crawlo 1.1.4__py3-none-any.whl → 1.1.5__py3-none-any.whl

tests/test_config_validator.py

@@ -0,0 +1,194 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+配置验证器测试脚本
+用于验证配置验证器的功能
+"""
+import sys
+import os
+import unittest
+
+# 添加项目根目录到路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.config_validator import ConfigValidator, validate_config
+
+
+class TestConfigValidator(unittest.TestCase):
+    """配置验证器测试类"""
+    
+    def setUp(self):
+        """测试前准备"""
+        self.validator = ConfigValidator()
+    
+    def test_valid_standalone_config(self):
+        """测试有效的单机配置"""
+        config = {
+            'PROJECT_NAME': 'test_project',
+            'QUEUE_TYPE': 'memory',
+            'CONCURRENCY': 8,
+            'DOWNLOAD_DELAY': 1.0,
+            'DOWNLOAD_TIMEOUT': 30,
+            'CONNECTION_POOL_LIMIT': 50,
+            'SCHEDULER_MAX_QUEUE_SIZE': 2000,
+            'LOG_LEVEL': 'INFO',
+            'MIDDLEWARES': [
+                'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
+                'crawlo.middleware.download_delay.DownloadDelayMiddleware'
+            ],
+            'PIPELINES': [
+                'crawlo.pipelines.console_pipeline.ConsolePipeline'
+            ]
+        }
+        
+        is_valid, errors, warnings = self.validator.validate(config)
+        self.assertTrue(is_valid)
+        self.assertEqual(len(errors), 0)
+    
+    def test_valid_distributed_config(self):
+        """测试有效的分布式配置"""
+        config = {
+            'PROJECT_NAME': 'test_project',
+            'QUEUE_TYPE': 'redis',
+            'CONCURRENCY': 16,
+            'DOWNLOAD_DELAY': 1.0,
+            'DOWNLOAD_TIMEOUT': 30,
+            'CONNECTION_POOL_LIMIT': 50,
+            'SCHEDULER_MAX_QUEUE_SIZE': 2000,
+            'SCHEDULER_QUEUE_NAME': 'crawlo:test_project:queue:requests',
+            'REDIS_HOST': '127.0.0.1',
+            'REDIS_PORT': 6379,
+            'REDIS_URL': 'redis://127.0.0.1:6379/0',
+            'LOG_LEVEL': 'INFO',
+            'MIDDLEWARES': [
+                'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
+                'crawlo.middleware.download_delay.DownloadDelayMiddleware'
+            ],
+            'PIPELINES': [
+                'crawlo.pipelines.console_pipeline.ConsolePipeline'
+            ]
+        }
+        
+        is_valid, errors, warnings = self.validator.validate(config)
+        self.assertTrue(is_valid)
+        self.assertEqual(len(errors), 0)
+    
+    def test_invalid_project_name(self):
+        """测试无效的项目名称"""
+        config = {
+            'PROJECT_NAME': '',  # 空字符串
+            'QUEUE_TYPE': 'memory',
+            'CONCURRENCY': 8
+        }
+        
+        is_valid, errors, warnings = self.validator.validate(config)
+        self.assertFalse(is_valid)
+        self.assertIn("PROJECT_NAME 必须是非空字符串", errors)
+    
+    def test_invalid_concurrency(self):
+        """测试无效的并发数"""
+        config = {
+            'PROJECT_NAME': 'test_project',
+            'QUEUE_TYPE': 'memory',
+            'CONCURRENCY': -1  # 负数
+        }
+        
+        is_valid, errors, warnings = self.validator.validate(config)
+        self.assertFalse(is_valid)
+        self.assertIn("CONCURRENCY 必须是正整数", errors)
+    
+    def test_invalid_queue_type(self):
+        """测试无效的队列类型"""
+        config = {
+            'PROJECT_NAME': 'test_project',
+            'QUEUE_TYPE': 'invalid_type',  # 无效类型
+            'CONCURRENCY': 8
+        }
+        
+        is_valid, errors, warnings = self.validator.validate(config)
+        self.assertFalse(is_valid)
+        self.assertIn("QUEUE_TYPE 必须是以下值之一: ['memory', 'redis', 'auto']", errors)
+    
+    def test_invalid_redis_queue_name(self):
+        """测试无效的Redis队列名称"""
+        config = {
+            'PROJECT_NAME': 'test_project',
