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

tests/test_distributed.py

@@ -1,65 +1,65 @@
-#!/usr/bin/env python
-# -*- coding: UTF-8 -*-
-"""
-分布式采集测试脚本
-用于验证分布式采集功能是否正常工作
-"""
-
-import asyncio
-import sys
-import os
-import time
-
-# 添加项目根目录到 Python 路径
-project_root = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, project_root)
-
-# 切换到项目根目录
-os.chdir(project_root)
-
-from crawlo.crawler import CrawlerProcess
-from crawlo.utils.log import get_logger
-
-logger = get_logger(__name__)
-
-
-async def test_distributed_crawling():
-    """测试分布式采集功能"""
-    logger.info("开始测试分布式采集功能...")
-
-    # 创建爬虫进程并应用配置
-    try:
-        # 确保 spider 模块被正确导入
-        spider_modules = ['ofweek_distributed.spiders']
-        process = CrawlerProcess(spider_modules=spider_modules)
-        logger.info("爬虫进程初始化成功")
-
-        # 运行指定的爬虫，使用正确的爬虫名称
-        result = await process.crawl('of_week_distributed')
-        logger.info(f"爬虫运行完成，结果: {result}")
-
-    except Exception as e:
-        logger.error(f"运行失败: {e}")
-        import traceback
-        traceback.print_exc()
-        sys.exit(1)
-
-
-def main():
-    """主函数"""
-    start_time = time.time()
-    logger.info("开始分布式采集测试")
-
-    try:
-        asyncio.run(test_distributed_crawling())
-        end_time = time.time()
-        logger.info(f"分布式采集测试完成，耗时: {end_time - start_time:.2f} 秒")
-    except KeyboardInterrupt:
-        logger.info("用户中断测试")
-    except Exception as e:
-        logger.error(f"测试过程中发生错误: {e}")
-        sys.exit(1)
-
-
-if __name__ == '__main__':
-    main()
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+"""
+分布式采集测试脚本
+用于验证分布式采集功能是否正常工作
+"""
+
+import asyncio
+import sys
+import os
+import time
+
+# 添加项目根目录到 Python 路径
+project_root = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, project_root)
+
+# 切换到项目根目录
+os.chdir(project_root)
+
+from crawlo.crawler import CrawlerProcess
+from crawlo.utils.log import get_logger
+
+logger = get_logger(__name__)
+
+
+async def test_distributed_crawling():
+    """测试分布式采集功能"""
+    logger.info("开始测试分布式采集功能...")
+
+    # 创建爬虫进程并应用配置
+    try:
+        # 确保 spider 模块被正确导入
+        spider_modules = ['ofweek_distributed.spiders']
+        process = CrawlerProcess(spider_modules=spider_modules)
+        logger.info("爬虫进程初始化成功")
+
+        # 运行指定的爬虫，使用正确的爬虫名称
+        result = await process.crawl('of_week_distributed')
+        logger.info(f"爬虫运行完成，结果: {result}")
+
+    except Exception as e:
+        logger.error(f"运行失败: {e}")
+        import traceback
+        traceback.print_exc()
+        sys.exit(1)
+
+
+def main():
+    """主函数"""
+    start_time = time.time()
+    logger.info("开始分布式采集测试")
+
+    try:
+        asyncio.run(test_distributed_crawling())
+        end_time = time.time()
+        logger.info(f"分布式采集测试完成，耗时: {end_time - start_time:.2f} 秒")
+    except KeyboardInterrupt:
+        logger.info("用户中断测试")
+    except Exception as e:
+        logger.error(f"测试过程中发生错误: {e}")
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

tests/test_double_crawlo_fix.py

@@ -1,208 +1,208 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-双重 crawlo 前缀问题修复测试脚本
-用于验证 Redis 队列名称中双重 crawlo 前缀问题的修复
-"""
-import sys
-import os
-import asyncio
-import traceback
-
-# 添加项目根目录到路径
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-
-# 导入相关模块
-from crawlo.queue.queue_manager import QueueManager, QueueConfig, QueueType
-from crawlo.queue.redis_priority_queue import RedisPriorityQueue
-
-
-async def test_redis_queue_naming():
-    """测试 Redis 队列命名修复"""
-    print("开始测试 Redis 队列命名修复...")
