crawlo 1.3.3__py3-none-any.whl → 1.3.4__py3-none-any.whl

tests/error_handling_example.py

@@ -1,172 +1,172 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-错误处理使用示例
-展示如何在实际项目中使用增强版错误处理工具
-"""
-import sys
-import os
-import asyncio
-import time
-from typing import Optional
-
-# 添加项目根目录到 Python 路径
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-
-from crawlo.utils.enhanced_error_handler import (
-    EnhancedErrorHandler, 
-    ErrorContext, 
-    DetailedException, 
-    handle_exception
-)
-
-
-# 创建错误处理器实例
-error_handler = EnhancedErrorHandler("example_module")
-
-
-class DatabaseConnectionError(DetailedException):
-    """数据库连接错误"""
-    pass
-
-
-class NetworkTimeoutError(DetailedException):
-    """网络超时错误"""
-    pass
-
-
-@handle_exception(context="数据库连接", module="database", function="connect_to_db", error_code="DB001")
-def connect_to_db(host: str, port: int) -> bool:
-    """模拟数据库连接"""
-    print(f"正在连接数据库 {host}:{port}...")
-    
-    # 模拟连接失败
-    if host == "invalid.host":
-        raise DatabaseConnectionError(
-            "无法连接到数据库服务器",
-            context=ErrorContext(context="数据库连接失败", module="database", function="connect_to_db"),
-            error_code="DB001",
-            host=host,
-            port=port
-        )
-    
-    # 模拟连接成功
-    print("数据库连接成功")
-    return True
-
-
-@error_handler.retry_on_failure(max_retries=3, delay=0.5, backoff_factor=2.0)
-async def fetch_data_from_api(url: str) -> dict:
-    """模拟从API获取数据（带重试机制）"""
-    print(f"正在从 {url} 获取数据...")
-    
-    # 模拟网络问题
-    if url == "https://slow.api.com/data":
-        time.sleep(2)  # 模拟慢速响应
-        raise NetworkTimeoutError(
-            "API响应超时",
-            context=ErrorContext(context="API调用超时", module="api", function="fetch_data_from_api"),
-            error_code="API001",
-            url=url,
-            timeout=1
-        )
-    
-    if url == "https://error.api.com/data":
-        raise NetworkTimeoutError(
-            "API服务器错误",
-            context=ErrorContext(context="API服务器错误", module="api", function="fetch_data_from_api"),
-            error_code="API002",
-            url=url,
-            status_code=500
-        )
-    
-    # 模拟成功响应
-    print("API数据获取成功")
-    return {"data": "sample data", "status": "success"}
-
-
-def process_data(data: dict) -> Optional[str]:
-    """处理数据"""
-    try:
-        print("正在处理数据...")
-        
-        # 模拟处理错误
-        if not data:
-            raise ValueError("数据为空")
-        
-        if "error" in data:
-            raise RuntimeError(f"数据处理失败: {data['error']}")
-        
-        # 模拟处理成功
-        result = f"处理完成: {data.get('data', 'no data')}"
-        print(f"{result}")
-        return result
-        
-    except Exception as e:
-        # 使用错误处理器处理异常
-        context = ErrorContext(context="数据处理", module="data_processor", function="process_data")
-        error_handler.handle_error(e, context=context, raise_error=False)
-        return None
-
-
-async def main():
-    """主函数"""
-    print("错误处理使用示例")
-    print("=" * 50)
-    
-    # 1. 测试数据库连接（成功情况）
-    print("1. 测试数据库连接（成功情况）")
-    try:
-        connect_to_db("localhost", 5432)
-    except Exception as e:
-        print(f"意外错误: {e}")
-    print()
-    
-    # 2. 测试数据库连接（失败情况）
-    print("2. 测试数据库连接（失败情况）")
-    try:
-        connect_to_db("invalid.host", 5432)
-    except Exception as e:
-        print(f"预期的数据库连接错误: {e}")
-    print()
-    
-    # 3. 测试API调用（成功情况）
-    print("3. 测试API调用（成功情况）")
-    try:
-        data = await fetch_data_from_api("https://api.com/data")
-        process_data(data)
-    except Exception as e:
-        print(f"API调用错误: {e}")
-    print()
-    
-    # 4. 测试API调用（失败情况，带重试）
-    print("4. 测试API调用（失败情况，带重试）")
-    try:
-        data = await fetch_data_from_api("https://error.api.com/data")
-        process_data(data)
-    except Exception as e:
-        print(f"API调用错误（重试后仍然失败）: {e}")
-    print()
-    
-    # 5. 测试数据处理（失败情况）
-    print("5. 测试数据处理（失败情况）")
-    process_data(None)  # 空数据
-    process_data({"error": "invalid format"})  # 错误数据
-    print()
-    
-    # 6. 查看错误历史
-    print("6. 错误历史记录")
-    history = error_handler.get_error_history()
-    print(f"共记录 {len(history)} 个错误:")
-    for i, record in enumerate(history, 1):
-        print(f"  {i}. {record['exception_type']}: {record['message']}")
-        if record['context']:
-            print(f"     上下文: {record['context']}")
-    print()
-    
-    print("=" * 50)
-    print("示例运行完成")
-
-
-if __name__ == "__main__":
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+错误处理使用示例
+展示如何在实际项目中使用增强版错误处理工具
+"""
+import sys
+import os
+import asyncio
+import time
+from typing import Optional
+
+# 添加项目根目录到 Python 路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.utils.enhanced_error_handler import (
+    EnhancedErrorHandler, 
+    ErrorContext, 
+    DetailedException, 
+    handle_exception
+)
+
+
+# 创建错误处理器实例
+error_handler = EnhancedErrorHandler("example_module")
+
+
+class DatabaseConnectionError(DetailedException):
+    """数据库连接错误"""
+    pass
+
+
+class NetworkTimeoutError(DetailedException):
+    """网络超时错误"""
+    pass
+
+
+@handle_exception(context="数据库连接", module="database", function="connect_to_db", error_code="DB001")
+def connect_to_db(host: str, port: int) -> bool:
+    """模拟数据库连接"""
+    print(f"正在连接数据库 {host}:{port}...")
+    
+    # 模拟连接失败
+    if host == "invalid.host":
+        raise DatabaseConnectionError(
+            "无法连接到数据库服务器",
+            context=ErrorContext(context="数据库连接失败", module="database", function="connect_to_db"),
+            error_code="DB001",
+            host=host,
+            port=port
+        )
+    
+    # 模拟连接成功
+    print("数据库连接成功")
+    return True
+
+
+@error_handler.retry_on_failure(max_retries=3, delay=0.5, backoff_factor=2.0)
+async def fetch_data_from_api(url: str) -> dict:
+    """模拟从API获取数据（带重试机制）"""
+    print(f"正在从 {url} 获取数据...")
+    
+    # 模拟网络问题
+    if url == "https://slow.api.com/data":
+        time.sleep(2)  # 模拟慢速响应
+        raise NetworkTimeoutError(
+            "API响应超时",
+            context=ErrorContext(context="API调用超时", module="api", function="fetch_data_from_api"),
+            error_code="API001",
+            url=url,
+            timeout=1
+        )
+    
+    if url == "https://error.api.com/data":
+        raise NetworkTimeoutError(
+            "API服务器错误",
+            context=ErrorContext(context="API服务器错误", module="api", function="fetch_data_from_api"),
+            error_code="API002",
+            url=url,
+            status_code=500
+        )
+    
+    # 模拟成功响应
+    print("API数据获取成功")
+    return {"data": "sample data", "status": "success"}
+
+
+def process_data(data: dict) -> Optional[str]:
+    """处理数据"""
+    try:
+        print("正在处理数据...")
