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

tests/test_performance_monitor.py

@@ -0,0 +1,116 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+性能监控工具测试
+测试 PerformanceMonitor, PerformanceTimer, performance_monitor_decorator
+"""
+import sys
+import os
+import unittest
+from unittest.mock import Mock, patch, MagicMock
+import asyncio
+
+# 添加项目根目录到 Python 路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+# 尝试导入性能监控工具
+try:
+    from crawlo.utils.performance_monitor import PerformanceMonitor, PerformanceTimer, performance_monitor_decorator
+    PSUTIL_AVAILABLE = True
+except ImportError:
+    PSUTIL_AVAILABLE = False
+    PerformanceMonitor = None
+    PerformanceTimer = None
+    performance_monitor_decorator = None
+
+
+class TestPerformanceTimer(unittest.TestCase):
+    """性能计时器测试"""
+
+    @unittest.skipIf(not PSUTIL_AVAILABLE, "psutil not available")
+    def setUp(self):
+        """测试前准备"""
+        self.timer = PerformanceTimer("test_timer")
+        
+    @unittest.skipIf(not PSUTIL_AVAILABLE, "psutil not available")
+    def test_timer_initialization(self):
+        """测试计时器初始化"""
+        self.assertEqual(self.timer.name, "test_timer")
+        self.assertIsNone(self.timer.start_time)
+        self.assertIsNone(self.timer.end_time)
+        
+    @unittest.skipIf(not PSUTIL_AVAILABLE, "psutil not available")
+    def test_timer_context_manager(self):
+        """测试计时器上下文管理器"""
+        with self.timer as t:
+            # 在这里执行一些操作
+            result = 1 + 1
+            
+        self.assertEqual(result, 2)
+        # 验证计时器已启动和停止
+        self.assertIsNotNone(t.start_time)
+        self.assertIsNotNone(t.end_time)
+        
+    @unittest.skipIf(not PSUTIL_AVAILABLE, "psutil not available")
+    def test_timer_start_stop(self):
+        """测试计时器启动和停止"""
+        self.timer.start()
+        self.assertIsNotNone(self.timer.start_time)
+        
+        # 等待一小段时间
+        import time
+        time.sleep(0.01)
+        
+        elapsed = self.timer.stop()
+        self.assertIsNotNone(self.timer.end_time)
+        self.assertIsInstance(elapsed, float)
+        self.assertGreater(elapsed, 0)
+
+
+class TestPerformanceMonitor(unittest.TestCase):
+    """性能监控器测试"""
+
+    @unittest.skipIf(not PSUTIL_AVAILABLE, "psutil not available")
+    def setUp(self):
+        """测试前准备"""
+        self.monitor = PerformanceMonitor("test_monitor")
+        
+    @unittest.skipIf(not PSUTIL_AVAILABLE, "psutil not available")
+    def test_monitor_initialization(self):
+        """测试监控器初始化"""
+        self.assertEqual(self.monitor.start_time, self.monitor.start_time)
+        self.assertIsInstance(self.monitor.metrics, dict)
+        self.assertIn('cpu_usage', self.monitor.metrics)
+        self.assertIn('memory_usage', self.monitor.metrics)
+        self.assertIn('network_io', self.monitor.metrics)
+        self.assertIn('disk_io', self.monitor.metrics)
+
+
+class TestPerformanceMonitorDecorator(unittest.TestCase):
+    """性能监控装饰器测试"""
+
+    @unittest.skipIf(not PSUTIL_AVAILABLE, "psutil not available")
+    def test_performance_monitor_decorator_sync(self):
+        """测试同步函数的性能监控装饰器"""
+        @performance_monitor_decorator(name="test_sync_function")
+        def sync_function():
+            return "test_result"
+            
+        result = sync_function()
+        self.assertEqual(result, "test_result")
+        
+    @unittest.skipIf(not PSUTIL_AVAILABLE, "psutil not available")
+    def test_performance_monitor_decorator_async(self):
+        """测试异步函数的性能监控装饰器"""
+        @performance_monitor_decorator(name="test_async_function")
+        async def async_function():
+            await asyncio.sleep(0.01)  # 模拟异步操作
+            return "async_result"
+            
+        # 使用事件循环运行异步函数
+        result = asyncio.run(async_function())
+        self.assertEqual(result, "async_result")
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_proxy_api.py

@@ -1,265 +1,265 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-代理API测试脚本
-================
-测试指定的代理API接口是否能正常工作
-"""
-
-import asyncio
-import aiohttp
-import sys
-import os
-from urllib.parse import urlparse
-
-# 添加项目根目录到Python路径
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-
-from crawlo.middleware.proxy import ProxyMiddleware
-from crawlo.network.request import Request
-from crawlo.settings.setting_manager import SettingManager
-
-
-async def test_proxy_api(proxy_api_url):
-    """测试代理API接口"""
-    print(f"=== 测试代理API接口 ===")
