crawlo 1.3.6__py3-none-any.whl → 1.3.7__py3-none-any.whl

tests/test_framework_startup.py

@@ -1,65 +1,65 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""
-测试框架启动信息是否正确输出到日志文件
-"""
-import sys
-import os
-sys.path.insert(0, '/')
-
-def test_framework_startup():
-    print("=== 测试框架启动信息输出 ===")
-    
-    # 删除旧的日志文件
-    test_log_file = '/Users/oscar/projects/Crawlo/test_startup.log'
-    if os.path.exists(test_log_file):
-        os.remove(test_log_file)
-    
-    # 准备测试设置
-    test_settings = {
-        'PROJECT_NAME': 'test_startup',
-        'LOG_LEVEL': 'INFO',
-        'LOG_FILE': test_log_file,
-        'RUN_MODE': 'standalone'
-    }
-    
-    # 初始化框架
-    from crawlo.core.framework_initializer import initialize_framework
-    settings = initialize_framework(test_settings)
-    
-    print(f"设置初始化完成: {settings.get('PROJECT_NAME')}")
-    
-    # 检查日志文件是否包含框架启动信息
-    if os.path.exists(test_log_file):
-        with open(test_log_file, 'r', encoding='utf-8') as f:
-            content = f.read()
-            print(f"日志文件内容长度: {len(content)} 字符")
-            
-            # 检查关键的框架启动信息
-            if "Crawlo框架初始化完成" in content:
-                print("✅ 发现: Crawlo框架初始化完成")
-            else:
-                print("❌ 未找到: Crawlo框架初始化完成")
-                
-            if "Crawlo Framework Started" in content:
-                print("✅ 发现: Crawlo Framework Started")
-            else:
-                print("❌ 未找到: Crawlo Framework Started")
-                
-            if "使用单机模式" in content:
-                print("✅ 发现: 使用单机模式")
-            else:
-                print("❌ 未找到: 使用单机模式")
-                
-            print("\n前50行日志内容:")
-            lines = content.split('\n')[:50]
-            for i, line in enumerate(lines, 1):
-                if any(keyword in line for keyword in ["框架", "Framework", "Started"]):
-                    print(f"{i:3d}: {line}")
-    else:
-        print("❌ 日志文件未创建")
-    
-    print("=== 测试完成 ===")
-
-if __name__ == "__main__":
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+测试框架启动信息是否正确输出到日志文件
+"""
+import sys
+import os
+sys.path.insert(0, '/')
+
+def test_framework_startup():
+    print("=== 测试框架启动信息输出 ===")
+    
+    # 删除旧的日志文件
+    test_log_file = '/Users/oscar/projects/Crawlo/test_startup.log'
+    if os.path.exists(test_log_file):
+        os.remove(test_log_file)
+    
+    # 准备测试设置
+    test_settings = {
+        'PROJECT_NAME': 'test_startup',
+        'LOG_LEVEL': 'INFO',
+        'LOG_FILE': test_log_file,
+        'RUN_MODE': 'standalone'
+    }
+    
+    # 初始化框架
+    from crawlo.core.framework_initializer import initialize_framework
+    settings = initialize_framework(test_settings)
+    
+    print(f"设置初始化完成: {settings.get('PROJECT_NAME')}")
+    
+    # 检查日志文件是否包含框架启动信息
+    if os.path.exists(test_log_file):
+        with open(test_log_file, 'r', encoding='utf-8') as f:
+            content = f.read()
+            print(f"日志文件内容长度: {len(content)} 字符")
+            
+            # 检查关键的框架启动信息
+            if "Crawlo框架初始化完成" in content:
+                print("✅ 发现: Crawlo框架初始化完成")
+            else:
+                print("❌ 未找到: Crawlo框架初始化完成")
+                
+            if "Crawlo Framework Started" in content:
+                print("✅ 发现: Crawlo Framework Started")
+            else:
+                print("❌ 未找到: Crawlo Framework Started")
