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

tests/spider_log_timing_test.py

@@ -0,0 +1,178 @@
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+"""
+模拟爬虫场景测试日志文件生成时机
+"""
+
+import os
+import sys
+import time
+import asyncio
+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.logging import configure_logging as configure, get_logger
+
+
+class MockSpider:
+    """模拟爬虫类"""
+    
+    def __init__(self, name):
+        self.name = name
+        self.logger = get_logger(f'spider.{name}')
+    
+    async def start_requests(self):
+        """开始请求"""
+        self.logger.info(f"Spider {self.name} 开始请求")
+        # 模拟一些网络请求
+        for i in range(3):
+            self.logger.info(f"Spider {self.name} 发送请求 {i+1}")
+            await asyncio.sleep(0.1)
+    
+    async def parse(self, response):
+        """解析响应"""
+        self.logger.info(f"Spider {self.name} 解析响应")
+        # 模拟解析过程
+        await asyncio.sleep(0.05)
+        self.logger.info(f"Spider {self.name} 提取数据")
+        return {"data": f"item from {self.name}"}
+    
+    async def crawl(self):
+        """执行爬取"""
+        self.logger.info(f"Spider {self.name} 开始爬取")
+        await self.start_requests()
+        await self.parse("mock_response")
+        self.logger.info(f"Spider {self.name} 爬取完成")
+
+
+async def test_spider_logging_timing():
+    """测试爬虫日志记录时机"""
+    print("=== 测试爬虫日志记录时机 ===")
+    
+    # 设置日志文件路径
+    log_file = "logs/spider_timing_test.log"
+    
+    # 删除可能存在的旧日志文件
+    if os.path.exists(log_file):
+        os.remove(log_file)
+    
+    # 配置日志系统
+    print("1. 配置日志系统...")
+    configure(
+        level='INFO',
+        file_path=log_file,
+        console_enabled=True,
+        file_enabled=True
+    )
+    
+    print(f"   配置后日志文件是否存在: {os.path.exists(log_file)}")
+    
+    # 创建爬虫实例
+    print("\n2. 创建爬虫实例...")
+    spider = MockSpider("test_spider")
+    print(f"   创建爬虫后日志文件是否存在: {os.path.exists(log_file)}")
+    
+    # 检查文件内容
+    if os.path.exists(log_file):
+        with open(log_file, 'r', encoding='utf-8') as f:
+            content = f.read()
+            print(f"   日志文件行数: {len(content.splitlines())}")
+    
+    # 执行爬取
+    print("\n3. 执行爬取...")
+    await spider.crawl()
+    
+    print(f"   爬取完成后日志文件是否存在: {os.path.exists(log_file)}")
+    
+    # 检查最终文件内容
+    if os.path.exists(log_file):
+        with open(log_file, 'r', encoding='utf-8') as f:
+            lines = f.readlines()
+            print(f"\n最终日志文件内容:")
+            print(f"  总行数: {len(lines)}")
+            print(f"  文件大小: {os.path.getsize(log_file)} 字节")
+            if lines:
+                print(f"  第一行: {lines[0].strip()}")
+                print(f"  最后一行: {lines[-1].strip()}")
+    
+    # 等待一段时间后再次检查
+    print("\n4. 等待2秒后再次检查...")
+    time.sleep(2)
+    
+    if os.path.exists(log_file):
+        with open(log_file, 'r', encoding='utf-8') as f:
+            lines = f.readlines()
+            print(f"  等待后总行数: {len(lines)}")
+
+
+async def test_multiple_spiders():
+    """测试多个爬虫的日志记录"""
+    print("\n=== 测试多个爬虫的日志记录 ===")
+    
+    # 设置日志文件路径
+    log_file = "logs/multi_spider_test.log"
+    
+    # 删除可能存在的旧日志文件
+    if os.path.exists(log_file):
+        os.remove(log_file)
+    
+    # 配置日志系统
+    configure(
+        level='INFO',
+        file_path=log_file,
+        console_enabled=True,
+        file_enabled=True
+    )
+    
+    # 创建多个爬虫实例
+    spiders = [MockSpider(f"spider_{i}") for i in range(3)]
+    
+    print("1. 顺序执行多个爬虫...")