-    print("=" * 50)
-    
-    test_cases = [
-        {
-            "name": "正常命名",
-            "queue_name": "crawlo:test_project:queue:requests",
-            "expected_module": "test_project",
-            "expected_queue": "crawlo:test_project:queue:requests",
-            "expected_processing": "crawlo:test_project:queue:processing",
-            "expected_failed": "crawlo:test_project:queue:failed"
-        },
-        {
-            "name": "双重 crawlo 前缀",
-            "queue_name": "crawlo:crawlo:queue:requests",
-            "expected_module": "crawlo",
-            "expected_queue": "crawlo:crawlo:queue:requests",
-            "expected_processing": "crawlo:crawlo:queue:processing",
-            "expected_failed": "crawlo:crawlo:queue:failed"
-        },
-        {
-            "name": "三重 crawlo 前缀",
-            "queue_name": "crawlo:crawlo:crawlo:queue:requests",
-            "expected_module": "crawlo",
-            "expected_queue": "crawlo:crawlo:queue:requests",
-            "expected_processing": "crawlo:crawlo:queue:processing",
-            "expected_failed": "crawlo:crawlo:queue:failed"
-        },
-        {
-            "name": "无 crawlo 前缀",
-            "queue_name": "test_project:queue:requests",
-            "expected_module": "test_project",
-            "expected_queue": "crawlo:test_project:queue:requests",
-            "expected_processing": "crawlo:test_project:queue:processing",
-            "expected_failed": "crawlo:test_project:queue:failed"
-        }
-    ]
-    
-    try:
-        for i, test_case in enumerate(test_cases, 1):
-            print(f"测试 {i}: {test_case['name']}")
-            print(f"  输入队列名称: {test_case['queue_name']}")
-            
-            # 测试 RedisPriorityQueue 直接初始化
-            try:
-                queue = RedisPriorityQueue(
-                    redis_url="redis://127.0.0.1:6379/15",
-                    queue_name=test_case['queue_name'],
-                    module_name=test_case['expected_module']
-                )
-                
-                print(f"  修复后队列名称: {queue.queue_name}")
-                print(f"  修复后处理队列: {queue.processing_queue}")
-                print(f"  修复后失败队列: {queue.failed_queue}")
-                
-                # 验证结果
-                assert queue.queue_name == test_case['expected_queue'], \
-                    f"队列名称不匹配: {queue.queue_name} != {test_case['expected_queue']}"
-                assert queue.processing_queue == test_case['expected_processing'], \
-                    f"处理队列名称不匹配: {queue.processing_queue} != {test_case['expected_processing']}"
-                assert queue.failed_queue == test_case['expected_failed'], \
-                    f"失败队列名称不匹配: {queue.failed_queue} != {test_case['expected_failed']}"
-                
-                print("  测试通过")
-            except Exception as e:
-                print(f"  测试失败: {e}")
-                traceback.print_exc()
-                return False
-            
-            print()
-        
-        print("Redis 队列命名修复测试通过！")
-        return True
-        
-    except Exception as e:
-        print(f"Redis 队列命名修复测试失败: {e}")
-        traceback.print_exc()
-        return False
-
-
-async def test_queue_manager_naming():
-    """测试队列管理器中的项目名称提取"""
-    print("开始测试队列管理器项目名称提取...")