+                
+            if "使用单机模式" in content:
+                print("✅ 发现: 使用单机模式")
+            else:
+                print("❌ 未找到: 使用单机模式")
+                
+            print("\n前50行日志内容:")
+            lines = content.split('\n')[:50]
+            for i, line in enumerate(lines, 1):
+                if any(keyword in line for keyword in ["框架", "Framework", "Started"]):
+                    print(f"{i:3d}: {line}")
+    else:
+        print("❌ 日志文件未创建")
+    
+    print("=== 测试完成 ===")
+
+if __name__ == "__main__":
     test_framework_startup()

tests/test_get_component_logger.py

@@ -1,84 +1,84 @@
-#!/usr/bin/env python
-# -*- coding: UTF-8 -*-
-"""
-测试增强后的 get_component_logger 函数
-"""
-
-import os
-import sys
-from pathlib import Path
-
-# 添加项目根目录到Python路径
-project_root = Path(__file__).parent.parent
-sys.path.insert(0, str(project_root))
-
-from crawlo.utils.log import get_component_logger
-
-
-class MockComponent:
-    """模拟组件类"""
-    pass
-
-
-class MockSettings:
-    """模拟设置类"""
-    def __init__(self):
-        self.LOG_LEVEL = 'DEBUG'
-        self.LOG_LEVEL_MockComponent = 'WARNING'
-    
-    def get(self, key, default=None):
-        return getattr(self, key, default)
-
-
-def test_get_component_logger():
-    """测试 get_component_logger 函数"""
-    print("=== 测试 get_component_logger 函数 ===")
-    
-    # 1. 测试基本用法
-    print("1. 测试基本用法...")
-    logger1 = get_component_logger(MockComponent)
-    print(f"   Logger名称: {logger1.name}")
-    print(f"   Logger级别: {logger1.level}")
-    
-    # 2. 测试带settings的用法
-    print("2. 测试带settings的用法...")
-    settings = MockSettings()
-    logger2 = get_component_logger(MockComponent, settings)
-    print(f"   Logger名称: {logger2.name}")
-    print(f"   Logger级别: {logger2.level}")
-    
-    # 3. 测试带level参数的用法
-    print("3. 测试带level参数的用法...")
-    logger3 = get_component_logger(MockComponent, level='ERROR')
-    print(f"   Logger名称: {logger3.name}")
-    print(f"   Logger级别: {logger3.level}")
-    
-    # 4. 测试日志输出
-    print("4. 测试日志输出...")
-    logger1.info("这是info级别的测试消息")
-    logger1.warning("这是warning级别的测试消息")
-    logger1.error("这是error级别的测试消息")
-    
-    print("\n=== 测试完成 ===")
-
-
-def main():
-    """主函数"""
-    print("开始测试增强后的 get_component_logger 函数...")
-    
-    try:
-        test_get_component_logger()
-        
-        print("\n=== 所有测试完成 ===")
-        
-    except Exception as e:
-        print(f"\n测试过程中出现错误: {e}")
-        import traceback
-        traceback.print_exc()
-        return 1
-    
-    return 0
-
-
-if __name__ == '__main__':
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+"""
+测试增强后的 get_component_logger 函数
+"""
+
+import os
+import sys
+from pathlib import Path
+
+# 添加项目根目录到Python路径
+project_root = Path(__file__).parent.parent
+sys.path.insert(0, str(project_root))
+
+from crawlo.utils.log import get_component_logger
+
+
+class MockComponent:
+    """模拟组件类"""
+    pass
+
+
+class MockSettings:
+    """模拟设置类"""
+    def __init__(self):
+        self.LOG_LEVEL = 'DEBUG'
+        self.LOG_LEVEL_MockComponent = 'WARNING'
+    
+    def get(self, key, default=None):
+        return getattr(self, key, default)
+
+
+def test_get_component_logger():
+    """测试 get_component_logger 函数"""
+    print("=== 测试 get_component_logger 函数 ===")
+    
+    # 1. 测试基本用法
+    print("1. 测试基本用法...")