+    for i, spider in enumerate(spiders):
+        print(f"   执行爬虫 {i+1}...")
+        await spider.crawl()
+        
+        # 检查当前日志文件状态
+        if os.path.exists(log_file):
+            with open(log_file, 'r', encoding='utf-8') as f:
+                lines = f.readlines()
+                print(f"     当前日志行数: {len(lines)}")
+    
+    print(f"\n   所有爬虫执行完成后日志文件是否存在: {os.path.exists(log_file)}")
+    
+    # 检查最终文件内容
+    if os.path.exists(log_file):
+        with open(log_file, 'r', encoding='utf-8') as f:
+            lines = f.readlines()
+            print(f"\n最终日志文件内容:")
+            print(f"  总行数: {len(lines)}")
+            print(f"  文件大小: {os.path.getsize(log_file)} 字节")
+            if lines:
+                print(f"  第一行: {lines[0].strip()}")
+                print(f"  最后一行: {lines[-1].strip()}")
+
+
+async def main():
+    """主函数"""
+    print("开始测试爬虫日志记录时机...")
+    
+    try:
+        await test_spider_logging_timing()
+        await test_multiple_spiders()
+        
+        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__':
+    asyncio.run(main())

tests/test_advanced_tools.py

@@ -1,149 +1,149 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-高级工具测试
-"""
-import unittest
-from crawlo.tools import (
-    # 数据处理工具
-    clean_text,
-    format_currency,
-    validate_email,
-    validate_url,
-    check_data_integrity,
-    
-    # 重试机制
-    RetryMechanism,
-    should_retry,
-    exponential_backoff,
-    
-    # 反爬虫应对工具
-    AntiCrawler,
-    rotate_proxy,
-    handle_captcha,
-    detect_rate_limiting,
-    
-    # 分布式协调工具
-    generate_pagination_tasks,
-    distribute_tasks,
-    DistributedCoordinator,
-    TaskDistributor,
-    DeduplicationTool
-)
-
-
-class TestAdvancedTools(unittest.TestCase):
-    """高级工具测试类"""
-
-    def test_data_processing_tools(self):
-        """测试数据处理工具"""
-        # 测试数据清洗
-        dirty_text = "<p>这是一个&nbsp;<b>测试</b>&amp;文本</p>"
-        clean_result = clean_text(dirty_text)
-        self.assertEqual(clean_result, "这是一个 测试&文本")
-        
-        # 测试数据格式化
-        price = 1234.567
-        formatted_price = format_currency(price, "¥", 2)
-        self.assertEqual(formatted_price, "¥1,234.57")
-        
-        # 测试字段验证
-        self.assertTrue(validate_email("test@example.com"))
-        self.assertFalse(validate_email("invalid-email"))
-        
-        self.assertTrue(validate_url("https://example.com"))
-        self.assertFalse(validate_url("invalid-url"))
-        
-        # 测试数据完整性检查
-        data = {
-            "name": "张三",
-            "email": "test@example.com",
-            "phone": "13812345678"
-        }
-        required_fields = ["name", "email", "phone"]
-        integrity_result = check_data_integrity(data, required_fields)
-        self.assertTrue(integrity_result["is_valid"])
-
-    def test_retry_mechanism(self):
-        """测试重试机制"""
-        # 测试指数退避
-        delay = exponential_backoff(0)
-        self.assertGreater(delay, 0)
-        
-        # 测试是否应该重试
-        self.assertTrue(should_retry(status_code=500))
-        self.assertTrue(should_retry(exception=ConnectionError()))
-        self.assertFalse(should_retry(status_code=200))
-
-    def test_anti_crawler_tools(self):
-        """测试反爬虫应对工具"""
-        # 测试反爬虫工具
-        anti_crawler = AntiCrawler()
-        
-        # 测试随机User-Agent
-        user_agent = anti_crawler.get_random_user_agent()
-        self.assertIsInstance(user_agent, str)
-        self.assertGreater(len(user_agent), 0)
-        
-        # 测试代理轮换
-        proxy = anti_crawler.rotate_proxy()
-        self.assertIsInstance(proxy, dict)