-    print("=" * 50)
-    
-    test_cases = [
-        {
-            "name": "正常命名",
-            "queue_name": "crawlo:test_project:queue:requests",
-            "expected_module": "test_project"
-        },
-        {
-            "name": "双重 crawlo 前缀",
-            "queue_name": "crawlo:crawlo:queue:requests",
-            "expected_module": "crawlo"
-        },
-        {
-            "name": "三重 crawlo 前缀",
-            "queue_name": "crawlo:crawlo:crawlo:queue:requests",
-            "expected_module": "crawlo"
-        },
-        {
-            "name": "无 crawlo 前缀",
-            "queue_name": "test_project:queue:requests",
-            "expected_module": "test_project"
-        }
-    ]
-    
-    try:
-        for i, test_case in enumerate(test_cases, 1):
-            print(f"测试 {i}: {test_case['name']}")
-            print(f"  输入队列名称: {test_case['queue_name']}")
-            
-            # 测试队列管理器中的项目名称提取逻辑
-            if ':' in test_case['queue_name']:
-                parts = test_case['queue_name'].split(':')
-                if len(parts) >= 2:
-                    # 处理可能的双重 crawlo 前缀
-                    if parts[0] == "crawlo" and parts[1] == "crawlo":
-                        # 双重 crawlo 前缀，取第三个部分作为项目名称
-                        if len(parts) >= 3:
-                            project_name = parts[2]
-                        else:
-                            project_name = "default"
-                    elif parts[0] == "crawlo":
-                        # 正常的 crawlo 前缀，取第二个部分作为项目名称
-                        project_name = parts[1]
-                    else:
-                        # 没有 crawlo 前缀，使用第一个部分作为项目名称
-                        project_name = parts[0]
-                else:
-                    project_name = test_case['queue_name'] or "default"
-            else:
-                project_name = test_case['queue_name'] or "default"
-            
-            print(f"  提取的项目名称: {project_name}")
-            print(f"  期望的项目名称: {test_case['expected_module']}")
-            
-            # 验证结果
-            assert project_name == test_case['expected_module'], \
-                f"项目名称不匹配: {project_name} != {test_case['expected_module']}"
-            
-            print("  测试通过")
-            print()
-        
-        print("队列管理器项目名称提取测试通过！")
-        return True
-        
-    except Exception as e:
-        print(f"队列管理器项目名称提取测试失败: {e}")
-        traceback.print_exc()
-        return False
-
-
-async def main():
-    """主测试函数"""
-    print("开始双重 crawlo 前缀问题修复测试...")
-    print("=" * 50)
-    
-    try:
-        # 测试 Redis 队列命名修复
-        redis_test_success = await test_redis_queue_naming()
-        print()
-        
-        # 测试队列管理器项目名称提取
-        manager_test_success = await test_queue_manager_naming()
-        print()
-        
-        print("=" * 50)
-        if redis_test_success and manager_test_success:
-            print("所有测试通过！双重 crawlo 前缀问题已修复")
-        else:
-            print("部分测试失败，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 = asyncio.run(main())
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+双重 crawlo 前缀问题修复测试脚本
+用于验证 Redis 队列名称中双重 crawlo 前缀问题的修复
+"""
+import sys
+import os
+import asyncio
+import traceback
+
+# 添加项目根目录到路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+# 导入相关模块
+from crawlo.queue.queue_manager import QueueManager, QueueConfig, QueueType
+from crawlo.queue.redis_priority_queue import RedisPriorityQueue
+
+
+async def test_redis_queue_naming():
+    """测试 Redis 队列命名修复"""
+    print("开始测试 Redis 队列命名修复...")
+    print("=" * 50)
+    
+    test_cases = [
+        {
+            "name": "正常命名",
+            "queue_name": "crawlo:test_project:queue:requests",
+            "expected_module": "test_project",
+            "expected_queue": "crawlo:test_project:queue:requests",
+            "expected_processing": "crawlo:test_project:queue:processing",
+            "expected_failed": "crawlo:test_project:queue:failed"
+        },
+        {
+            "name": "双重 crawlo 前缀",
+            "queue_name": "crawlo:crawlo:queue:requests",
+            "expected_module": "crawlo",
+            "expected_queue": "crawlo:crawlo:queue:requests",
+            "expected_processing": "crawlo:crawlo:queue:processing",
+            "expected_failed": "crawlo:crawlo:queue:failed"
+        },
+        {
+            "name": "三重 crawlo 前缀",
+            "queue_name": "crawlo:crawlo:crawlo:queue:requests",
+            "expected_module": "crawlo",
+            "expected_queue": "crawlo:crawlo:queue:requests",
+            "expected_processing": "crawlo:crawlo:queue:processing",
+            "expected_failed": "crawlo:crawlo:queue:failed"
+        },
+        {
+            "name": "无 crawlo 前缀",
+            "queue_name": "test_project:queue:requests",
+            "expected_module": "test_project",
+            "expected_queue": "crawlo:test_project:queue:requests",
+            "expected_processing": "crawlo:test_project:queue:processing",
+            "expected_failed": "crawlo:test_project:queue:failed"
+        }
+    ]
+    
+    try:
+        for i, test_case in enumerate(test_cases, 1):
+            print(f"测试 {i}: {test_case['name']}")
+            print(f"  输入队列名称: {test_case['queue_name']}")
+            
+            # 测试 RedisPriorityQueue 直接初始化
+            try:
+                queue = RedisPriorityQueue(
+                    redis_url="redis://127.0.0.1:6379/15",
+                    queue_name=test_case['queue_name'],
+                    module_name=test_case['expected_module']
+                )
+                
+                print(f"  修复后队列名称: {queue.queue_name}")
+                print(f"  修复后处理队列: {queue.processing_queue}")
+                print(f"  修复后失败队列: {queue.failed_queue}")
+                
+                # 验证结果
+                assert queue.queue_name == test_case['expected_queue'], \
+                    f"队列名称不匹配: {queue.queue_name} != {test_case['expected_queue']}"
+                assert queue.processing_queue == test_case['expected_processing'], \
+                    f"处理队列名称不匹配: {queue.processing_queue} != {test_case['expected_processing']}"
+                assert queue.failed_queue == test_case['expected_failed'], \
+                    f"失败队列名称不匹配: {queue.failed_queue} != {test_case['expected_failed']}"
+                
+                print("  测试通过")
+            except Exception as e:
+                print(f"  测试失败: {e}")
+                traceback.print_exc()
+                return False
+            
+            print()
+        
+        print("Redis 队列命名修复测试通过！")
+        return True
+        
+    except Exception as e:
+        print(f"Redis 队列命名修复测试失败: {e}")
+        traceback.print_exc()
+        return False
+
+
+async def test_queue_manager_naming():
+    """测试队列管理器中的项目名称提取"""
+    print("开始测试队列管理器项目名称提取...")
