crawlo 1.1.4__py3-none-any.whl → 1.1.6__py3-none-any.whl

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()

tests/test_dynamic_proxy_real.py

@@ -0,0 +1,110 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+实际测试动态下载器（Playwright）通过代理访问网站
+"""
+
+import asyncio
+from crawlo.spider import Spider
+from crawlo.network.request import Request
+from crawlo.tools import AuthenticatedProxy
+
+
+class ProxyTestSpider(Spider):
+    """代理测试爬虫"""
+    name = "proxy_test_spider"  # 添加name属性
+    
+    # 自定义配置
+    custom_settings = {
+        "DOWNLOADER_TYPE": "playwright",
+        "PLAYWRIGHT_BROWSER_TYPE": "chromium",
+        "PLAYWRIGHT_HEADLESS": True,
+        # 配置带认证的代理
+        "PLAYWRIGHT_PROXY": {
+            "server": "http://182.201.243.186:58111",
+            "username": "dwe20241014",
+            "password": "Dwe0101014"
+        }
+    }
+    
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        print("代理测试爬虫初始化完成")
+        print(f"代理配置: {self.custom_settings.get('PLAYWRIGHT_PROXY')}")
+
+    def start_requests(self):
+        """开始请求"""
+        urls = [
+            "https://httpbin.org/ip",  # 查看IP地址
+            "https://httpbin.org/headers",  # 查看请求头
+        ]
+        
+        for url in urls:
+            request = Request(url, callback=self.parse)
+            yield request
+
+    def parse(self, response):
+        """解析响应"""
+        print(f"\n=== 响应信息 ===")
+        print(f"URL: {response.url}")
+        print(f"状态码: {response.status_code}")
+        print(f"响应内容: {response.text[:500]}")
+        
+        # 保存响应内容
+        filename = response.url.split("/")[-1].replace("?", "_").replace("&", "_")
+        with open(f"proxy_test_{filename}.html", "w", encoding="utf-8") as f:
+            f.write(response.text)
+        print(f"响应已保存到 proxy_test_{filename}.html")
+        
+        # 返回一个简单的item
+        yield {"url": response.url, "status": response.status_code}
+
+
+# 异步运行函数
+async def run_spider():
+    """运行爬虫"""
+    print("开始测试动态下载器通过代理访问网站...")
+    
+    # 创建爬虫实例
+    spider = ProxyTestSpider()
+    
+    # 创建一个简单的crawler模拟器
+    class MockCrawler:
+        def __init__(self):
+            from crawlo.settings.setting_manager import SettingManager
+            self.settings = SettingManager()
+            # 应用爬虫的自定义设置
+            if hasattr(spider, 'custom_settings'):
+                for key, value in spider.custom_settings.items():
+                    self.settings.set(key, value)
+    
+    crawler = MockCrawler()
+    
+    # 创建爬虫实例并绑定crawler
+    spider_instance = spider.create_instance(crawler)
+    
+    # 执行初始请求
+    requests = list(spider_instance.start_requests())
+    print(f"生成了 {len(requests)} 个请求")
+    
+    # 使用Playwright下载器处理请求
+    try:
+        from crawlo.downloader import PlaywrightDownloader
+        downloader = PlaywrightDownloader(crawler)
+        await downloader.download(requests[0])  # 测试第一个请求
+        print("Playwright下载器测试成功!")
+    except Exception as e:
+        print(f"Playwright下载器测试失败: {e}")
+        import traceback
+        traceback.print_exc()
+    
+    print("\n测试完成!")
+
+
+async def main():
+    """主函数"""
+    await run_spider()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())