crawlo 1.1.9__py3-none-any.whl → 1.2.1__py3-none-any.whl

tests/test_downloader_proxy_compatibility.py

@@ -0,0 +1,269 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+测试代理中间件与Crawlo框架中三个主要下载器的兼容性
+- aiohttp_downloader
+- httpx_downloader
+- curl_cffi_downloader
+"""
+
+import asyncio
+import sys
+import os
+
+# 添加项目根目录到Python路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.downloader.aiohttp_downloader import AioHttpDownloader
+from crawlo.downloader.httpx_downloader import HttpXDownloader
+from crawlo.downloader.cffi_downloader import CurlCffiDownloader
+from crawlo.middleware.proxy import ProxyMiddleware
+from crawlo.network.request import Request
+from crawlo.settings.setting_manager import SettingManager
+
+
+class MockSpider:
+    """模拟爬虫类"""
+    def __init__(self, crawler):
+        self.crawler = crawler
+
+
+class MockCrawler:
+    """模拟爬虫实例"""
+    def __init__(self, settings):
+        self.settings = settings
+        self.spider = MockSpider(self)  # 添加spider属性
+
+
+def create_test_settings(proxy_url=None):
+    """创建测试设置"""
+    settings = SettingManager()
+    settings.set("LOG_LEVEL", "DEBUG")
+    settings.set("DOWNLOAD_TIMEOUT", 30)
+    settings.set("CONNECTION_POOL_LIMIT", 100)
+    settings.set("CONNECTION_POOL_LIMIT_PER_HOST", 20)
+    settings.set("DOWNLOAD_MAXSIZE", 10 * 1024 * 1024)
+    settings.set("VERIFY_SSL", True)
+    
+    # 代理相关设置
+    if proxy_url:
+        settings.set("PROXY_ENABLED", True)
+        settings.set("PROXY_API_URL", proxy_url)
+        settings.set("PROXY_REFRESH_INTERVAL", 60)
+        settings.set("PROXY_POOL_SIZE", 5)
+    else:
+        settings.set("PROXY_ENABLED", False)
+        
+    return settings
+
+
+async def test_aiohttp_with_proxy(proxy_url, target_url):
+    """测试aiohttp下载器与代理的适配性"""
+    print(f"\n=== 测试 aiohttp 下载器与代理 ===")
+    print(f"代理URL: {proxy_url}")
+    print(f"目标URL: {target_url}")
+    
+    try:
+        # 创建设置
+        settings = create_test_settings(proxy_url)
+        crawler = MockCrawler(settings)
+        
+        # 创建下载器
+        downloader = AioHttpDownloader(crawler)
+        downloader.open()
+        
+        # 创建代理中间件
+        proxy_middleware = ProxyMiddleware(settings, "DEBUG")
+        
+        # 创建请求
+        request = Request(url=target_url)
+        
+        # 创建模拟爬虫
+        spider = MockSpider(crawler)
+        
+        # 通过代理中间件处理请求
+        await proxy_middleware.process_request(request, spider)
+        
+        if request.proxy:
+            print(f"✓ 代理已成功设置: {request.proxy}")
+        else:
+            print("⚠ 代理未设置")
+            
+        # 尝试下载
+        try:
+            response = await downloader.download(request)
+            if response and response.status_code:
+                print(f"✓ 下载成功，状态码: {response.status_code}")
+                # 只检查状态码，避免编码问题
+                return True
+            else:
+                print("✗ 下载失败，响应为空")
+                return False
+        except Exception as e:
+            print(f"✗ 下载过程中出错: {e}")
+            return False
+            
+    except Exception as e:
+        print(f"✗ 测试aiohttp时出错: {e}")
+        return False
+    finally:
+        # 清理资源
+        try:
+            await downloader.close()
+            await proxy_middleware.close()
+        except:
+            pass
+
+
+async def test_httpx_with_proxy_async(proxy_url, target_url):
+    """测试httpx下载器与代理的适配性"""
+    print(f"\n=== 测试 httpx 下载器与代理 ===")
+    print(f"代理URL: {proxy_url}")
+    print(f"目标URL: {target_url}")
+    
+    try:
+        # 创建设置
+        settings = create_test_settings(proxy_url)
+        crawler = MockCrawler(settings)
+        
+        # 创建下载器
+        downloader = HttpXDownloader(crawler)
+        downloader.open()
+        
+        # 创建代理中间件
+        proxy_middleware = ProxyMiddleware(settings, "DEBUG")
+        
+        # 创建请求
+        request = Request(url=target_url)
+        