+        
+        # 模拟处理错误
+        if not data:
+            raise ValueError("数据为空")
+        
+        if "error" in data:
+            raise RuntimeError(f"数据处理失败: {data['error']}")
+        
+        # 模拟处理成功
+        result = f"处理完成: {data.get('data', 'no data')}"
+        print(f"{result}")
+        return result
+        
+    except Exception as e:
+        # 使用错误处理器处理异常
+        context = ErrorContext(context="数据处理", module="data_processor", function="process_data")
+        error_handler.handle_error(e, context=context, raise_error=False)
+        return None
+
+
+async def main():
+    """主函数"""
+    print("错误处理使用示例")
+    print("=" * 50)
+    
+    # 1. 测试数据库连接（成功情况）
+    print("1. 测试数据库连接（成功情况）")
+    try:
+        connect_to_db("localhost", 5432)
+    except Exception as e:
+        print(f"意外错误: {e}")
+    print()
+    
+    # 2. 测试数据库连接（失败情况）
+    print("2. 测试数据库连接（失败情况）")
+    try:
+        connect_to_db("invalid.host", 5432)
+    except Exception as e:
+        print(f"预期的数据库连接错误: {e}")
+    print()
+    
+    # 3. 测试API调用（成功情况）
+    print("3. 测试API调用（成功情况）")
+    try:
+        data = await fetch_data_from_api("https://api.com/data")
+        process_data(data)
+    except Exception as e:
+        print(f"API调用错误: {e}")
+    print()
+    
+    # 4. 测试API调用（失败情况，带重试）
+    print("4. 测试API调用（失败情况，带重试）")
+    try:
+        data = await fetch_data_from_api("https://error.api.com/data")
+        process_data(data)
+    except Exception as e:
+        print(f"API调用错误（重试后仍然失败）: {e}")
+    print()
+    
+    # 5. 测试数据处理（失败情况）
+    print("5. 测试数据处理（失败情况）")
+    process_data(None)  # 空数据
+    process_data({"error": "invalid format"})  # 错误数据
+    print()
+    
+    # 6. 查看错误历史
+    print("6. 错误历史记录")
+    history = error_handler.get_error_history()
+    print(f"共记录 {len(history)} 个错误:")
+    for i, record in enumerate(history, 1):
+        print(f"  {i}. {record['exception_type']}: {record['message']}")
+        if record['context']:
+            print(f"     上下文: {record['context']}")
+    print()
+    
+    print("=" * 50)
+    print("示例运行完成")
+
+
+if __name__ == "__main__":
     asyncio.run(main())

tests/final_comprehensive_test.py

@@ -0,0 +1,152 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+最终综合测试脚本
+全面测试框架的所有核心功能，特别是我们修改的部分
+"""
+
+import sys
+import os
+import asyncio
+import time
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.spider import Spider
+from crawlo import Request
+
+
+class TestSpider(Spider):
+    """测试爬虫"""
+    name = 'final_test_spider'
+    
+    def start_requests(self):
+        """发起测试请求"""
+        # 生成一些测试请求
+        for i in range(5):
+            yield Request(f'https://httpbin.org/get?page={i}', callback=self.parse)
+    
+    def parse(self, response):
+        """解析响应"""
+        print(f"成功获取响应: {response.url}")
+        print(f"状态码: {response.status_code}")
+        return []
+
+
+async def test_queue_blocking_behavior():
+    """测试队列阻塞行为"""
+    print("测试队列阻塞行为...")
+    
+    from crawlo.queue.queue_manager import QueueConfig, QueueManager
+    
+    # 创建小队列配置
+    queue_config = QueueConfig(
+        queue_type='memory',
+        max_queue_size=3  # 非常小的队列
+    )
+    
+    # 创建队列管理器
+    queue_manager = QueueManager(queue_config)
+    await queue_manager.initialize()
+    
+    # 测试添加超过队列大小的请求
+    print("添加6个请求到大小为3的队列...")
