crawlo 1.4.7__py3-none-any.whl → 1.4.8__py3-none-any.whl

tests/test_proxy_providers.py

@@ -1,57 +1,57 @@
-# tests/test_proxy_providers.py
-import pytest
-import pytest
-import respx
-from httpx import Response
-from crawlo.proxy.providers import StaticProxyProvider, FileProxyProvider, APIProxyProvider
-import tempfile
-import os
-
-
-@pytest.mark.asyncio
-async def test_static_provider():
-    """测试静态代理提供者"""
-    provider = StaticProxyProvider(['http://1.1.1.1:8080', 'http://2.2.2.2:8080'])
-    proxies = await provider.fetch_proxies()
-    assert len(proxies) == 2
-    assert 'http://1.1.1.1:8080' in proxies
-    assert 'http://2.2.2.2:8080' in proxies
-
-
-@pytest.mark.asyncio
-async def test_file_provider():
-    """测试文件代理提供者"""
-    with tempfile.NamedTemporaryFile(mode='w', delete=False) as f:
-        f.write("http://a.com:8080\nhttp://b.com:8080\n")
-        temp_path = f.name
-    try:
-        provider = FileProxyProvider(temp_path)
-        proxies = await provider.fetch_proxies()
-        assert len(proxies) == 2
-        assert 'http://a.com:8080' in proxies
-        assert 'http://b.com:8080' in proxies
-    finally:
-        os.unlink(temp_path)
-
-
-@pytest.mark.asyncio
-@respx.mock
-async def test_api_provider():
-    """使用 respx 拦截 HTTP 请求，更简洁可靠"""
-    # 拦截 GET 请求
-    respx.get("https://api.example.com").mock(
-        return_value=Response(
-            200,
-            json=[
-                {"ip": "1.1.1.1", "port": 8080},
-                {"ip": "2.2.2.2", "port": 8080}
-            ]
-        )
-    )
-
-    provider = APIProxyProvider(url="https://api.example.com")
-    proxies = await provider.fetch_proxies()
-
-    assert len(proxies) == 2
-    assert "http://1.1.1.1:8080" in proxies
+# tests/test_proxy_providers.py
+import pytest
+import pytest
+import respx
+from httpx import Response
+from crawlo.proxy.providers import StaticProxyProvider, FileProxyProvider, APIProxyProvider
+import tempfile
+import os
+
+
+@pytest.mark.asyncio
+async def test_static_provider():
+    """测试静态代理提供者"""
+    provider = StaticProxyProvider(['http://1.1.1.1:8080', 'http://2.2.2.2:8080'])
+    proxies = await provider.fetch_proxies()
+    assert len(proxies) == 2
+    assert 'http://1.1.1.1:8080' in proxies
+    assert 'http://2.2.2.2:8080' in proxies
+
+
+@pytest.mark.asyncio
+async def test_file_provider():
+    """测试文件代理提供者"""
+    with tempfile.NamedTemporaryFile(mode='w', delete=False) as f:
+        f.write("http://a.com:8080\nhttp://b.com:8080\n")
+        temp_path = f.name
+    try:
+        provider = FileProxyProvider(temp_path)
+        proxies = await provider.fetch_proxies()
+        assert len(proxies) == 2
+        assert 'http://a.com:8080' in proxies
+        assert 'http://b.com:8080' in proxies
+    finally:
+        os.unlink(temp_path)
+
+
+@pytest.mark.asyncio
+@respx.mock
+async def test_api_provider():
+    """使用 respx 拦截 HTTP 请求，更简洁可靠"""
+    # 拦截 GET 请求
+    respx.get("https://api.example.com").mock(
+        return_value=Response(
+            200,
+            json=[
+                {"ip": "1.1.1.1", "port": 8080},
+                {"ip": "2.2.2.2", "port": 8080}
+            ]
+        )
+    )
+
+    provider = APIProxyProvider(url="https://api.example.com")
+    proxies = await provider.fetch_proxies()
+
+    assert len(proxies) == 2
+    assert "http://1.1.1.1:8080" in proxies
     assert "http://2.2.2.2:8080" in proxies