+        # 创建模拟爬虫
+        spider = MockSpider(crawler)
+        
+        # 通过代理中间件处理请求
+        await proxy_middleware.process_request(request, spider)
+        
+        if request.proxy:
+            print(f"✓ 代理已成功设置: {request.proxy}")
+        else:
+            print("⚠ 代理未设置")
+            
+        # 尝试下载
+        try:
+            response = await downloader.download(request)
+            if response and response.status_code:
+                print(f"✓ 下载成功，状态码: {response.status_code}")
+                # 只检查状态码，避免编码问题
+                return True
+            else:
+                print("✗ 下载失败，响应为空")
+                return False
+        except Exception as e:
+            print(f"✗ 下载过程中出错: {e}")
+            return False
+            
+    except Exception as e:
+        print(f"✗ 测试httpx时出错: {e}")
+        return False
+    finally:
+        # 清理资源
+        try:
+            await downloader.close()
+            await proxy_middleware.close()
+        except:
+            pass
+
+
+async def test_curl_cffi_with_proxy_async(proxy_url, target_url):
+    """测试curl-cffi下载器与代理的适配性"""
+    print(f"\n=== 测试 curl-cffi 下载器与代理 ===")
+    print(f"代理URL: {proxy_url}")
+    print(f"目标URL: {target_url}")
+    
+    try:
+        # 创建设置
+        settings = create_test_settings(proxy_url)
+        crawler = MockCrawler(settings)
+        
+        # 创建下载器
+        downloader = CurlCffiDownloader(crawler)
+        downloader.open()
+        
+        # 创建代理中间件
+        proxy_middleware = ProxyMiddleware(settings, "DEBUG")
+        
+        # 创建请求
+        request = Request(url=target_url)
+        
+        # 创建模拟爬虫
+        spider = MockSpider(crawler)
+        
+        # 通过代理中间件处理请求
+        await proxy_middleware.process_request(request, spider)
+        
+        if request.proxy:
+            print(f"✓ 代理已成功设置: {request.proxy}")
+        else:
+            print("⚠ 代理未设置")
+            
+        # 尝试下载
+        try:
+            response = await downloader.download(request)
+            if response and response.status_code:
+                print(f"✓ 下载成功，状态码: {response.status_code}")
+                # 只检查状态码，避免编码问题
+                return True
+            else:
+                print("✗ 下载失败，响应为空")
+                return False
+        except Exception as e:
+            print(f"✗ 下载过程中出错: {e}")
+            return False
+            
+    except Exception as e:
+        print(f"✗ 测试curl-cffi时出错: {e}")
+        return False
+    finally:
+        # 清理资源
+        try:
+            await downloader.close()
+            await proxy_middleware.close()
+        except:
+            pass
+
+
+async def main():
+    """主测试函数"""
+    print("开始测试代理中间件与三个下载器的兼容性...")
+    
+    # 使用测试代理URL（这里使用一个公开的测试代理）
+    # 注意：在实际使用中，您需要替换为有效的代理URL
+    test_proxy_url = "http://test.proxy.api:8080/proxy/getitem/"
+    test_target_url = "https://httpbin.org/ip"  # 一个返回IP信息的测试站点
+    
+    print(f"测试代理API: {test_proxy_url}")
+    print(f"测试目标URL: {test_target_url}")
+    
+    # 测试aiohttp下载器
+    aiohttp_result = await test_aiohttp_with_proxy(test_proxy_url, test_target_url)
+    
+    # 测试httpx下载器
+    httpx_result = await test_httpx_with_proxy_async(test_proxy_url, test_target_url)
+    
+    # 测试curl-cffi下载器
+    curl_cffi_result = await test_curl_cffi_with_proxy_async(test_proxy_url, test_target_url)
+    
+    # 汇总结果
+    print("\n" + "="*50)
+    print("测试结果汇总:")
+    print(f"aiohttp 下载器: {'✓ 通过' if aiohttp_result else '✗ 失败'}")
+    print(f"httpx 下载器: {'✓ 通过' if httpx_result else '✗ 失败'}")
+    print(f"curl-cffi 下载器: {'✓ 通过' if curl_cffi_result else '✗ 失败'}")
+    
+    overall_result = all([aiohttp_result, httpx_result, curl_cffi_result])
+    print(f"\n总体结果: {'✓ 所有下载器都适配代理中间件' if overall_result else '✗ 部分下载器不兼容'}")
+    
+    return overall_result
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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())