+    logger1 = get_component_logger(MockComponent)
+    print(f"   Logger名称: {logger1.name}")
+    print(f"   Logger级别: {logger1.level}")
+    
+    # 2. 测试带settings的用法
+    print("2. 测试带settings的用法...")
+    settings = MockSettings()
+    logger2 = get_component_logger(MockComponent, settings)
+    print(f"   Logger名称: {logger2.name}")
+    print(f"   Logger级别: {logger2.level}")
+    
+    # 3. 测试带level参数的用法
+    print("3. 测试带level参数的用法...")
+    logger3 = get_component_logger(MockComponent, level='ERROR')
+    print(f"   Logger名称: {logger3.name}")
+    print(f"   Logger级别: {logger3.level}")
+    
+    # 4. 测试日志输出
+    print("4. 测试日志输出...")
+    logger1.info("这是info级别的测试消息")
+    logger1.warning("这是warning级别的测试消息")
+    logger1.error("这是error级别的测试消息")
+    
+    print("\n=== 测试完成 ===")
+
+
+def main():
+    """主函数"""
+    print("开始测试增强后的 get_component_logger 函数...")
+    
+    try:
+        test_get_component_logger()
+        
+        print("\n=== 所有测试完成 ===")
+        
+    except Exception as e:
+        print(f"\n测试过程中出现错误: {e}")
+        import traceback
+        traceback.print_exc()
+        return 1
+    
+    return 0
+
+
+if __name__ == '__main__':
     sys.exit(main())

tests/test_integration.py

@@ -1,169 +1,169 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-集成测试
-测试 Crawlo 框架的核心功能集成
-"""
-
-import asyncio
-import sys
-import os
-from unittest.mock import Mock, AsyncMock
-
-# 添加项目根目录到路径
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-
-from crawlo.config import CrawloConfig
-from crawlo.crawler import CrawlerProcess
-from crawlo import Spider, Request, Item
-from crawlo.extension.memory_monitor import MemoryMonitorExtension
-
-
-class MockItem(Item):
-    """模拟数据项"""
-    title = ''
-    url = ''
-
-
-class MockSpider(Spider):
-    """模拟爬虫"""
-    name = 'mock_spider'
-    
-    async def start_requests(self):
-        """发起模拟请求"""
-        yield Request('https://httpbin.org/get', callback=self.parse)
-    
-    async def parse(self, response):
-        """解析响应"""
-        item = MockItem(
-            title='Test Item',
-            url=response.url
-        )
-        yield item
-
-
-class MockSettings:
-    """模拟设置"""
-    def get(self, key, default=None):
-        config = {
-            'PROJECT_NAME': 'integration_test',
-            'LOG_LEVEL': 'WARNING',  # 减少日志输出
-            'REDIS_URL': 'redis://127.0.0.1:6379/15',
-            'REDIS_HOST': '127.0.0.1',
-            'REDIS_PORT': 6379,
-            'REDIS_DB': 15,
-            'FILTER_CLASS': 'crawlo.filters.aioredis_filter.AioRedisFilter',
-            'CUSTOM_PIPELINES': ['crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline'],
-            'CUSTOM_EXTENSIONS': [
-                'crawlo.extension.memory_monitor.MemoryMonitorExtension',
-            ],
-            'MEMORY_MONITOR_ENABLED': True,
-            'MEMORY_MONITOR_INTERVAL': 1,
-            'MEMORY_WARNING_THRESHOLD': 95.0,
-            'MEMORY_CRITICAL_THRESHOLD': 98.0,
-            'CONCURRENT_REQUESTS': 5,
-            'DOWNLOAD_DELAY': 0.1,
-        }
-        return config.get(key, default)
-    
-    def get_int(self, key, default=0):
-        value = self.get(key, default)
-        return int(value) if value is not None else default
-        
-    def get_float(self, key, default=0.0):
-        value = self.get(key, default)
-        return float(value) if value is not None else default
-        
-    def get_bool(self, key, default=False):
-        value = self.get(key, default)
-        if isinstance(value, bool):
-            return value
-        if isinstance(value, str):
-            return value.lower() in ('true', '1', 'yes')
-        return bool(value)
-        
-    def get_list(self, key, default=None):
-        value = self.get(key, default or [])
-        if isinstance(value, str):
-            return [v.strip() for v in value.split(',') if v.strip()]
-        return list(value)
-
-
-async def test_crawler_integration():
-    """测试爬虫集成"""
-    print("🔍 测试爬虫集成...")