-        
-        # 测试验证码检测
-        self.assertTrue(anti_crawler.handle_captcha("请输入验证码进行验证"))
-        self.assertFalse(anti_crawler.handle_captcha("正常页面内容"))
-        
-        # 测试频率限制检测
-        self.assertTrue(anti_crawler.detect_rate_limiting(429, {}))
-        self.assertFalse(anti_crawler.detect_rate_limiting(200, {}))
-
-    def test_distributed_coordinator_tools(self):
-        """测试分布式协调工具"""
-        # 测试任务分发器
-        distributor = TaskDistributor()
-        
-        # 测试分页任务生成
-        base_url = "https://example.com/products"
-        pagination_tasks = distributor.generate_pagination_tasks(base_url, 1, 5)
-        self.assertEqual(len(pagination_tasks), 5)
-        
-        # 测试任务分发
-        tasks = list(range(1, 21))  # 20个任务
-        distributed = distributor.distribute_tasks(tasks, 4)  # 分发给4个工作节点
-        self.assertEqual(len(distributed), 4)
-        self.assertEqual(sum(len(worker_tasks) for worker_tasks in distributed), 20)
-        
-        # 测试去重工具
-        dedup_tool = DeduplicationTool()
-        
-        # 测试数据指纹生成
-        fingerprint1 = dedup_tool.generate_fingerprint({"name": "test", "value": 123})
-        fingerprint2 = dedup_tool.generate_fingerprint({"name": "test", "value": 123})
-        self.assertEqual(fingerprint1, fingerprint2)
-        
-        # 测试去重功能
-        self.assertFalse(dedup_tool.is_duplicate({"name": "test", "value": 123}))
-        self.assertTrue(dedup_tool.add_to_dedup({"name": "test", "value": 123}))
-        self.assertTrue(dedup_tool.is_duplicate({"name": "test", "value": 123}))
-        self.assertFalse(dedup_tool.add_to_dedup({"name": "test", "value": 123}))
-        
-        # 测试分布式协调器
-        coordinator = DistributedCoordinator()
-        
-        # 测试任务ID生成
-        task_id = coordinator.generate_task_id("https://example.com", "test_spider")
-        self.assertIsInstance(task_id, str)
-        self.assertEqual(len(task_id), 32)  # MD5 hash长度
-        
-        # 测试分页任务生成
-        pagination_tasks = coordinator.generate_pagination_tasks("https://example.com/products", 1, 5)
-        self.assertEqual(len(pagination_tasks), 5)
-        
-        # 测试任务分发
-        tasks = list(range(1, 21))  # 20个任务
-        distributed = coordinator.distribute_tasks(tasks, 4)  # 分发给4个工作节点
-        self.assertEqual(len(distributed), 4)
-
-
-if __name__ == '__main__':
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+高级工具测试
+"""
+import unittest
+from crawlo.tools import (
+    # 数据处理工具
+    clean_text,
+    format_currency,
+    validate_email,
+    validate_url,
+    check_data_integrity,
+    
+    # 重试机制
+    RetryMechanism,
+    should_retry,
+    exponential_backoff,
+    
+    # 反爬虫应对工具
+    AntiCrawler,
+    rotate_proxy,
+    handle_captcha,
+    detect_rate_limiting,
+    
+    # 分布式协调工具
+    generate_pagination_tasks,
+    distribute_tasks,
+    DistributedCoordinator,
+    TaskDistributor,
+    DeduplicationTool
+)
+
+
+class TestAdvancedTools(unittest.TestCase):
+    """高级工具测试类"""
+
+    def test_data_processing_tools(self):
+        """测试数据处理工具"""
+        # 测试数据清洗
+        dirty_text = "<p>这是一个&nbsp;<b>测试</b>&amp;文本</p>"
+        clean_result = clean_text(dirty_text)
+        self.assertEqual(clean_result, "这是一个 测试&文本")
+        
+        # 测试数据格式化
+        price = 1234.567
+        formatted_price = format_currency(price, "¥", 2)
+        self.assertEqual(formatted_price, "¥1,234.57")
+        
+        # 测试字段验证
+        self.assertTrue(validate_email("test@example.com"))
+        self.assertFalse(validate_email("invalid-email"))
+        
+        self.assertTrue(validate_url("https://example.com"))