+    start_time = time.time()
+    
+    # 创建生产者任务
+    async def producer():
+        for i in range(6):
+            request = Request(f'https://example.com/test{i}')
+            await queue_manager.put(request)
+            print(f"添加请求 {i}")
+    
+    # 创建消费者任务
+    async def consumer():
+        retrieved = 0
+        while retrieved < 6:
+            request = await queue_manager.get(timeout=2.0)
+            if request:
+                print(f"获取请求: {request.url}")
+                retrieved += 1
+                await asyncio.sleep(0.1)  # 模拟处理时间
+    
+    # 并发运行生产者和消费者
+    await asyncio.gather(producer(), consumer())
+    
+    end_time = time.time()
+    print(f"队列测试完成，耗时 {end_time - start_time:.2f} 秒")
+    
+    # 关闭队列
+    await queue_manager.close()
+
+
+async def test_framework_initialization():
+    """测试框架初始化"""
+    print("测试框架初始化...")
+    
+    from crawlo.initialization import initialize_framework
+    
+    # 测试默认配置
+    settings = initialize_framework()
+    print(f"默认配置 - RUN_MODE: {settings.get('RUN_MODE')}")
+    print(f"默认配置 - QUEUE_TYPE: {settings.get('QUEUE_TYPE')}")
+    
+    # 测试自定义配置
+    custom_settings = {
+        'PROJECT_NAME': 'final_test',
+        'SCHEDULER_MAX_QUEUE_SIZE': 100
+    }
+    
+    settings = initialize_framework(custom_settings)
+    print(f"自定义配置 - PROJECT_NAME: {settings.get('PROJECT_NAME')}")
+    print(f"自定义配置 - SCHEDULER_MAX_QUEUE_SIZE: {settings.get('SCHEDULER_MAX_QUEUE_SIZE')}")
+
+
+async def test_crawler_execution():
+    """测试爬虫执行"""
+    print("测试爬虫执行...")
+    
+    from crawlo.initialization import initialize_framework
+    from crawlo.crawler import CrawlerProcess
+    
+    # 初始化框架
+    settings = initialize_framework({
+        'PROJECT_NAME': 'final_test'
+    })
+    
+    # 创建爬虫进程
+    process = CrawlerProcess(settings=settings)
+    
+    # 运行爬虫
+    await process.crawl(TestSpider)
+
+
+async def main():
+    """主函数"""
+    print("开始最终综合测试...")
+    print("=" * 50)
+    
+    try:
+        # 1. 测试框架初始化
+        await test_framework_initialization()
+        print()
+        
+        # 2. 测试队列阻塞行为
+        await test_queue_blocking_behavior()
+        print()
+        
+        # 3. 测试爬虫执行
+        await test_crawler_execution()
+        print()
+        
+        print("=" * 50)
+        print("所有测试通过！框架工作正常。")
+        
+    except Exception as e:
+        print("=" * 50)
+        print(f"测试失败: {e}")
+        import traceback
+        traceback.print_exc()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

tests/final_validation_test.py

@@ -0,0 +1,183 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+最终验证测试脚本
+验证所有修改的功能是否正常工作
+"""
+
+import sys
+import os
+import asyncio
+import time
+
+# 添加项目根目录到Python路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.spider import Spider
+from crawlo import Request
+
+
+class ValidationTestSpider(Spider):
+    """验证测试爬虫"""
+    name = 'validation_test_spider'
+    
+    def start_requests(self):
+        """发起测试请求"""
+        # 生成一些测试请求
+        for i in range(3):
+            yield Request(f'https://httpbin.org/get?page={i}', callback=self.parse)
+    
+    def parse(self, response):
+        """解析响应"""
+        print(f"成功获取响应: {response.url}")
+        print(f"状态码: {response.status_code}")
+        return []
+
+
+async def test_framework_startup_logging():
+    """测试框架启动日志"""
+    print("测试框架启动日志...")
