crawlo 1.4.7__py3-none-any.whl → 1.4.8__py3-none-any.whl

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)

tests/test_item_dedup_redis_key.py

@@ -1,123 +1,123 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-数据项去重Redis Key测试脚本
-用于验证RedisDedupPipeline和示例项目中的Redis去重管道是否使用统一的Redis key命名规范
-"""
-import sys
-import os
-import traceback
-
-# 添加项目根目录到路径
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-
-from crawlo.pipelines.redis_dedup_pipeline import RedisDedupPipeline
-
-
-class MockSettings:
-    """模拟设置类"""
-    def __init__(self, project_name="test_project"):
-        self.project_name = project_name
-    
-    def get(self, key, default=None):
-        if key == 'PROJECT_NAME':
-            return self.project_name
-        elif key == 'REDIS_HOST':
-            return 'localhost'
-        elif key == 'REDIS_PORT':
-            return 6379
-        elif key == 'REDIS_DB':
-            return 2
-        elif key == 'REDIS_PASSWORD':
-            return None
-        elif key == 'LOG_LEVEL':
-            return 'INFO'
-        return default
-    
-    def getint(self, key, default=0):
-        if key == 'REDIS_PORT':
-            return 6379
-        elif key == 'REDIS_DB':
-            return 2
-        return default
-
-
-class MockCrawler:
-    """模拟爬虫类"""
-    def __init__(self, project_name="test_project"):
-        self.settings = MockSettings(project_name)
-
-
-async def test_item_dedup_redis_key():
-    """测试数据项去重Redis key命名规范"""
-    print("测试数据项去重Redis key命名规范...")
-    
-    try:
-        # 测试不同的项目名称
-        test_cases = [
-            {
-                "project_name": "books_distributed",
-                "expected_key": "crawlo:books_distributed:item:fingerprint",
-                "description": "书籍分布式项目"
-            },
-            {
-                "project_name": "api_data_collection",
-                "expected_key": "crawlo:api_data_collection:item:fingerprint",
-                "description": "API数据采集项目"
-            },
-            {
-                "project_name": "test_project",
-                "expected_key": "crawlo:test_project:item:fingerprint",
-                "description": "测试项目"
-            }
-        ]
-        
-        for i, test_case in enumerate(test_cases, 1):
-            print(f"   {i}. 测试 {test_case['description']}...")
-            
-            # 测试RedisDedupPipeline
-            mock_crawler = MockCrawler(test_case["project_name"])
-            pipeline = RedisDedupPipeline.from_crawler(mock_crawler)
-            
-            # 验证Redis key是否符合规范
-            assert pipeline.redis_key == test_case["expected_key"], \
-                f"Redis key不匹配: {pipeline.redis_key} != {test_case['expected_key']}"
-            
-            print(f"      Redis key: {pipeline.redis_key}")
-        
-        print("数据项去重Redis key命名规范测试通过！")
-        return True
-        
-    except Exception as e:
-        print(f"数据项去重Redis key命名规范测试失败: {e}")
-        traceback.print_exc()
-        return False
-
-
-def main():
-    """主测试函数"""
-    print("开始数据项去重Redis key命名规范测试...")
-    print("=" * 50)
-    
-    try:
-        success = test_item_dedup_redis_key()
-        
-        print("=" * 50)
-        if success:
-            print("所有测试通过！数据项去重使用统一的Redis key命名规范")
-        else:
-            print("测试失败，请检查实现")
-            return 1
-            
-    except Exception as e:
-        print("=" * 50)
-        print(f"测试过程中发生异常: {e}")
-        traceback.print_exc()
-        return 1
-    
-    return 0
-
-
-if __name__ == "__main__":
-    exit_code = main()
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+数据项去重Redis Key测试脚本
+用于验证RedisDedupPipeline和示例项目中的Redis去重管道是否使用统一的Redis key命名规范
+"""
+import sys
+import os
+import traceback
+
+# 添加项目根目录到路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.pipelines.redis_dedup_pipeline import RedisDedupPipeline
+
+
+class MockSettings:
+    """模拟设置类"""
+    def __init__(self, project_name="test_project"):
+        self.project_name = project_name
+    
+    def get(self, key, default=None):
+        if key == 'PROJECT_NAME':
+            return self.project_name
+        elif key == 'REDIS_HOST':
+            return 'localhost'
+        elif key == 'REDIS_PORT':
+            return 6379
+        elif key == 'REDIS_DB':
+            return 2
+        elif key == 'REDIS_PASSWORD':
+            return None
+        elif key == 'LOG_LEVEL':
+            return 'INFO'
+        return default
+    
+    def getint(self, key, default=0):
+        if key == 'REDIS_PORT':
+            return 6379
+        elif key == 'REDIS_DB':
+            return 2
+        return default
+
+
+class MockCrawler:
+    """模拟爬虫类"""
+    def __init__(self, project_name="test_project"):
+        self.settings = MockSettings(project_name)
+
+
+async def test_item_dedup_redis_key():
+    """测试数据项去重Redis key命名规范"""
+    print("测试数据项去重Redis key命名规范...")
+    
+    try:
+        # 测试不同的项目名称
+        test_cases = [
+            {
+                "project_name": "books_distributed",
+                "expected_key": "crawlo:books_distributed:item:fingerprint",
+                "description": "书籍分布式项目"
+            },
+            {
+                "project_name": "api_data_collection",
+                "expected_key": "crawlo:api_data_collection:item:fingerprint",
+                "description": "API数据采集项目"
+            },
+            {
+                "project_name": "test_project",
+                "expected_key": "crawlo:test_project:item:fingerprint",
+                "description": "测试项目"
+            }
+        ]
+        
+        for i, test_case in enumerate(test_cases, 1):
+            print(f"   {i}. 测试 {test_case['description']}...")
+            
+            # 测试RedisDedupPipeline
+            mock_crawler = MockCrawler(test_case["project_name"])
+            pipeline = RedisDedupPipeline.from_crawler(mock_crawler)
+            
+            # 验证Redis key是否符合规范
+            assert pipeline.redis_key == test_case["expected_key"], \
+                f"Redis key不匹配: {pipeline.redis_key} != {test_case['expected_key']}"
+            
+            print(f"      Redis key: {pipeline.redis_key}")
+        
+        print("数据项去重Redis key命名规范测试通过！")
+        return True
+        
+    except Exception as e:
+        print(f"数据项去重Redis key命名规范测试失败: {e}")
+        traceback.print_exc()
+        return False
+
+
+def main():
+    """主测试函数"""
+    print("开始数据项去重Redis key命名规范测试...")
+    print("=" * 50)
+    
+    try:
+        success = test_item_dedup_redis_key()
+        
+        print("=" * 50)
+        if success:
+            print("所有测试通过！数据项去重使用统一的Redis key命名规范")
+        else:
+            print("测试失败，请检查实现")
+            return 1
+            
+    except Exception as e:
+        print("=" * 50)
+        print(f"测试过程中发生异常: {e}")
+        traceback.print_exc()
+        return 1
+    
+    return 0
+
+
+if __name__ == "__main__":
+    exit_code = main()
     sys.exit(exit_code)