tests/test_proxy_stats.py

@@ -1,20 +1,20 @@
-# tests/test_proxy_stats.py
-from crawlo.proxy.stats import ProxyStats
-
-
-def test_proxy_stats():
-    """测试代理统计功能"""
-    stats = ProxyStats()
-    url = 'http://proxy1:8080'
-
-    stats.record(url, 'success')
-    stats.record(url, 'success')
-    stats.record(url, 'failure')
-
-    assert stats.get(url)['success'] == 2
-    assert stats.get(url)['failure'] == 1
-    assert stats.get(url)['total'] == 3
-
-    all_data = stats.all()
-    assert url in all_data
+# tests/test_proxy_stats.py
+from crawlo.proxy.stats import ProxyStats
+
+
+def test_proxy_stats():
+    """测试代理统计功能"""
+    stats = ProxyStats()
+    url = 'http://proxy1:8080'
+
+    stats.record(url, 'success')
+    stats.record(url, 'success')
+    stats.record(url, 'failure')
+
+    assert stats.get(url)['success'] == 2
+    assert stats.get(url)['failure'] == 1
+    assert stats.get(url)['total'] == 3
+
+    all_data = stats.all()
+    assert url in all_data
     assert all_data[url]['success'] == 2

tests/test_proxy_strategies.py

@@ -1,60 +1,60 @@
-# tests/test_proxy_strategies.py
-import pytest
-from crawlo import Request
-from crawlo.proxy.strategies import STRATEGIES
-
-
-@pytest.fixture
-def mock_proxies():
-    """提供测试用的代理列表"""
-    return [
-        {'url': 'http://p1:8080'},
-        {'url': 'http://p2:8080'},
-        {'url': 'http://p3:8080'},
-    ]
-
-
-@pytest.fixture
-def mock_stats():
-    """提供测试用的统计信息"""
-    return {
-        'http://p1:8080': {'total': 10},
-        'http://p2:8080': {'total': 5},
-        'http://p3:8080': {'total': 1},
-    }
-
-
-@pytest.fixture
-def mock_request():
-    """提供测试用的请求对象"""
-    return Request("https://example.com")
-
-
-def test_random_strategy(mock_proxies, mock_request, mock_stats):
-    """测试随机策略"""
-    strategy = STRATEGIES['random']
-    chosen = strategy(mock_proxies, mock_request, mock_stats)
-    assert chosen in [p['url'] for p in mock_proxies]
-
-
-def test_least_used_strategy(mock_proxies, mock_request, mock_stats):
-    """测试最少使用策略"""
-    strategy = STRATEGIES['least_used']
-    chosen = strategy(mock_proxies, mock_request, mock_stats)
-    assert chosen == 'http://p3:8080'  # total=1
-
-
-def test_domain_rule_strategy(mock_proxies, mock_request, mock_stats):
-    """测试域名规则策略"""
-    from crawlo.proxy.strategies.domain_rule import domain_rule_strategy
-    request = Request("https://taobao.com/item/123")
-    rules = {'taobao.com': 'http://special:8080'}
-
-    # Monkey patch 确保有回退策略
-    old_strategy = STRATEGIES['least_used']
-    try:
-        STRATEGIES['least_used'] = lambda p, r, s: 'http://fallback:8080'
-        chosen = domain_rule_strategy(mock_proxies, request, mock_stats, rules)
-        assert chosen == 'http://special:8080'
-    finally:
+# tests/test_proxy_strategies.py
+import pytest
+from crawlo import Request
+from crawlo.proxy.strategies import STRATEGIES
+
+
+@pytest.fixture
+def mock_proxies():
+    """提供测试用的代理列表"""
+    return [
+        {'url': 'http://p1:8080'},
+        {'url': 'http://p2:8080'},
+        {'url': 'http://p3:8080'},
+    ]
+
+
+@pytest.fixture
+def mock_stats():
+    """提供测试用的统计信息"""
+    return {
+        'http://p1:8080': {'total': 10},
+        'http://p2:8080': {'total': 5},
+        'http://p3:8080': {'total': 1},
+    }
+
+
+@pytest.fixture
+def mock_request():
+    """提供测试用的请求对象"""
+    return Request("https://example.com")
+
+
+def test_random_strategy(mock_proxies, mock_request, mock_stats):
+    """测试随机策略"""
+    strategy = STRATEGIES['random']
+    chosen = strategy(mock_proxies, mock_request, mock_stats)
+    assert chosen in [p['url'] for p in mock_proxies]
+
+
+def test_least_used_strategy(mock_proxies, mock_request, mock_stats):
+    """测试最少使用策略"""
+    strategy = STRATEGIES['least_used']
+    chosen = strategy(mock_proxies, mock_request, mock_stats)
+    assert chosen == 'http://p3:8080'  # total=1
+
+
+def test_domain_rule_strategy(mock_proxies, mock_request, mock_stats):
+    """测试域名规则策略"""
+    from crawlo.proxy.strategies.domain_rule import domain_rule_strategy
+    request = Request("https://taobao.com/item/123")
+    rules = {'taobao.com': 'http://special:8080'}
+
+    # Monkey patch 确保有回退策略
+    old_strategy = STRATEGIES['least_used']
+    try:
+        STRATEGIES['least_used'] = lambda p, r, s: 'http://fallback:8080'
+        chosen = domain_rule_strategy(mock_proxies, request, mock_stats, rules)
+        assert chosen == 'http://special:8080'
+    finally:
         STRATEGIES['least_used'] = old_strategy

