crawlo 1.4.5__py3-none-any.whl → 1.4.6__py3-none-any.whl

tests/test_proxy_middleware_refactored.py

@@ -126,9 +126,8 @@ class TestProxyMiddlewareRefactored(unittest.TestCase):
     @patch('crawlo.utils.log.get_logger')
     def test_update_proxy_pool_with_parsed_data(self, mock_get_logger):
         """测试使用解析后的代理数据更新代理池"""
-        self.settings.set('PROXY_ENABLED', True)
+        # 不再需要 PROXY_ENABLED，只要配置了 PROXY_API_URL 就会启用
         self.settings.set('PROXY_API_URL', 'http://proxy-api.example.com')
-        self.settings.set('PROXY_POOL_SIZE', 2)
         self.settings.set('LOG_LEVEL', 'INFO')
         
         mock_get_logger.return_value = Mock()
@@ -181,5 +180,29 @@ class TestProxyMiddlewareRefactored(unittest.TestCase):
         healthy_proxy = asyncio.run(middleware._get_healthy_proxy())
         self.assertEqual(healthy_proxy.proxy_str, proxy2.proxy_str)
 
+    def test_proxy_middleware_initialization(self):
+        """测试代理中间件初始化"""
+        # 不再需要 PROXY_ENABLED，只要配置了 PROXY_API_URL 就会启用
+        self.settings.set('PROXY_API_URL', 'http://test-proxy-api.com')
+        middleware = ProxyMiddleware(self.settings, "DEBUG")
+        self.assertIsInstance(middleware, ProxyMiddleware)
+        self.assertTrue(middleware.enabled)
+        self.assertEqual(middleware.api_url, 'http://test-proxy-api.com')
+
+    def test_proxy_middleware_enabled_with_api_url(self):
+        """测试配置了代理API URL时中间件启用"""
+        # 不再需要 PROXY_ENABLED，只要配置了 PROXY_API_URL 就会启用
+        self.settings.set('PROXY_API_URL', 'http://test-proxy-api.com')
+        middleware = ProxyMiddleware(self.settings, "DEBUG")
+        self.assertTrue(middleware.enabled)
+        self.assertEqual(middleware.api_url, 'http://test-proxy-api.com')
+
+    def test_proxy_middleware_disabled_without_api_url(self):
+        """测试未配置代理API URL时中间件禁用"""
+        # 不再需要 PROXY_ENABLED，只要不配置 PROXY_API_URL 就会禁用
+        self.settings.set('PROXY_API_URL', None)
+        middleware = ProxyMiddleware(self.settings, "DEBUG")
+        self.assertFalse(middleware.enabled)
+
 if __name__ == '__main__':
     unittest.main()

tests/test_proxy_only.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+代理中间件测试脚本
+测试指定的代理URL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.settings.setting_manager import SettingManager
+from crawlo.middleware.proxy import ProxyMiddleware
+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}")
+        
+        # 测试代理提取功能
+        if proxy:
+            print(f"代理格式正确: {proxy.startswith('http://') or proxy.startswith('https://')}")
+            
+            # 测试处理请求
+            print("\n测试处理请求...")
+            request = Request(url="https://httpbin.org/ip")
+            
+            class MockSpider:
+                def __init__(self):
+                    self.name = "test_spider"
+            
+            spider = MockSpider()
+            
+            await proxy_middleware.process_request(request, spider)
+            
+            if request.proxy:
+                print(f"请求代理设置成功: {request.proxy}")
+            else:
+                print("请求代理设置失败")
+        else:
+            print("未能从API获取有效代理")
+    else:
+        print("代理中间件未启用或模式不正确")
+        
+    return proxy_middleware
+
+
+async def main():
+    """主测试函数"""
+    print("开始测试代理中间件...")
+    
+    # 测试代理中间件
+    await test_proxy_middleware()
+    
+    print("\n测试完成")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

tests/test_proxy_with_downloader.py

@@ -0,0 +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__":
+    asyncio.run(main())