+            'QUEUE_TYPE': 'redis',
+            'CONCURRENCY': 8,
+            'SCHEDULER_QUEUE_NAME': 'invalid_queue_name'  # 不符合命名规范
+        }
+        
+        is_valid, errors, warnings = self.validator.validate(config)
+        self.assertTrue(is_valid)  # 队列名称错误是警告，不是错误
+        self.assertGreater(len(warnings), 0)
+        self.assertTrue(any("Redis队列名称" in warning for warning in warnings))
+    
+    def test_missing_redis_queue_name(self):
+        """测试缺少Redis队列名称"""
+        config = {
+            'PROJECT_NAME': 'test_project',
+            'QUEUE_TYPE': 'redis',
+            'CONCURRENCY': 8
+            # 缺少 SCHEDULER_QUEUE_NAME
+        }
+        
+        is_valid, errors, warnings = self.validator.validate(config)
+        self.assertFalse(is_valid)
+        self.assertIn("使用Redis队列时，SCHEDULER_QUEUE_NAME 不能为空", errors)
+    
+    def test_invalid_redis_port(self):
+        """测试无效的Redis端口"""
+        config = {
+            'PROJECT_NAME': 'test_project',
+            'QUEUE_TYPE': 'redis',
+            'CONCURRENCY': 8,
+            'SCHEDULER_QUEUE_NAME': 'crawlo:test_project:queue:requests',
+            'REDIS_HOST': '127.0.0.1',
+            'REDIS_PORT': 99999  # 无效端口
+        }
+        
+        is_valid, errors, warnings = self.validator.validate(config)
+        self.assertFalse(is_valid)
+        self.assertIn("REDIS_PORT 必须是1-65535之间的整数", errors)
+    
+    def test_invalid_log_level(self):
+        """测试无效的日志级别"""
+        config = {
+            'PROJECT_NAME': 'test_project',
+            'QUEUE_TYPE': 'memory',
+            'CONCURRENCY': 8,
+            'LOG_LEVEL': 'INVALID_LEVEL'  # 无效日志级别
+        }
+        
+        is_valid, errors, warnings = self.validator.validate(config)
+        self.assertFalse(is_valid)
+        self.assertIn("LOG_LEVEL 必须是以下值之一: ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']", errors)
+    
+    def test_convenience_function(self):
+        """测试便利函数"""
+        config = {
+            'PROJECT_NAME': 'test_project',
+            'QUEUE_TYPE': 'memory',
+            'CONCURRENCY': 8,
+            'LOG_LEVEL': 'INFO'
+        }
+        
+        is_valid, errors, warnings = validate_config(config)
+        self.assertTrue(is_valid)
+        self.assertEqual(len(errors), 0)
+
+
+def main():
+    """主测试函数"""
+    print("🚀 开始配置验证器测试...")
+    print("=" * 50)
+    
+    # 运行测试
+    unittest.main(argv=['first-arg-is-ignored'], exit=False, verbosity=2)
+    
+    print("=" * 50)
+    print("✅ 配置验证器测试完成")
+
+
+if __name__ == "__main__":
+    main()

tests/test_date_tools.py

@@ -0,0 +1,124 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+日期工具测试
+"""
+import unittest
+from crawlo.tools import (
+    TimeUtils,
+    parse_time,
+    format_time,
+    time_diff,
+    to_timestamp,
+    to_datetime,
+    now,
+    to_timezone,
+    to_utc,
+    to_local
+)
+
+
+class TestDateTools(unittest.TestCase):
+    """日期工具测试类"""
+
+    def test_date_parsing(self):
+        """测试日期解析功能"""
+        # 测试标准格式
+        dt = parse_time("2025-09-10 14:30:00")
+        self.assertIsNotNone(dt)
+        self.assertEqual(dt.year, 2025)
+        self.assertEqual(dt.month, 9)
+        self.assertEqual(dt.day, 10)
+        self.assertEqual(dt.hour, 14)
+        self.assertEqual(dt.minute, 30)
+        self.assertEqual(dt.second, 0)
+        
+        # 测试不同格式
+        dt2 = parse_time("September 10, 2025 2:30 PM")
+        self.assertIsNotNone(dt2)
+        self.assertEqual(dt2.year, 2025)
+        self.assertEqual(dt2.month, 9)
+        self.assertEqual(dt2.day, 10)
+        self.assertEqual(dt2.hour, 14)
+        self.assertEqual(dt2.minute, 30)
+
+    def test_date_formatting(self):
+        """测试日期格式化功能"""
+        dt = parse_time("2025-09-10 14:30:00")
+        
+        # 测试标准格式