-    
-    # 创建配置
-    config = CrawloConfig.standalone(
-        concurrency=2,
-        download_delay=0.1,
-        LOG_LEVEL='WARNING'
-    )
-    
-    # 添加自定义管道和扩展
-    config.set('CUSTOM_PIPELINES', [
-        'crawlo.pipelines.console_pipeline.ConsolePipeline',
-    ])
-    
-    config.set('CUSTOM_EXTENSIONS', [
-        'crawlo.extension.memory_monitor.MemoryMonitorExtension',
-    ])
-    
-    # 创建爬虫进程
-    process = CrawlerProcess(settings=config.to_dict())
-    
-    # 添加爬虫
-    process.crawl(MockSpider)
-    
-    # 运行测试
-    await process.start()
-    
-    print("   爬虫集成测试完成")
-
-
-async def test_extension_integration():
-    """测试扩展集成"""
-    print("🔍 测试扩展集成...")
-    
-    # 创建模拟爬虫
-    mock_crawler = Mock()
-    mock_crawler.settings = MockSettings()
-    mock_crawler.subscriber = Mock()
-    mock_crawler.subscriber.subscribe = Mock()
-    
-    try:
-        # 尝试创建内存监控扩展实例
-        extension = MemoryMonitorExtension.create_instance(mock_crawler)
-        print("   扩展集成测试完成")
-    except Exception as e:
-        if "NotConfigured" in str(type(e)):
-            print("   扩展未启用（正常情况）")
-        else:
-            raise e
-
-
-async def main():
-    """主测试函数"""
-    print("开始Crawlo框架集成测试...")
-    print("=" * 50)
-    
-    try:
-        await test_crawler_integration()
-        await test_extension_integration()
-        
-        print("=" * 50)
-        print("所有集成测试通过！")
-        
-    except Exception as e:
-        print("=" * 50)
-        print(f"测试失败: {e}")
-        import traceback
-        traceback.print_exc()
-        return 1
-    
-    return 0
-
-
-if __name__ == "__main__":
-    exit_code = asyncio.run(main())
-    sys.exit(exit_code)
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+集成测试
+测试 Crawlo 框架的核心功能集成
+"""
+
+import asyncio
+import sys
+import os
+from unittest.mock import Mock, AsyncMock
+
+# 添加项目根目录到路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.config import CrawloConfig
+from crawlo.crawler import CrawlerProcess
+from crawlo import Spider, Request, Item
+from crawlo.extension.memory_monitor import MemoryMonitorExtension
+
+
+class MockItem(Item):
+    """模拟数据项"""
+    title = ''
+    url = ''
+
+
+class MockSpider(Spider):
+    """模拟爬虫"""
+    name = 'mock_spider'
+    
+    async def start_requests(self):
+        """发起模拟请求"""
+        yield Request('https://httpbin.org/get', callback=self.parse)
+    
+    async def parse(self, response):
+        """解析响应"""
+        item = MockItem(
+            title='Test Item',
+            url=response.url
+        )
+        yield item
+
+
+class MockSettings:
+    """模拟设置"""
+    def get(self, key, default=None):
+        config = {
+            'PROJECT_NAME': 'integration_test',
+            'LOG_LEVEL': 'WARNING',  # 减少日志输出
+            'REDIS_URL': 'redis://127.0.0.1:6379/15',
+            'REDIS_HOST': '127.0.0.1',
+            'REDIS_PORT': 6379,
+            'REDIS_DB': 15,
+            'FILTER_CLASS': 'crawlo.filters.aioredis_filter.AioRedisFilter',
+            'CUSTOM_PIPELINES': ['crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline'],