tests/test_real_scenario_proxy.py

@@ -39,28 +39,28 @@ COOKIES = {
     "Hm_lvt_929f8b362150b1f77b477230541dbbc2": "1758071793",
     "historystock": "600699",
     "spversion": "20130314",
-    "cid": "f9bc812da2c3a7ddf6d5df1fa2d497091758076438",
-    "u_ukey": "A10702B8689642C6BE607730E11E6E4A",
+    "cid": "example_cid_value",
+    "u_ukey": "example_u_ukey_value",
     "u_uver": "1.0.0",
-    "u_dpass": "Qk3U07X7SHGKa0AcRUg1R1DVWbPioD9Eg270bdikvlwWWXexbsXnRsQNt%2B04iXwdHi80LrSsTFH9a%2B6rtRvqGg%3D%3D",
-    "u_did": "E3ED337393E1429DA56E380DD00B3CCD",
+    "u_dpass": "example_u_dpass_value",
+    "u_did": "example_u_did_value",
     "u_ttype": "WEB",
     "user_status": "0",
     "ttype": "WEB",
     "log": "",
-    "Hm_lvt_69929b9dce4c22a060bd22d703b2a280": "1758079404,1758113068,1758157144",
-    "HMACCOUNT": "08DF0D235A291EAA",
-    "Hm_lvt_78c58f01938e4d85eaf619eae71b4ed1": "1758071793,1758113068,1758157144",
-    "user": "MDpteF9lNXRkY3RpdHo6Ok5vbmU6NTAwOjgxNzYyOTAwNDo3LDExMTExMTExMTExLDQwOzQ0LDExLDQwOzYsMSw0MDs1LDEsNDA7MSwxMDEsNDA7MiwxLDQwOzMsMSw0MDs1LDEsNDA7OCwwMDAwMDAwMDAwMDAwMDAwMDAwMDAwMSw0MDsxMDIsMSw0MDoxNjo6OjgwNzYyOTAwNDoxNzU4MTYxNTE0Ojo6MTc1ODA3MjA2MDo2MDQ4MDA6MDoxYTQ0NmFlNDY4M2VmZWY3YmNjYTczY2U3ODZmZTNiODg6ZGVmYXVsdF81OjA%3D",
-    "userid": "807629004",
-    "u_name": "mx_e5tdctitz",
-    "escapename": "mx_e5tdctitz",
-    "ticket": "85eea709becdd924d7eb975351de629e",
-    "utk": "8959c4c6b6f5fb7628864feab15473f4",
-    "sess_tk": "eyJ0eXAiOiJKV1QiLCJhbGciOiJFUzI1NiIsImtpZCI6InNlc3NfdGtfMSIsImJ0eSI6InNlc3NfdGsifQ.eyJqdGkiOiI4ODNiZmU4NmU3M2NhN2NjN2JlZmVmODM0NmFlNDZhNDEiLCJpYXQiOjE3NTgxNjE1MTQsImV4cCI6MTc1ODc2NjMxNCwic3ViIjoiODA3NjI5MDA0IiwiaXNzIjoidXBhc3MuaXdlbmNhaS5jb20iLCJhdWQiOiIyMDIwMTExODUyODg5MDcyIiwiYWN0Ijoib2ZjIiwiY3VocyI6ImIwNTcyZDVjOWNlNDg0MGFlOWYxYTlhYjU3NGZkNjQyYjgzNmExN2E3Y2NhZjk4ZWRiNzI5ZmJkOWFjOGVkYmYifQ.UBNIzxGvQQtXSiIcB_1JJl-EuAc1S9j2LcTLXjwy4ImhDDbh1oJvyRdDUrXdUpwBpIyx5zgYqgt_3FEhY_iayw",
-    "cuc": "ap2eap3gg99g",
-    "Hm_lvt_f79b64788a4e377c608617fba4c736e2": "1758161692",
-    "v": "A1glI4rWhPCQGqh0MvA0ioufKY3vQbzLHqWQT5JJpBNGLfazOlGMW261YNrh",
+    "Hm_lvt_69929b9dce4c22a060bd22d703b2a280": "example_Hm_lvt_value",
+    "HMACCOUNT": "example_HMACCOUNT_value",
+    "Hm_lvt_78c58f01938e4d85eaf619eae71b4ed1": "example_Hm_lvt_value",
+    "user": "example_user_value",
+    "userid": "example_userid_value",
+    "u_name": "example_u_name_value",
+    "escapename": "example_escapename_value",
+    "ticket": "example_ticket_value",
+    "utk": "example_utk_value",
+    "sess_tk": "example_sess_tk_value",
+    "cuc": "example_cuc_value",
+    "Hm_lvt_f79b64788a4e377c608617fba4c736e2": "example_Hm_lvt_value",
+    "v": "example_v_value",
     "Hm_lpvt_78c58f01938e4d85eaf619eae71b4ed1": "1758163145",
     "Hm_lpvt_f79b64788a4e377c608617fba4c736e2": "1758163145",
     "Hm_lpvt_69929b9dce4c22a060bd22d703b2a280": "1758163145"