+        formatted = format_time(dt, "%Y-%m-%d")
+        self.assertEqual(formatted, "2025-09-10")
+        
+        # 测试中文格式
+        formatted_cn = format_time(dt, "%Y年%m月%d日")
+        self.assertEqual(formatted_cn, "2025年09月10日")
+
+    def test_time_difference(self):
+        """测试时间差计算功能"""
+        start_time = "2025-09-10 10:00:00"
+        end_time = "2025-09-10 14:30:45"
+        
+        # 测试秒级差值
+        diff_seconds = time_diff(start_time, end_time, "seconds")
+        self.assertEqual(diff_seconds, 16245)  # 4小时30分45秒 = 16245秒
+        
+        # 测试分钟级差值
+        diff_minutes = time_diff(start_time, end_time, "minutes")
+        self.assertEqual(diff_minutes, 270)  # 270分钟
+        
+        # 测试小时级差值
+        diff_hours = time_diff(start_time, end_time, "hours")
+        self.assertEqual(diff_hours, 4)  # 4小时
+
+    def test_timestamp_conversion(self):
+        """测试时间戳转换功能"""
+        # 测试转换为时间戳
+        dt = parse_time("2025-09-10 14:30:00")
+        timestamp = to_timestamp(dt)
+        self.assertIsInstance(timestamp, float)
+        
+        # 测试从时间戳转换
+        dt_from_ts = to_datetime(timestamp)
+        self.assertEqual(dt.year, dt_from_ts.year)
+        self.assertEqual(dt.month, dt_from_ts.month)
+        self.assertEqual(dt.day, dt_from_ts.day)
+        self.assertEqual(dt.hour, dt_from_ts.hour)
+        self.assertEqual(dt.minute, dt_from_ts.minute)
+        self.assertEqual(dt.second, dt_from_ts.second)
+
+    def test_timezone_conversion(self):
+        """测试时区转换功能"""
+        dt = parse_time("2025-09-10 14:30:00")
+        
+        # 测试UTC转换
+        utc_time = to_utc(dt)
+        self.assertIsNotNone(utc_time)
+        
+        # 测试本地时区转换
+        local_time = to_local(dt)
+        self.assertIsNotNone(local_time)
+        
+        # 测试指定时区转换
+        ny_time = to_timezone(dt, "America/New_York")
+        self.assertIsNotNone(ny_time)
+
+    def test_time_utils_class(self):
+        """测试TimeUtils类方法"""
+        # 测试日期加减
+        base_date = "2025-09-10"
+        plus_30_days = TimeUtils.add_days(base_date, 30)
+        self.assertEqual(plus_30_days.month, 10)
+        self.assertEqual(plus_30_days.day, 10)
+        
+        # 测试月份加减
+        plus_3_months = TimeUtils.add_months(base_date, 3)
+        self.assertEqual(plus_3_months.month, 12)
+        
+        # 测试闰年判断
+        self.assertTrue(TimeUtils.is_leap_year(2024))
+        self.assertFalse(TimeUtils.is_leap_year(2025))
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_dynamic_downloaders_proxy.py

@@ -0,0 +1,125 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+测试动态下载器（Selenium和Playwright）的代理功能
+"""
+
+import asyncio
+from crawlo.tools import AuthenticatedProxy
+
+
+def test_selenium_proxy_configuration():
+    """测试Selenium下载器的代理配置"""
+    print("=== 测试Selenium下载器的代理配置 ===")
+    
+    # 代理配置
+    proxy_config = {
+        "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
+        "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
+    }
+    
+    # 创建代理对象
+    proxy_url = proxy_config["http"]
+    proxy = AuthenticatedProxy(proxy_url)
+    
+    print(f"原始代理URL: {proxy_url}")
+    print(f"清洁URL: {proxy.clean_url}")
+    print(f"认证信息: {proxy.get_auth_credentials()}")
+    
+    # Selenium的代理设置方式
+    print(f"\nSelenium代理设置方式:")
+    print(f"  1. 在爬虫设置中配置:")
+    print(f"     settings = {{")
+    print(f"         'SELENIUM_PROXY': '{proxy.clean_url}',")
+    print(f"     }}")
+    
+    # 对于带认证的代理，需要特殊处理
+    if proxy.username and proxy.password:
+        print(f"\n  2. 带认证代理的处理:")
+        print(f"     - 用户名: {proxy.username}")
+        print(f"     - 密码: {proxy.password}")
+        print(f"     - 认证头: {proxy.get_auth_header()}")
+        print(f"     - 注意: Selenium需要通过扩展或其他方式处理认证")
+    
+    print("\nSelenium测试完成!")