+        self.assertFalse(validate_url("invalid-url"))
+        
+        # 测试数据完整性检查
+        data = {
+            "name": "张三",
+            "email": "test@example.com",
+            "phone": "13812345678"
+        }
+        required_fields = ["name", "email", "phone"]
+        integrity_result = check_data_integrity(data, required_fields)
+        self.assertTrue(integrity_result["is_valid"])
+
+    def test_retry_mechanism(self):
+        """测试重试机制"""
+        # 测试指数退避
+        delay = exponential_backoff(0)
+        self.assertGreater(delay, 0)
+        
+        # 测试是否应该重试
+        self.assertTrue(should_retry(status_code=500))
+        self.assertTrue(should_retry(exception=ConnectionError()))
+        self.assertFalse(should_retry(status_code=200))
+
+    def test_anti_crawler_tools(self):
+        """测试反爬虫应对工具"""
+        # 测试反爬虫工具
+        anti_crawler = AntiCrawler()
+        
+        # 测试随机User-Agent
+        user_agent = anti_crawler.get_random_user_agent()
+        self.assertIsInstance(user_agent, str)
+        self.assertGreater(len(user_agent), 0)
+        
+        # 测试代理轮换
+        proxy = anti_crawler.rotate_proxy()
+        self.assertIsInstance(proxy, dict)
+        
+        # 测试验证码检测
+        self.assertTrue(anti_crawler.handle_captcha("请输入验证码进行验证"))
+        self.assertFalse(anti_crawler.handle_captcha("正常页面内容"))
+        
+        # 测试频率限制检测
+        self.assertTrue(anti_crawler.detect_rate_limiting(429, {}))
+        self.assertFalse(anti_crawler.detect_rate_limiting(200, {}))
+
+    def test_distributed_coordinator_tools(self):
+        """测试分布式协调工具"""
+        # 测试任务分发器
+        distributor = TaskDistributor()
+        
+        # 测试分页任务生成
+        base_url = "https://example.com/products"
+        pagination_tasks = distributor.generate_pagination_tasks(base_url, 1, 5)
+        self.assertEqual(len(pagination_tasks), 5)
+        
+        # 测试任务分发
+        tasks = list(range(1, 21))  # 20个任务
+        distributed = distributor.distribute_tasks(tasks, 4)  # 分发给4个工作节点
+        self.assertEqual(len(distributed), 4)
+        self.assertEqual(sum(len(worker_tasks) for worker_tasks in distributed), 20)
+        
+        # 测试去重工具
+        dedup_tool = DeduplicationTool()
+        
+        # 测试数据指纹生成
+        fingerprint1 = dedup_tool.generate_fingerprint({"name": "test", "value": 123})
+        fingerprint2 = dedup_tool.generate_fingerprint({"name": "test", "value": 123})
+        self.assertEqual(fingerprint1, fingerprint2)
+        
+        # 测试去重功能
+        self.assertFalse(dedup_tool.is_duplicate({"name": "test", "value": 123}))
+        self.assertTrue(dedup_tool.add_to_dedup({"name": "test", "value": 123}))
+        self.assertTrue(dedup_tool.is_duplicate({"name": "test", "value": 123}))
+        self.assertFalse(dedup_tool.add_to_dedup({"name": "test", "value": 123}))
+        
+        # 测试分布式协调器
+        coordinator = DistributedCoordinator()
+        
+        # 测试任务ID生成
+        task_id = coordinator.generate_task_id("https://example.com", "test_spider")
+        self.assertIsInstance(task_id, str)
+        self.assertEqual(len(task_id), 32)  # MD5 hash长度
+        
+        # 测试分页任务生成
+        pagination_tasks = coordinator.generate_pagination_tasks("https://example.com/products", 1, 5)
+        self.assertEqual(len(pagination_tasks), 5)
+        
+        # 测试任务分发
+        tasks = list(range(1, 21))  # 20个任务
+        distributed = coordinator.distribute_tasks(tasks, 4)  # 分发给4个工作节点
+        self.assertEqual(len(distributed), 4)
+
+
+if __name__ == '__main__':
     unittest.main()