tests/test_proxy_with_downloader.py

@@ -1,153 +1,153 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""
-代理中间件与下载器配合测试脚本
-测试指定的代理URL与下载器的兼容性
-"""
-
-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.settings.setting_manager import SettingManager
-from crawlo.middleware.proxy import ProxyMiddleware
-from crawlo.downloader.httpx_downloader import HttpXDownloader
-from crawlo.network import Request
-
-
-async def test_proxy_middleware():
-    """测试代理中间件"""
-    print("=== 测试代理中间件 ===")
-    
-    # 创建设置管理器
-    settings_manager = SettingManager()
-    settings = settings_manager  # SettingManager实例本身就是设置对象
-    
-    # 配置代理
-    settings.set('PROXY_API_URL', 'http://proxy-api.example.com/proxy/getitem/')
-    settings.set('LOG_LEVEL', 'DEBUG')
-    
-    # 创建代理中间件
-    proxy_middleware = ProxyMiddleware(settings, "DEBUG")
-    
-    print(f"代理中间件已创建")
-    print(f"模式: {proxy_middleware.mode}")
-    print(f"是否启用: {proxy_middleware.enabled}")
-    
-    if proxy_middleware.enabled and proxy_middleware.mode == "dynamic":
-        # 测试从API获取代理
-        print("\n尝试从API获取代理...")
-        proxy = await proxy_middleware._fetch_proxy_from_api()
-        print(f"获取到的代理: {proxy}")
-        
-    return proxy_middleware
-
-
-async def test_downloader_with_proxy():
-    """测试下载器与代理配合"""
-    print("\n=== 测试下载器与代理配合 ===")
-    
-    # 创建设置管理器
-    settings_manager = SettingManager()
-    settings = settings_manager  # SettingManager实例本身就是设置对象
-    
-    # 配置代理
-    settings.set('PROXY_API_URL', 'http://proxy-api.example.com/proxy/getitem/')
-    settings.set('LOG_LEVEL', 'DEBUG')
-    
-    # 创建代理中间件
-    proxy_middleware = ProxyMiddleware(settings, "DEBUG")
-    
-    # 创建下载器
-    class MockStats:
-        def __init__(self):
-            pass
-            
-        def inc_value(self, key, count=1):
-            pass
-    
-    class MockSubscriber:
-        def __init__(self):
-            pass
-            
-        def subscribe(self, callback, event):
-            pass
-    
-    class MockSpider:
-        def __init__(self):
-            self.name = "test_spider"
-    
-    class MockEngine:
-        def __init__(self):
-            pass
-    
-    class MockCrawler:
-        def __init__(self, settings):
-            self.settings = settings
-            self.spider = MockSpider()  # 添加spider属性
-            self.stats = MockStats()    # 添加stats属性
-            self.subscriber = MockSubscriber()  # 添加subscriber属性
-            self.engine = MockEngine()  # 添加engine属性
-    
-    crawler = MockCrawler(settings)
-    downloader = HttpXDownloader(crawler)
-    downloader.open()
-    
-    # 创建测试请求
-    test_url = "https://httpbin.org/ip"  # 返回客户端IP的测试站点
-    request = Request(url=test_url)
-    
-    # 创建模拟爬虫
-    spider = MockSpider()
-    
-    try:
-        # 通过代理中间件处理请求
-        print("通过代理中间件处理请求...")
-        await proxy_middleware.process_request(request, spider)
-        
-        if request.proxy:
-            print(f"代理已设置: {request.proxy}")
-        else:
-            print("未设置代理")
-            
-        # 使用下载器下载
-        print(f"开始下载: {test_url}")
-        response = await downloader.download(request)
-        
-        if response:
-            print(f"下载成功，状态码: {response.status_code}")
-            print(f"响应内容: {response.text[:200]}...")  # 只显示前200个字符
-        else:
-            print("下载失败，响应为空")
-            
-    except Exception as e:
-        print(f"下载过程中出错: {e}")
-        import traceback
-        traceback.print_exc()
-        
-    finally:
-        # 清理资源
-        try:
-            await downloader.close()
-        except:
-            pass
-
-
-async def main():
-    """主测试函数"""
-    print("开始测试代理中间件与下载器的配合...")
-    
-    # 测试代理中间件
-    await test_proxy_middleware()
-    
-    # 测试下载器与代理配合
-    await test_downloader_with_proxy()
-    
-    print("\n测试完成")
-
-