+
+
+async def test_playwright_proxy_configuration():
+    """测试Playwright下载器的代理配置"""
+    print("\n=== 测试Playwright下载器的代理配置 ===")
+    
+    # 代理配置
+    proxy_config = {
+        "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
+        "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
+    }
+    
+    # 创建代理对象
+    proxy_url = proxy_config["http"]
+    proxy = AuthenticatedProxy(proxy_url)
+    
+    print(f"原始代理URL: {proxy_url}")
+    print(f"清洁URL: {proxy.clean_url}")
+    print(f"认证信息: {proxy.get_auth_credentials()}")
+    
+    # Playwright的代理设置方式
+    print(f"\nPlaywright代理设置方式:")
+    print(f"  1. 简单代理配置:")
+    print(f"     settings = {{")
+    print(f"         'PLAYWRIGHT_PROXY': '{proxy.clean_url}',")
+    print(f"     }}")
+    
+    # 对于带认证的代理，Playwright可以直接在代理配置中包含认证信息
+    if proxy.username and proxy.password:
+        print(f"\n  2. 带认证的代理配置:")
+        print(f"     settings = {{")
+        print(f"         'PLAYWRIGHT_PROXY': {{")
+        print(f"             'server': '{proxy.clean_url}',")
+        print(f"             'username': '{proxy.username}',")
+        print(f"             'password': '{proxy.password}'")
+        print(f"         }}")
+        print(f"     }}")
+    
+    print("\nPlaywright测试完成!")
+
+
+def show_proxy_usage_examples():
+    """显示代理使用示例"""
+    print("\n=== 代理使用示例 ===")
+    
+    # 代理配置示例
+    proxy_examples = [
+        "http://username:password@proxy.example.com:8080",  # 带认证HTTP代理
+        "https://user:pass@secure-proxy.example.com:443",   # 带认证HTTPS代理
+        "http://proxy.example.com:8080",                    # 不带认证代理
+        "socks5://username:password@socks-proxy.example.com:1080"  # SOCKS5代理
+    ]
+    
+    for i, proxy_url in enumerate(proxy_examples, 1):
+        print(f"\n示例 {i}: {proxy_url}")
+        try:
+            proxy = AuthenticatedProxy(proxy_url)
+            print(f"  清洁URL: {proxy.clean_url}")
+            print(f"  用户名: {proxy.username or '无'}")
+            print(f"  密码: {proxy.password or '无'}")
+            print(f"  是否有效: {proxy.is_valid()}")
+            if proxy.username and proxy.password:
+                print(f"  认证头: {proxy.get_auth_header()}")
+        except Exception as e:
+            print(f"  错误: {e}")
+
+
+async def main():
+    """主测试函数"""
+    print("开始测试动态下载器的代理功能...\n")
+    
+    # 测试各个下载器
+    test_selenium_proxy_configuration()
+    await test_playwright_proxy_configuration()
+    show_proxy_usage_examples()
+    
+    print("\n所有测试完成!")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

tests/test_dynamic_proxy.py

@@ -0,0 +1,93 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+测试动态下载器（Selenium和Playwright）的代理功能
+"""
+
+import asyncio
+from crawlo.network.request import Request
+from crawlo.tools import AuthenticatedProxy
+
+
+def test_proxy_with_selenium():
+    """测试Selenium下载器与认证代理"""
+    print("=== 测试Selenium下载器与认证代理 ===")
+    
+    # 代理配置
+    proxy_config = {
+        "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
+        "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
+    }
+    
+    # 创建代理对象
+    proxy_url = proxy_config["http"]
+    proxy = AuthenticatedProxy(proxy_url)
+    
+    print(f"原始代理URL: {proxy_url}")
+    print(f"清洁URL: {proxy.clean_url}")
+    print(f"认证信息: {proxy.get_auth_credentials()}")
+    
+    # Selenium的代理设置方式
+    print(f"Selenium代理设置方式:")
+    print(f"  1. 在设置中配置: SELENIUM_PROXY = '{proxy.clean_url}'")
+    print(f"  2. 认证信息需要通过其他方式处理")
+    
+    # 对于带认证的代理，Selenium需要特殊处理
+    if proxy.username and proxy.password:
+        print(f"  3. 认证信息:")
+        print(f"    用户名: {proxy.username}")
+        print(f"    密码: {proxy.password}")
+        print(f"    认证头: {proxy.get_auth_header()}")
+    
+    print("Selenium测试完成!")
