps(func)
-            async def async_wrapper(*args, **kwargs):
-                return await retry_mechanism.async_retry(func, *args, **kwargs)
-
-            return async_wrapper
-        else:
-            @wraps(func)
-            def sync_wrapper(*args, **kwargs):
-                return retry_mechanism.sync_retry(func, *args, **kwargs)
-
-            return sync_wrapper
-
-    return decorator
-
-
-# 便捷函数
-def should_retry(status_code: Optional[int] = None,
-                 exception: Optional[Exception] = None) -> bool:
-    """判断是否应该重试"""
-    retry_mechanism = RetryMechanism()
-    return retry_mechanism.should_retry(status_code, exception)
-
-
-def exponential_backoff(attempt: int, base_delay: float = 1.0,
-                        max_delay: float = 60.0) -> float:
-    """计算指数退避延迟时间"""
-    retry_mechanism = RetryMechanism()
-    return retry_mechanism.exponential_backoff(attempt, base_delay, max_delay)
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+# @Time    : 2025-09-10 22:00
+# @Author  : crawl-coder
+# @Desc    : 重试机制工具
+"""
+
+import time
+import random
+import asyncio
+from typing import Callable, Any, Optional, Tuple, Set
+from functools import wraps
+
+
+class RetryMechanism:
+    """重试机制工具类"""
+
+    # 默认应该重试的HTTP状态码
+    DEFAULT_RETRY_STATUS_CODES = {429, 500, 502, 503, 504}
+
+    # 默认应该重试的异常类型
+    DEFAULT_RETRY_EXCEPTIONS = (
+        ConnectionError,
+        TimeoutError,
+        asyncio.TimeoutError,
+    )
+
+    def __init__(self, max_retries: int = 3,
+                 retry_status_codes: Optional[Set[int]] = None,
+                 retry_exceptions: Optional[Tuple[type, ...]] = None):
+        """
+        初始化重试机制
+        
+        Args:
+            max_retries (int): 最大重试次数
+            retry_status_codes (Optional[Set[int]]): 应该重试的HTTP状态码
+            retry_exceptions (Optional[Tuple[type, ...]]): 应该重试的异常类型
+        """
+        self.max_retries = max_retries
+        self.retry_status_codes = retry_status_codes or self.DEFAULT_RETRY_STATUS_CODES
+        self.retry_exceptions = retry_exceptions or self.DEFAULT_RETRY_EXCEPTIONS
+
+    def should_retry(self, status_code: Optional[int] = None,
+                     exception: Optional[Exception] = None) -> bool:
+        """
+        判断是否应该重试
+        
+        Args:
+            status_code (Optional[int]): HTTP状态码
+            exception (Optional[Exception]): 异常对象
+            
+        Returns:
+            bool: 是否应该重试
+        """
+        # 如果有状态码，检查是否在重试列表中
+        if status_code is not None and status_code in self.retry_status_codes:
+            return True
+
+        # 如果有异常，检查是否在重试列表中
+        if exception is not None and isinstance(exception, self.retry_exceptions):
+            return True
+
+        return False
+
+    def exponential_backoff(self, attempt: int, base_delay: float = 1.0,
+                            max_delay: float = 60.0) -> float:
+        """
+        计算指数退避延迟时间
+        
+        Args:
+            attempt (int): 当前重试次数
+            base_delay (float): 基础延迟时间（秒）
+            max_delay (float): 最大延迟时间（秒）
+            
+        Returns:
+            float: 延迟时间（秒）
+        """
+        # 计算基本延迟：base_delay * (2 ^ attempt)
+        delay = base_delay * (2 ** attempt)
+
+        # 添加随机抖动，避免惊群效应
+        jitter = random.uniform(0, 0.1) * delay
+
+        # 返回最终延迟时间，不超过最大延迟
+        return min(delay + jitter, max_delay)
+
+    async def async_retry(self, func: Callable, *args, **kwargs) -> Any:
+        """
+        异步重试执行函数
+        
+        Args:
+            func (Callable): 要执行的函数
+            *args: 函数参数
+            **kwargs: 函数关键字参数
+            
+        Returns:
+            Any: 函数执行结果
+            
+        Raises:
+            Exception: 如果超过最大重试次数仍未成功，则抛出最后一个异常
+        """
+        last_exception = None
+
+        for attempt in range(self.max_retries + 1):
+            try:
+                result = await func(*args, **kwargs)