-if __name__ == "__main__":
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+代理中间件与下载器配合测试脚本
+测试指定的代理URL与下载器的兼容性
+"""
+
+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.settings.setting_manager import SettingManager
+from crawlo.middleware.proxy import ProxyMiddleware
+from crawlo.downloader.httpx_downloader import HttpXDownloader
+from crawlo.network import Request
+
+
+async def test_proxy_middleware():
+    """测试代理中间件"""
+    print("=== 测试代理中间件 ===")
+    
+    # 创建设置管理器
+    settings_manager = SettingManager()
+    settings = settings_manager  # SettingManager实例本身就是设置对象
+    
+    # 配置代理
+    settings.set('PROXY_API_URL', 'http://proxy-api.example.com/proxy/getitem/')
+    settings.set('LOG_LEVEL', 'DEBUG')
+    
+    # 创建代理中间件
+    proxy_middleware = ProxyMiddleware(settings, "DEBUG")
+    
+    print(f"代理中间件已创建")
+    print(f"模式: {proxy_middleware.mode}")
+    print(f"是否启用: {proxy_middleware.enabled}")
+    
+    if proxy_middleware.enabled and proxy_middleware.mode == "dynamic":
+        # 测试从API获取代理
+        print("\n尝试从API获取代理...")
+        proxy = await proxy_middleware._fetch_proxy_from_api()
+        print(f"获取到的代理: {proxy}")
+        
+    return proxy_middleware
+
+
+async def test_downloader_with_proxy():
+    """测试下载器与代理配合"""
+    print("\n=== 测试下载器与代理配合 ===")
+    
+    # 创建设置管理器
+    settings_manager = SettingManager()
+    settings = settings_manager  # SettingManager实例本身就是设置对象
+    
+    # 配置代理
+    settings.set('PROXY_API_URL', 'http://proxy-api.example.com/proxy/getitem/')
+    settings.set('LOG_LEVEL', 'DEBUG')
+    
+    # 创建代理中间件
+    proxy_middleware = ProxyMiddleware(settings, "DEBUG")
+    
+    # 创建下载器
+    class MockStats:
+        def __init__(self):
+            pass
+            
+        def inc_value(self, key, count=1):
+            pass
+    
+    class MockSubscriber:
+        def __init__(self):
+            pass
+            
+        def subscribe(self, callback, event):
+            pass
+    
+    class MockSpider:
+        def __init__(self):
+            self.name = "test_spider"
+    
+    class MockEngine:
+        def __init__(self):
+            pass
+    
+    class MockCrawler:
+        def __init__(self, settings):
+            self.settings = settings
+            self.spider = MockSpider()  # 添加spider属性
+            self.stats = MockStats()    # 添加stats属性
+            self.subscriber = MockSubscriber()  # 添加subscriber属性
+            self.engine = MockEngine()  # 添加engine属性
+    
+    crawler = MockCrawler(settings)
+    downloader = HttpXDownloader(crawler)
+    downloader.open()
+    
+    # 创建测试请求
+    test_url = "https://httpbin.org/ip"  # 返回客户端IP的测试站点
+    request = Request(url=test_url)
+    
+    # 创建模拟爬虫
+    spider = MockSpider()
+    
+    try:
+        # 通过代理中间件处理请求
+        print("通过代理中间件处理请求...")
+        await proxy_middleware.process_request(request, spider)
+        
+        if request.proxy:
+            print(f"代理已设置: {request.proxy}")
+        else:
+            print("未设置代理")
+            
+        # 使用下载器下载
+        print(f"开始下载: {test_url}")
+        response = await downloader.download(request)
+        
+        if response:
+            print(f"下载成功，状态码: {response.status_code}")
+            print(f"响应内容: {response.text[:200]}...")  # 只显示前200个字符
+        else:
+            print("下载失败，响应为空")
+            
+    except Exception as e:
+        print(f"下载过程中出错: {e}")
+        import traceback
+        traceback.print_exc()
+        
+    finally:
+        # 清理资源
+        try:
+            await downloader.close()
+        except:
+            pass
+
+
+async def main():
+    """主测试函数"""
+    print("开始测试代理中间件与下载器的配合...")
+    
+    # 测试代理中间件
+    await test_proxy_middleware()
+    
+    # 测试下载器与代理配合
+    await test_downloader_with_proxy()
+    
+    print("\n测试完成")
+
+
+if __name__ == "__main__":
     asyncio.run(main())