+
+
+async def test_proxy_with_playwright():
+    """测试Playwright下载器与认证代理"""
+    print("\n=== 测试Playwright下载器与认证代理 ===")
+    
+    # 代理配置
+    proxy_config = {
+        "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
+        "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
+    }
+    
+    # 创建代理对象
+    proxy_url = proxy_config["http"]
+    proxy = AuthenticatedProxy(proxy_url)
+    
+    print(f"原始代理URL: {proxy_url}")
+    print(f"清洁URL: {proxy.clean_url}")
+    print(f"认证信息: {proxy.get_auth_credentials()}")
+    
+    # Playwright的代理设置方式
+    print(f"Playwright代理设置方式:")
+    print(f"  1. 在启动浏览器时配置代理:")
+    print(f"     browser = await playwright.chromium.launch(proxy={{'server': '{proxy.clean_url}'}})")
+    
+    # 对于带认证的代理，Playwright需要在代理配置中包含认证信息
+    if proxy.username and proxy.password:
+        print(f"  2. 带认证的代理配置:")
+        print(f"     proxy_config = {{")
+        print(f"         'server': '{proxy.clean_url}',")
+        print(f"         'username': '{proxy.username}',")
+        print(f"         'password': '{proxy.password}'")
+        print(f"     }}")
+        print(f"     browser = await playwright.chromium.launch(proxy=proxy_config)")
+    
+    print("Playwright测试完成!")
+
+
+async def main():
+    """主测试函数"""
+    print("开始测试动态下载器的代理功能...\n")
+    
+    # 测试各个下载器
+    test_proxy_with_selenium()
+    await test_proxy_with_playwright()
+    
+    print("\n所有测试完成!")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

tests/test_dynamic_proxy_config.py

@@ -0,0 +1,147 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+测试动态下载器（Selenium和Playwright）的代理配置逻辑
+"""
+
+from crawlo.tools import AuthenticatedProxy
+
+
+def test_selenium_proxy_logic():
+    """测试Selenium下载器的代理配置逻辑"""
+    print("=== 测试Selenium下载器的代理配置逻辑 ===")
+    
+    # 代理配置
+    proxy_config = {
+        "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
+        "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
+    }
+    
+    # 创建代理对象
+    proxy_url = proxy_config["http"]
+    proxy = AuthenticatedProxy(proxy_url)
+    
+    print(f"原始代理URL: {proxy_url}")
+    print(f"清洁URL: {proxy.clean_url}")
+    print(f"认证信息: {proxy.get_auth_credentials()}")
+    
+    # 模拟Selenium的代理配置逻辑
+    print(f"\nSelenium代理配置逻辑:")
+    print(f"  1. 在爬虫设置中配置:")
+    print(f"     settings = {{")
+    print(f"         'SELENIUM_PROXY': '{proxy.clean_url}',")
+    print(f"     }}")
+    
+    # 对于带认证的代理，需要特殊处理
+    if proxy.username and proxy.password:
+        print(f"\n  2. 带认证代理的处理逻辑:")
+        print(f"     - 用户名: {proxy.username}")
+        print(f"     - 密码: {proxy.password}")
+        print(f"     - 认证头: {proxy.get_auth_header()}")
+        print(f"     - 处理方式: 通过浏览器扩展或手动输入认证信息")
+    
+    print("\nSelenium配置逻辑测试完成!")