-    print(f"API地址: {proxy_api_url}")
-    
-    try:
-        timeout = aiohttp.ClientTimeout(total=10)
-        async with aiohttp.ClientSession(timeout=timeout) as session:
-            async with session.get(proxy_api_url) as response:
-                print(f"状态码: {response.status}")
-                print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
-                
-                # 尝试解析JSON响应
-                try:
-                    data = await response.json()
-                    print(f"响应数据: {data}")
-                    return data
-                except Exception as e:
-                    # 如果不是JSON，尝试获取文本
-                    try:
-                        text = await response.text()
-                        print(f"响应文本: {text[:200]}{'...' if len(text) > 200 else ''}")
-                        return text
-                    except Exception as e2:
-                        print(f"无法解析响应内容: {e2}")
-                        return None
-                        
-    except asyncio.TimeoutError:
-        print("请求超时")
-        return None
-    except Exception as e:
-        print(f"请求失败: {e}")
-        return None
-
-
-def extract_proxy_url(proxy_data):
-    """从API响应中提取代理URL"""
-    proxy_url = None
-    
-    if isinstance(proxy_data, dict):
-        # 检查是否有status字段且为成功状态
-        if proxy_data.get('status') == 0:
-            # 获取proxy字段
-            proxy_info = proxy_data.get('proxy', {})
-            if isinstance(proxy_info, dict):
-                # 优先使用https代理，否则使用http代理
-                proxy_url = proxy_info.get('https') or proxy_info.get('http')
-            elif isinstance(proxy_info, str):
-                proxy_url = proxy_info
-        else:
-            # 直接尝试常见的字段名
-            for key in ['proxy', 'data', 'url', 'http', 'https']:
-                if key in proxy_data:
-                    value = proxy_data[key]
-                    if isinstance(value, str):
-                        proxy_url = value
-                        break
-                    elif isinstance(value, dict):
-                        proxy_url = value.get('https') or value.get('http')
-                        break
-        
-        # 如果还是没有找到，尝试更深层的嵌套
-        if not proxy_url:
-            for key, value in proxy_data.items():
-                if isinstance(value, str) and (value.startswith('http://') or value.startswith('https://')):
-                    proxy_url = value
-                    break
-                elif isinstance(value, dict):
-                    # 递归查找
-                    for sub_key, sub_value in value.items():
-                        if isinstance(sub_value, str) and (sub_value.startswith('http://') or sub_value.startswith('https://')):
-                            proxy_url = sub_value
-                            break
-                    if proxy_url:
-                        break
-    
-    elif isinstance(proxy_data, str):
-        # 如果响应是字符串，直接使用
-        if proxy_data.startswith('http://') or proxy_data.startswith('https://'):
-            proxy_url = proxy_data
-    
-    return proxy_url
-
-
-async def test_target_url_without_proxy(target_url):
-    """不使用代理直接测试访问目标URL"""
-    print(f"\n=== 直接访问目标URL（不使用代理） ===")
-    print(f"目标URL: {target_url}")
-    
-    try:
-        timeout = aiohttp.ClientTimeout(total=15)
-        async with aiohttp.ClientSession(timeout=timeout) as session:
-            # 添加用户代理头，避免被反爬虫机制拦截
-            headers = {
-                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'
-            }
-            async with session.get(target_url, headers=headers) as response:
-                print(f"状态码: {response.status}")
-                print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
-                
-                # 只读取响应状态，不尝试解码内容
-                return response.status == 200
-                
-    except asyncio.TimeoutError:
-        print("请求超时")
-        return False
-    except Exception as e:
-        print(f"请求失败: {e}")
-        return False
-
-
-async def test_target_url_with_proxy(proxy_url, target_url, max_retries=3):
-    """使用代理测试访问目标URL"""
-    print(f"\n=== 使用代理测试访问目标URL ===")
-    print(f"代理地址: {proxy_url}")
-    print(f"目标URL: {target_url}")
-    
-    # 添加用户代理头，避免被反爬虫机制拦截
-    headers = {
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'
-    }
-    
-    for attempt in range(max_retries):
-        if attempt > 0:
-            print(f"\n第 {attempt + 1} 次重试...")