+    
+    from crawlo.initialization import initialize_framework
+    from crawlo.logging import get_logger
+    
+    # 初始化框架
+    settings = initialize_framework({
+        'PROJECT_NAME': 'validation_test'
+    })
+    
+    # 获取框架logger并检查启动日志
+    logger = get_logger('crawlo.framework')
+    print("框架启动日志已记录")
+
+
+async def test_queue_blocking_behavior():
+    """测试队列阻塞行为"""
+    print("测试队列阻塞行为...")
+    
+    from crawlo.queue.queue_manager import QueueConfig, QueueManager
+    from crawlo import Request
+    
+    # 创建小队列配置进行测试
+    queue_config = QueueConfig(
+        queue_type='memory',
+        max_queue_size=3  # 非常小的队列
+    )
+    
+    # 创建队列管理器
+    queue_manager = QueueManager(queue_config)
+    await queue_manager.initialize()
+    
+    # 测试添加超过队列大小的请求
+    print("添加5个请求到大小为3的队列...")
+    start_time = time.time()
+    
+    # 创建生产者任务
+    async def producer():
+        for i in range(5):
+            request = Request(f'https://example.com/test{i}')
+            await queue_manager.put(request)
+            print(f"添加请求 {i}")
+    
+    # 创建消费者任务
+    async def consumer():
+        retrieved = 0
+        while retrieved < 5:
+            request = await queue_manager.get(timeout=2.0)
+            if request:
+                print(f"获取请求: {request.url}")
+                retrieved += 1
+                await asyncio.sleep(0.1)  # 模拟处理时间
+    
+    # 并发运行生产者和消费者
+    await asyncio.gather(producer(), consumer())
+    
+    end_time = time.time()
+    print(f"队列测试完成，耗时 {end_time - start_time:.2f} 秒")
+    
+    # 关闭队列
+    await queue_manager.close()
+
+
+async def test_stats_output():
+    """测试统计信息输出"""
+    print("测试统计信息输出...")
+    
+    from crawlo.initialization import initialize_framework
+    from crawlo.crawler import CrawlerProcess
+    
+    # 初始化框架
+    settings = initialize_framework({
+        'PROJECT_NAME': 'stats_test'
+    })
+    
+    # 创建爬虫进程
+    process = CrawlerProcess(settings=settings)
+    
+    # 运行爬虫
+    await process.crawl(ValidationTestSpider)
+    
+    print("统计信息输出测试完成")
+
+
+async def test_spider_auto_import():
+    """测试爬虫自动导入"""
+    print("测试爬虫自动导入...")
+    
+    from crawlo.initialization import initialize_framework
+    from crawlo.crawler import CrawlerProcess
+    
+    # 初始化框架
+    settings = initialize_framework({
+        'PROJECT_NAME': 'auto_import_test'
+    })
+    
+    # 创建爬虫进程，指定spider_modules
+    spider_modules = ['crawlo.spider']  # 使用框架的spider模块进行测试
+    process = CrawlerProcess(settings=settings, spider_modules=spider_modules)
+    
+    # 检查爬虫是否已注册
+    spider_name = ValidationTestSpider.name
+    is_registered = process.is_spider_registered(spider_name)
+    print(f"爬虫 '{spider_name}' 是否已注册: {is_registered}")
+    
+    if is_registered:
+        print("爬虫自动导入功能正常")
+    else:
+        print("爬虫自动导入功能异常")
+
+
+async def main():
+    """主函数"""
+    print("开始最终验证测试...")
+    print("=" * 50)
+    
+    try:
+        # 1. 测试框架启动日志
+        await test_framework_startup_logging()
+        print()
+        
+        # 2. 测试队列阻塞行为
+        await test_queue_blocking_behavior()
+        print()
+        
+        # 3. 测试统计信息输出
+        await test_stats_output()
+        print()
+        
+        # 4. 测试爬虫自动导入
+        await test_spider_auto_import()
+        print()
+        
+        print("=" * 50)
+        print("所有验证测试通过！框架修改的功能工作正常。")
+        
+    except Exception as e:
+        print("=" * 50)
+        print(f"验证测试失败: {e}")
+        import traceback
+        traceback.print_exc()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())