+
+
+def test_playwright_proxy_logic():
+    """测试Playwright下载器的代理配置逻辑"""
+    print("\n=== 测试Playwright下载器的代理配置逻辑 ===")
+    
+    # 代理配置
+    proxy_config = {
+        "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
+        "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
+    }
+    
+    # 创建代理对象
+    proxy_url = proxy_config["http"]
+    proxy = AuthenticatedProxy(proxy_url)
+    
+    print(f"原始代理URL: {proxy_url}")
+    print(f"清洁URL: {proxy.clean_url}")
+    print(f"认证信息: {proxy.get_auth_credentials()}")
+    
+    # 模拟Playwright的代理配置逻辑
+    print(f"\nPlaywright代理配置逻辑:")
+    print(f"  1. 简单代理配置:")
+    print(f"     settings = {{")
+    print(f"         'PLAYWRIGHT_PROXY': '{proxy.clean_url}',")
+    print(f"     }}")
+    
+    # 对于带认证的代理，Playwright可以直接在代理配置中包含认证信息
+    if proxy.username and proxy.password:
+        print(f"\n  2. 带认证的代理配置逻辑:")
+        print(f"     settings = {{")
+        print(f"         'PLAYWRIGHT_PROXY': {{")
+        print(f"             'server': '{proxy.clean_url}',")
+        print(f"             'username': '{proxy.username}',")
+        print(f"             'password': '{proxy.password}'")
+        print(f"         }}")
+        print(f"     }}")
+        print(f"     实现方式: 在启动浏览器时传递proxy参数")
+    
+    print("\nPlaywright配置逻辑测试完成!")
+
+
+def show_proxy_configuration_examples():
+    """显示代理配置示例"""
+    print("\n=== 代理配置示例 ===")
+    
+    # 不同类型的代理配置示例
+    examples = [
+        {
+            "name": "带认证HTTP代理",
+            "url": "http://username:password@proxy.example.com:8080",
+            "selenium_config": "SELENIUM_PROXY = 'http://proxy.example.com:8080'",
+            "playwright_config": "PLAYWRIGHT_PROXY = {'server': 'http://proxy.example.com:8080', 'username': 'username', 'password': 'password'}"
+        },
+        {
+            "name": "带认证HTTPS代理",
+            "url": "https://user:pass@secure-proxy.example.com:443",
+            "selenium_config": "SELENIUM_PROXY = 'https://secure-proxy.example.com:443'",
+            "playwright_config": "PLAYWRIGHT_PROXY = {'server': 'https://secure-proxy.example.com:443', 'username': 'user', 'password': 'pass'}"
+        },
+        {
+            "name": "SOCKS5代理",
+            "url": "socks5://username:password@socks-proxy.example.com:1080",
+            "selenium_config": "SELENIUM_PROXY = 'socks5://socks-proxy.example.com:1080'",
+            "playwright_config": "PLAYWRIGHT_PROXY = {'server': 'socks5://socks-proxy.example.com:1080', 'username': 'username', 'password': 'password'}"
+        },
+        {
+            "name": "不带认证代理",
+            "url": "http://proxy.example.com:8080",
+            "selenium_config": "SELENIUM_PROXY = 'http://proxy.example.com:8080'",
+            "playwright_config": "PLAYWRIGHT_PROXY = 'http://proxy.example.com:8080'"
+        }
+    ]
+    
+    for i, example in enumerate(examples, 1):
+        print(f"\n示例 {i}: {example['name']}")
+        print(f"  代理URL: {example['url']}")
+        proxy = AuthenticatedProxy(example['url'])
+        print(f"  清洁URL: {proxy.clean_url}")
+        print(f"  用户名: {proxy.username or '无'}")
+        print(f"  密码: {proxy.password or '无'}")
+        print(f"  Selenium配置: {example['selenium_config']}")
+        print(f"  Playwright配置: {example['playwright_config']}")
+
+
+def main():
+    """主函数"""
+    print("开始测试动态下载器的代理配置逻辑...\n")
+    
+    # 测试各个下载器的配置逻辑
+    test_selenium_proxy_logic()
+    test_playwright_proxy_logic()
+    show_proxy_configuration_examples()
+    
+    print("\n所有配置逻辑测试完成!")
+    print("\n总结:")
+    print("1. Selenium和Playwright都支持代理配置")
+    print("2. 带认证的代理需要特殊处理")
+    print("3. Playwright对带认证代理的支持更直接")
+    print("4. Selenium需要通过扩展或其他方式处理认证")
+
+
+if __name__ == "__main__":
+    main()