-        
-        try:
-            # 创建aiohttp客户端会话
-            timeout = aiohttp.ClientTimeout(total=15)
-            async with aiohttp.ClientSession(timeout=timeout, headers=headers) as session:
-                # 处理代理URL，支持带认证的代理
-                if isinstance(proxy_url, str) and "@" in proxy_url and "://" in proxy_url:
-                    parsed = urlparse(proxy_url)
-                    if parsed.username and parsed.password:
-                        # 提取认证信息
-                        auth = aiohttp.BasicAuth(parsed.username, parsed.password)
-                        # 清理代理URL，移除认证信息
-                        clean_proxy = f"{parsed.scheme}://{parsed.hostname}"
-                        if parsed.port:
-                            clean_proxy += f":{parsed.port}"
-                        
-                        print(f"使用带认证的代理: {clean_proxy}")
-                        async with session.get(target_url, proxy=clean_proxy, proxy_auth=auth) as response:
-                            print(f"状态码: {response.status}")
-                            print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
-                            return response.status == 200
-                    else:
-                        # 没有认证信息的代理
-                        print(f"使用普通代理: {proxy_url}")
-                        async with session.get(target_url, proxy=proxy_url) as response:
-                            print(f"状态码: {response.status}")
-                            print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
-                            return response.status == 200
-                else:
-                    # 直接使用代理URL
-                    print(f"使用代理: {proxy_url}")
-                    async with session.get(target_url, proxy=proxy_url) as response:
-                        print(f"状态码: {response.status}")
-                        print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
-                        return response.status == 200
-                        
-        except asyncio.TimeoutError:
-            print("请求超时")
-            if attempt < max_retries - 1:
-                await asyncio.sleep(2)  # 等待2秒后重试
-            continue
-        except aiohttp.ClientConnectorError as e:
-            print(f"连接错误: {e}")
-            if attempt < max_retries - 1:
-                await asyncio.sleep(2)  # 等待2秒后重试
-            continue
-        except aiohttp.ClientHttpProxyError as e:
-            print(f"代理HTTP错误: {e}")
-            if attempt < max_retries - 1:
-                await asyncio.sleep(2)  # 等待2秒后重试
-            continue
-        except aiohttp.ServerDisconnectedError as e:
-            print(f"服务器断开连接: {e}")
-            if attempt < max_retries - 1:
-                await asyncio.sleep(2)  # 等待2秒后重试
-            continue
-        except Exception as e:
-            print(f"请求失败: {e}")
-            if attempt < max_retries - 1:
-                await asyncio.sleep(2)  # 等待2秒后重试
-            continue
-    
-    return False
-
-
-async def main():
-    """主测试函数"""
-    # 指定的代理API和测试链接
-    proxy_api = 'http://test.proxy.api:8080/proxy/getitem/'
-    target_url = 'https://stock.10jqka.com.cn/20240315/c655957791.shtml'
-    
-    print("开始测试代理接口和目标链接访问...\n")
-    
-    # 1. 测试代理API接口
-    proxy_data = await test_proxy_api(proxy_api)
-    
-    if not proxy_data:
-        print("代理API测试失败，无法获取代理信息")
-        return
-    
-    # 2. 从API响应中提取代理URL
-    proxy_url = extract_proxy_url(proxy_data)
-    
-    if not proxy_url:
-        print("无法从API响应中提取代理URL")
-        print(f"API响应内容: {proxy_data}")
-        return
-    
-    print(f"\n提取到的代理URL: {proxy_url}")
-    
-    # 3. 首先尝试直接访问，确认目标URL是否可访问
-    print("\n=== 测试直接访问目标URL ===")
-    direct_success = await test_target_url_without_proxy(target_url)
-    
-    if direct_success:
-        print("直接访问目标URL成功")
-    else:
-        print("直接访问目标URL失败")
-    
-    # 4. 使用代理访问目标URL
-    print("\n=== 测试使用代理访问目标URL ===")
-    proxy_success = await test_target_url_with_proxy(proxy_url, target_url)
-    
-    if proxy_success:
-        print(f"代理测试成功！代理 {proxy_url} 可以正常访问目标链接")
-    else:
-        print(f"代理测试失败！代理 {proxy_url} 无法访问目标链接")
-        
-    # 5. 总结
-    print(f"\n=== 测试总结 ===")
-    print(f"代理API访问: {'成功' if proxy_data else '失败'}")
-    print(f"代理提取: {'成功' if proxy_url else '失败'}")
-    print(f"直接访问: {'成功' if direct_success else '失败'}")
-    print(f"代理访问: {'成功' if proxy_success else '失败'}")
-
-
-if __name__ == "__main__":
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+代理API测试脚本
+================
+测试指定的代理API接口是否能正常工作
+"""
+
+import asyncio
+import aiohttp
+import sys
+import os
+from urllib.parse import urlparse
+