tests/test_queue_empty_check.py

@@ -1,42 +1,42 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-测试队列空检查功能
-"""
-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.queue.pqueue import SpiderPriorityQueue
-
-
-async def test_queue_empty_check():
-    """测试队列空检查功能"""
-    print("🚀 开始测试队列空检查功能...")
-    
-    # 创建队列实例
-    queue = SpiderPriorityQueue()
-    
-    # 检查空队列
-    print(f"空队列大小: {queue.qsize()}")
-    print(f"空队列是否为空: {queue.qsize() == 0}")
-    
-    # 添加一个元素
-    await queue.put((1, "test"))
-    print(f"添加元素后队列大小: {queue.qsize()}")
-    print(f"添加元素后队列是否为空: {queue.qsize() == 0}")
-    
-    # 获取元素
-    item = await queue.get()
-    print(f"获取元素: {item}")
-    print(f"获取元素后队列大小: {queue.qsize()}")
-    print(f"获取元素后队列是否为空: {queue.qsize() == 0}")
-    
-    print("✅ 队列空检查功能测试完成!")
-
-
-if __name__ == '__main__':
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+测试队列空检查功能
+"""
+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.queue.pqueue import SpiderPriorityQueue
+
+
+async def test_queue_empty_check():
+    """测试队列空检查功能"""
+    print("🚀 开始测试队列空检查功能...")
+    
+    # 创建队列实例
+    queue = SpiderPriorityQueue()
+    
+    # 检查空队列
+    print(f"空队列大小: {queue.qsize()}")
+    print(f"空队列是否为空: {queue.qsize() == 0}")
+    
+    # 添加一个元素
+    await queue.put((1, "test"))
+    print(f"添加元素后队列大小: {queue.qsize()}")
+    print(f"添加元素后队列是否为空: {queue.qsize() == 0}")
+    
+    # 获取元素
+    item = await queue.get()
+    print(f"获取元素: {item}")
+    print(f"获取元素后队列大小: {queue.qsize()}")
+    print(f"获取元素后队列是否为空: {queue.qsize() == 0}")
+    
+    print("✅ 队列空检查功能测试完成!")
+
+
+if __name__ == '__main__':
     asyncio.run(test_queue_empty_check())