crawlo 1.1.6__py3-none-any.whl → 1.1.9__py3-none-any.whl

tests/test_double_crawlo_fix_simple.py

@@ -1,125 +1,125 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-双重 crawlo 前缀问题修复简单测试脚本
-用于验证 Redis 队列名称中双重 crawlo 前缀问题的修复，不依赖于实际的 Redis 连接
-"""
-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.redis_priority_queue import RedisPriorityQueue
-
-
-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_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_queue": "crawlo:crawlo:queue:requests",  # 保持原始名称不变
-            "expected_processing": "crawlo:crawlo:queue:processing",  # 保持一致的双重前缀
-            "expected_failed": "crawlo:crawlo:queue:failed"
-        },
-        {
-            "name": "三重 crawlo 前缀",
-            "queue_name": "crawlo:crawlo:crawlo:queue:requests",
-            "expected_queue": "crawlo:crawlo:crawlo:queue:requests",  # 保持原始名称不变
-            "expected_processing": "crawlo:crawlo:crawlo:queue:processing",  # 保持一致的前缀
-            "expected_failed": "crawlo:crawlo:crawlo:queue:failed"
-        },
-        {
-            "name": "无 crawlo 前缀",
-            "queue_name": "test_project:queue:requests",
-            "expected_queue": "test_project:queue:requests",  # 保持原始名称不变
-            "expected_processing": "test_project:queue:processing",
-            "expected_failed": "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 初始化
-            try:
-                queue = RedisPriorityQueue(
-                    redis_url="redis://127.0.0.1:6379/15",
-                    queue_name=test_case['queue_name'],
-                    module_name="test_project"
-                )
-                
-                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
-
-
-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 = test_redis_queue_naming()
-        print()
-        
-        print("=" * 50)
-        if redis_test_success:
-            print("🎉 Redis 队列命名修复测试通过！双重 crawlo 前缀问题已修复")
-        else:
-            print("❌ Redis 队列命名修复测试失败，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 -*-
+"""
+双重 crawlo 前缀问题修复简单测试脚本
+用于验证 Redis 队列名称中双重 crawlo 前缀问题的修复，不依赖于实际的 Redis 连接
+"""
+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.redis_priority_queue import RedisPriorityQueue
+
+
+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_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_queue": "crawlo:crawlo:queue:requests",  # 保持原始名称不变
+            "expected_processing": "crawlo:crawlo:queue:processing",  # 保持一致的双重前缀
+            "expected_failed": "crawlo:crawlo:queue:failed"
+        },
+        {
+            "name": "三重 crawlo 前缀",
+            "queue_name": "crawlo:crawlo:crawlo:queue:requests",
+            "expected_queue": "crawlo:crawlo:crawlo:queue:requests",  # 保持原始名称不变
+            "expected_processing": "crawlo:crawlo:crawlo:queue:processing",  # 保持一致的前缀
+            "expected_failed": "crawlo:crawlo:crawlo:queue:failed"
+        },
+        {
+            "name": "无 crawlo 前缀",
+            "queue_name": "test_project:queue:requests",
+            "expected_queue": "test_project:queue:requests",  # 保持原始名称不变
+            "expected_processing": "test_project:queue:processing",
+            "expected_failed": "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 初始化
+            try:
+                queue = RedisPriorityQueue(
+                    redis_url="redis://127.0.0.1:6379/15",
+                    queue_name=test_case['queue_name'],
+                    module_name="test_project"
+                )
+                
+                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
+
+
+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 = test_redis_queue_naming()
+        print()
+        
+        print("=" * 50)
+        if redis_test_success:
+            print("🎉 Redis 队列命名修复测试通过！双重 crawlo 前缀问题已修复")
+        else:
+            print("❌ Redis 队列命名修复测试失败，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)

tests/test_dynamic_downloaders_proxy.py

@@ -1,125 +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__":
+#!/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())