+# 添加项目根目录到Python路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.middleware.proxy import ProxyMiddleware
+from crawlo.network.request import Request
+from crawlo.settings.setting_manager import SettingManager
+
+
+async def test_proxy_api(proxy_api_url):
+    """测试代理API接口"""
+    print(f"=== 测试代理API接口 ===")
+    print(f"API地址: {proxy_api_url}")
+    
+    try:
+        timeout = aiohttp.ClientTimeout(total=10)
+        async with aiohttp.ClientSession(timeout=timeout) as session:
+            async with session.get(proxy_api_url) as response:
+                print(f"状态码: {response.status}")
+                print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
+                
+                # 尝试解析JSON响应
+                try:
+                    data = await response.json()
+                    print(f"响应数据: {data}")
+                    return data
+                except Exception as e:
+                    # 如果不是JSON，尝试获取文本
+                    try:
+                        text = await response.text()
+                        print(f"响应文本: {text[:200]}{'...' if len(text) > 200 else ''}")
+                        return text
+                    except Exception as e2:
+                        print(f"无法解析响应内容: {e2}")
+                        return None
+                        
+    except asyncio.TimeoutError:
+        print("请求超时")
+        return None
+    except Exception as e:
+        print(f"请求失败: {e}")
+        return None
+
+
+def extract_proxy_url(proxy_data):
+    """从API响应中提取代理URL"""
+    proxy_url = None
+    
+    if isinstance(proxy_data, dict):
+        # 检查是否有status字段且为成功状态
+        if proxy_data.get('status') == 0:
+            # 获取proxy字段
+            proxy_info = proxy_data.get('proxy', {})
+            if isinstance(proxy_info, dict):
+                # 优先使用https代理，否则使用http代理
+                proxy_url = proxy_info.get('https') or proxy_info.get('http')
+            elif isinstance(proxy_info, str):
+                proxy_url = proxy_info
+        else:
+            # 直接尝试常见的字段名
+            for key in ['proxy', 'data', 'url', 'http', 'https']:
+                if key in proxy_data:
+                    value = proxy_data[key]
+                    if isinstance(value, str):
+                        proxy_url = value
+                        break
+                    elif isinstance(value, dict):
+                        proxy_url = value.get('https') or value.get('http')
+                        break
+        
+        # 如果还是没有找到，尝试更深层的嵌套
+        if not proxy_url:
+            for key, value in proxy_data.items():
+                if isinstance(value, str) and (value.startswith('http://') or value.startswith('https://')):
+                    proxy_url = value
+                    break
+                elif isinstance(value, dict):
+                    # 递归查找
+                    for sub_key, sub_value in value.items():
+                        if isinstance(sub_value, str) and (sub_value.startswith('http://') or sub_value.startswith('https://')):
+                            proxy_url = sub_value
+                            break
+                    if proxy_url:
+                        break
+    
+    elif isinstance(proxy_data, str):
+        # 如果响应是字符串，直接使用
+        if proxy_data.startswith('http://') or proxy_data.startswith('https://'):
+            proxy_url = proxy_data
+    
+    return proxy_url
+
+
+async def test_target_url_without_proxy(target_url):
+    """不使用代理直接测试访问目标URL"""
+    print(f"\n=== 直接访问目标URL（不使用代理） ===")
+    print(f"目标URL: {target_url}")
+    
+    try:
+        timeout = aiohttp.ClientTimeout(total=15)
+        async with aiohttp.ClientSession(timeout=timeout) as session:
+            # 添加用户代理头，避免被反爬虫机制拦截
+            headers = {
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'
+            }
+            async with session.get(target_url, headers=headers) as response:
+                print(f"状态码: {response.status}")
+                print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
+                
+                # 只读取响应状态，不尝试解码内容
+                return response.status == 200
+                
+    except asyncio.TimeoutError:
+        print("请求超时")
+        return False
+    except Exception as e:
+        print(f"请求失败: {e}")
+        return False
+
+
+async def test_target_url_with_proxy(proxy_url, target_url, max_retries=3):
+    """使用代理测试访问目标URL"""
+    print(f"\n=== 使用代理测试访问目标URL ===")
+    print(f"代理地址: {proxy_url}")
+    print(f"目标URL: {target_url}")
+    
+    # 添加用户代理头，避免被反爬虫机制拦截
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'
+    }
+    
+    for attempt in range(max_retries):
+        if attempt > 0:
+            print(f"\n第 {attempt + 1} 次重试...")