+            'CUSTOM_EXTENSIONS': [
+                'crawlo.extension.memory_monitor.MemoryMonitorExtension',
+            ],
+            'MEMORY_MONITOR_ENABLED': True,
+            'MEMORY_MONITOR_INTERVAL': 1,
+            'MEMORY_WARNING_THRESHOLD': 95.0,
+            'MEMORY_CRITICAL_THRESHOLD': 98.0,
+            'CONCURRENT_REQUESTS': 5,
+            'DOWNLOAD_DELAY': 0.1,
+        }
+        return config.get(key, default)
+    
+    def get_int(self, key, default=0):
+        value = self.get(key, default)
+        return int(value) if value is not None else default
+        
+    def get_float(self, key, default=0.0):
+        value = self.get(key, default)
+        return float(value) if value is not None else default
+        
+    def get_bool(self, key, default=False):
+        value = self.get(key, default)
+        if isinstance(value, bool):
+            return value
+        if isinstance(value, str):
+            return value.lower() in ('true', '1', 'yes')
+        return bool(value)
+        
+    def get_list(self, key, default=None):
+        value = self.get(key, default or [])
+        if isinstance(value, str):
+            return [v.strip() for v in value.split(',') if v.strip()]
+        return list(value)
+
+
+async def test_crawler_integration():
+    """测试爬虫集成"""
+    print("🔍 测试爬虫集成...")
+    
+    # 创建配置
+    config = CrawloConfig.standalone(
+        concurrency=2,
+        download_delay=0.1,
+        LOG_LEVEL='WARNING'
+    )
+    
+    # 添加自定义管道和扩展
+    config.set('CUSTOM_PIPELINES', [
+        'crawlo.pipelines.console_pipeline.ConsolePipeline',
+    ])
+    
+    config.set('CUSTOM_EXTENSIONS', [
+        'crawlo.extension.memory_monitor.MemoryMonitorExtension',
+    ])
+    
+    # 创建爬虫进程
+    process = CrawlerProcess(settings=config.to_dict())
+    
+    # 添加爬虫
+    process.crawl(MockSpider)
+    
+    # 运行测试
+    await process.start()
+    
+    print("   爬虫集成测试完成")
+
+
+async def test_extension_integration():
+    """测试扩展集成"""
+    print("🔍 测试扩展集成...")
+    
+    # 创建模拟爬虫
+    mock_crawler = Mock()
+    mock_crawler.settings = MockSettings()
+    mock_crawler.subscriber = Mock()
+    mock_crawler.subscriber.subscribe = Mock()
+    
+    try:
+        # 尝试创建内存监控扩展实例
+        extension = MemoryMonitorExtension.create_instance(mock_crawler)
+        print("   扩展集成测试完成")
+    except Exception as e:
+        if "NotConfigured" in str(type(e)):
+            print("   扩展未启用（正常情况）")
+        else:
+            raise e
+
+
+async def main():
+    """主测试函数"""
+    print("开始Crawlo框架集成测试...")
+    print("=" * 50)
+    
+    try:
+        await test_crawler_integration()
+        await test_extension_integration()
+        
+        print("=" * 50)
+        print("所有集成测试通过！")
+        
+    except Exception as e:
+        print("=" * 50)
+        print(f"测试失败: {e}")
+        import traceback
+        traceback.print_exc()
+        return 1
+    
+    return 0
+
+
+if __name__ == "__main__":
+    exit_code = asyncio.run(main())
+    sys.exit(exit_code)