+    print("=" * 50)
+    
+    test_cases = [
+        {
+            "name": "正常命名",
+            "queue_name": "crawlo:test_project:queue:requests",
+            "expected_module": "test_project"
+        },
+        {
+            "name": "双重 crawlo 前缀",
+            "queue_name": "crawlo:crawlo:queue:requests",
+            "expected_module": "crawlo"
+        },
+        {
+            "name": "三重 crawlo 前缀",
+            "queue_name": "crawlo:crawlo:crawlo:queue:requests",
+            "expected_module": "crawlo"
+        },
+        {
+            "name": "无 crawlo 前缀",
+            "queue_name": "test_project:queue:requests",
+            "expected_module": "test_project"
+        }
+    ]
+    
+    try:
+        for i, test_case in enumerate(test_cases, 1):
+            print(f"测试 {i}: {test_case['name']}")
+            print(f"  输入队列名称: {test_case['queue_name']}")
+            
+            # 测试队列管理器中的项目名称提取逻辑
+            if ':' in test_case['queue_name']:
+                parts = test_case['queue_name'].split(':')
+                if len(parts) >= 2:
+                    # 处理可能的双重 crawlo 前缀
+                    if parts[0] == "crawlo" and parts[1] == "crawlo":
+                        # 双重 crawlo 前缀，取第三个部分作为项目名称
+                        if len(parts) >= 3:
+                            project_name = parts[2]
+                        else:
+                            project_name = "default"
+                    elif parts[0] == "crawlo":
+                        # 正常的 crawlo 前缀，取第二个部分作为项目名称
+                        project_name = parts[1]
+                    else:
+                        # 没有 crawlo 前缀，使用第一个部分作为项目名称
+                        project_name = parts[0]
+                else:
+                    project_name = test_case['queue_name'] or "default"
+            else:
+                project_name = test_case['queue_name'] or "default"
+            
+            print(f"  提取的项目名称: {project_name}")
+            print(f"  期望的项目名称: {test_case['expected_module']}")
+            
+            # 验证结果
+            assert project_name == test_case['expected_module'], \
+                f"项目名称不匹配: {project_name} != {test_case['expected_module']}"
+            
+            print("  测试通过")
+            print()
+        
+        print("队列管理器项目名称提取测试通过！")
+        return True
+        
+    except Exception as e:
+        print(f"队列管理器项目名称提取测试失败: {e}")
+        traceback.print_exc()
+        return False
+
+
+async def main():
+    """主测试函数"""
+    print("开始双重 crawlo 前缀问题修复测试...")
+    print("=" * 50)
+    
+    try:
+        # 测试 Redis 队列命名修复
+        redis_test_success = await test_redis_queue_naming()
+        print()
+        
+        # 测试队列管理器项目名称提取
+        manager_test_success = await test_queue_manager_naming()
+        print()
+        
+        print("=" * 50)
+        if redis_test_success and manager_test_success:
+            print("所有测试通过！双重 crawlo 前缀问题已修复")
+        else:
+            print("部分测试失败，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 = asyncio.run(main())
     sys.exit(exit_code)