+        
+        try:
+            # 创建aiohttp客户端会话
+            timeout = aiohttp.ClientTimeout(total=15)
+            async with aiohttp.ClientSession(timeout=timeout, headers=headers) as session:
+                # 处理代理URL，支持带认证的代理
+                if isinstance(proxy_url, str) and "@" in proxy_url and "://" in proxy_url:
+                    parsed = urlparse(proxy_url)
+                    if parsed.username and parsed.password:
+                        # 提取认证信息
+                        auth = aiohttp.BasicAuth(parsed.username, parsed.password)
+                        # 清理代理URL，移除认证信息
+                        clean_proxy = f"{parsed.scheme}://{parsed.hostname}"
+                        if parsed.port:
+                            clean_proxy += f":{parsed.port}"
+                        
+                        print(f"使用带认证的代理: {clean_proxy}")
+                        async with session.get(target_url, proxy=clean_proxy, proxy_auth=auth) as response:
+                            print(f"状态码: {response.status}")
+                            print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
+                            return response.status == 200
+                    else:
+                        # 没有认证信息的代理
+                        print(f"使用普通代理: {proxy_url}")
+                        async with session.get(target_url, proxy=proxy_url) as response:
+                            print(f"状态码: {response.status}")
+                            print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
+                            return response.status == 200
+                else:
+                    # 直接使用代理URL
+                    print(f"使用代理: {proxy_url}")
+                    async with session.get(target_url, proxy=proxy_url) as response:
+                        print(f"状态码: {response.status}")
+                        print(f"响应头: {response.headers.get('content-type', 'Unknown')}")
+                        return response.status == 200
+                        
+        except asyncio.TimeoutError:
+            print("请求超时")
+            if attempt < max_retries - 1:
+                await asyncio.sleep(2)  # 等待2秒后重试
+            continue
+        except aiohttp.ClientConnectorError as e:
+            print(f"连接错误: {e}")
+            if attempt < max_retries - 1:
+                await asyncio.sleep(2)  # 等待2秒后重试
+            continue
+        except aiohttp.ClientHttpProxyError as e:
+            print(f"代理HTTP错误: {e}")
+            if attempt < max_retries - 1:
+                await asyncio.sleep(2)  # 等待2秒后重试
+            continue
+        except aiohttp.ServerDisconnectedError as e:
+            print(f"服务器断开连接: {e}")
+            if attempt < max_retries - 1:
+                await asyncio.sleep(2)  # 等待2秒后重试
+            continue
+        except Exception as e:
+            print(f"请求失败: {e}")
+            if attempt < max_retries - 1:
+                await asyncio.sleep(2)  # 等待2秒后重试
+            continue
+    
+    return False
+
+
+async def main():
+    """主测试函数"""
+    # 指定的代理API和测试链接
+    proxy_api = 'http://test.proxy.api:8080/proxy/getitem/'
+    target_url = 'https://stock.10jqka.com.cn/20240315/c655957791.shtml'
+    
+    print("开始测试代理接口和目标链接访问...\n")
+    
+    # 1. 测试代理API接口
+    proxy_data = await test_proxy_api(proxy_api)
+    
+    if not proxy_data:
+        print("代理API测试失败，无法获取代理信息")
+        return
+    
+    # 2. 从API响应中提取代理URL
+    proxy_url = extract_proxy_url(proxy_data)
+    
+    if not proxy_url:
+        print("无法从API响应中提取代理URL")
+        print(f"API响应内容: {proxy_data}")
+        return
+    
+    print(f"\n提取到的代理URL: {proxy_url}")
+    
+    # 3. 首先尝试直接访问，确认目标URL是否可访问
+    print("\n=== 测试直接访问目标URL ===")
+    direct_success = await test_target_url_without_proxy(target_url)
+    
+    if direct_success:
+        print("直接访问目标URL成功")
+    else:
+        print("直接访问目标URL失败")
+    
+    # 4. 使用代理访问目标URL
+    print("\n=== 测试使用代理访问目标URL ===")
+    proxy_success = await test_target_url_with_proxy(proxy_url, target_url)
+    
+    if proxy_success:
+        print(f"代理测试成功！代理 {proxy_url} 可以正常访问目标链接")
+    else:
+        print(f"代理测试失败！代理 {proxy_url} 无法访问目标链接")
+        
+    # 5. 总结
+    print(f"\n=== 测试总结 ===")
+    print(f"代理API访问: {'成功' if proxy_data else '失败'}")
+    print(f"代理提取: {'成功' if proxy_url else '失败'}")
+    print(f"直接访问: {'成功' if direct_success else '失败'}")
+    print(f"代理访问: {'成功' if proxy_success else '失败'}")
+
+
+if __name__ == "__main__":
     asyncio.run(main())