+
+                # 如果函数返回状态码，检查是否需要重试
+                if hasattr(result, 'status') and self.should_retry(status_code=result.status):
+                    if attempt < self.max_retries:
+                        delay = self.exponential_backoff(attempt)
+                        await asyncio.sleep(delay)
+                        continue
+                    else:
+                        raise Exception(f"HTTP {result.status} after {self.max_retries} retries")
+
+                return result
+
+            except Exception as e:
+                last_exception = e
+
+                # 检查是否应该重试
+                if self.should_retry(exception=e) and attempt < self.max_retries:
+                    delay = self.exponential_backoff(attempt)
+                    await asyncio.sleep(delay)
+                    continue
+                else:
+                    raise e
+
+        # 如果到达这里，说明所有重试都失败了
+        raise last_exception
+
+    def sync_retry(self, func: Callable, *args, **kwargs) -> Any:
+        """
+        同步重试执行函数
+        
+        Args:
+            func (Callable): 要执行的函数
+            *args: 函数参数
+            **kwargs: 函数关键字参数
+            
+        Returns:
+            Any: 函数执行结果
+            
+        Raises:
+            Exception: 如果超过最大重试次数仍未成功，则抛出最后一个异常
+        """
+        last_exception = None
+
+        for attempt in range(self.max_retries + 1):
+            try:
+                result = func(*args, **kwargs)
+
+                # 如果函数返回状态码，检查是否需要重试
+                if hasattr(result, 'status') and self.should_retry(status_code=result.status):
+                    if attempt < self.max_retries:
+                        delay = self.exponential_backoff(attempt)
+                        time.sleep(delay)
+                        continue
+                    else:
+                        raise Exception(f"HTTP {result.status} after {self.max_retries} retries")
+
+                return result
+
+            except Exception as e:
+                last_exception = e
+
+                # 检查是否应该重试
+                if self.should_retry(exception=e) and attempt < self.max_retries:
+                    delay = self.exponential_backoff(attempt)
+                    time.sleep(delay)
+                    continue
+                else:
+                    raise e
+
+        # 如果到达这里，说明所有重试都失败了
+        raise last_exception
+
+
+def retry(max_retries: int = 3,
+          retry_status_codes: Optional[Set[int]] = None,
+          retry_exceptions: Optional[Tuple[type, ...]] = None):
+    """
+    重试装饰器
+    
+    Args:
+        max_retries (int): 最大重试次数
+        retry_status_codes (Optional[Set[int]]): 应该重试的HTTP状态码
+        retry_exceptions (Optional[Tuple[type, ...]]): 应该重试的异常类型
+    """
+
+    def decorator(func: Callable) -> Callable:
+        retry_mechanism = RetryMechanism(max_retries, retry_status_codes, retry_exceptions)
+
+        if asyncio.iscoroutinefunction(func):
+            @wraps(func)
+            async def async_wrapper(*args, **kwargs):
+                return await retry_mechanism.async_retry(func, *args, **kwargs)
+
+            return async_wrapper
+        else:
+            @wraps(func)
+            def sync_wrapper(*args, **kwargs):
+                return retry_mechanism.sync_retry(func, *args, **kwargs)
+
+            return sync_wrapper
+
+    return decorator
+
+
+# 便捷函数
+def should_retry(status_code: Optional[int] = None,
+                 exception: Optional[Exception] = None) -> bool:
+    """判断是否应该重试"""
+    retry_mechanism = RetryMechanism()
+    return retry_mechanism.should_retry(status_code, exception)
+
+
+def exponential_backoff(attempt: int, base_delay: float = 1.0,
+                        max_delay: float = 60.0) -> float:
+    """计算指数退避延迟时间"""
+    retry_mechanism = RetryMechanism()
+    return retry_mechanism.exponential_backoff(attempt, base_delay, max_delay)