tests/verify_mysql_warnings.py

@@ -0,0 +1,110 @@
+# -*- coding: utf-8 -*-
+"""
+验证 MySQL 警告是否已解决
+通过模拟实际运行环境来检查
+"""
+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.utils.db_helper import SQLBuilder
+from crawlo.pipelines.mysql_pipeline import BaseMySQLPipeline, AsyncmyMySQLPipeline, AiomysqlMySQLPipeline
+
+
+def verify_mysql_syntax():
+    """验证 MySQL 语法是否正确，不会产生警告"""
+    print("=== 验证 MySQL 语法是否正确 ===\n")
+    
+    # 模拟实际使用的数据
+    test_data = {
+        'title': '新一代OLED屏下光谱颜色传感技术：解锁显示新密码，重塑视觉新体验',
+        'publish_time': '2025-10-09 09:57',
+        'url': 'https://ee.ofweek.com/2025-10/ART-8460-2806-30671544.html',
+        'source': '',
+        'content': '在全球智能手机市场竞争日趋白热化的当下，消费者对手机屏幕显示效果的要求愈发严苛...'
+    }
+    
+    # 模拟 ofweek_standalone 项目的配置
+    update_columns = ('title', 'publish_time')
+    
+    print("1. 检查 SQLBuilder 生成的语法...")
+    sql = SQLBuilder.make_insert(
+        table="news_items",
+        data=test_data,
+        auto_update=False,
+        update_columns=update_columns,
+        insert_ignore=False
+    )
+    
+    print("生成的 SQL:")
+    print(sql[:200] + "..." if len(sql) > 200 else sql)
+    print()
+    
+    # 检查是否包含弃用的 VALUES() 函数用法
+    if "VALUES(`title`)" in sql or "VALUES(`publish_time`)" in sql:
+        print("✗ 发现弃用的 VALUES() 函数用法，会产生警告")
+        return False
+    else:
+        print("✓ 未发现弃用的 VALUES() 函数用法")
+    
+    if "AS `excluded`" in sql and "ON DUPLICATE KEY UPDATE" in sql:
+        print("✓ 正确使用了新的 MySQL 语法")
+    else:
+        print("✗ 未正确使用新的 MySQL 语法")
+        return False
+    
+    # 检查更新子句
+    if "`title`=`excluded`.`title`" in sql and "`publish_time`=`excluded`.`publish_time`" in sql:
+        print("✓ 更新子句正确使用了 excluded 别名")
+    else:
+        print("✗ 更新子句语法不正确")
+        return False
+    
+    print("\n2. 检查批量插入语法...")
+    batch_result = SQLBuilder.make_batch(
+        table="news_items",
+        datas=[test_data, test_data],
+        auto_update=False,
+        update_columns=update_columns
+    )
+    
+    if batch_result:
+        batch_sql, _ = batch_result
+        print("生成的批量 SQL:")
+        print(batch_sql[:200] + "..." if len(batch_sql) > 200 else batch_sql)
+        print()
+        
+        # 检查批量插入语法
+        if "VALUES(`title`)" in batch_sql or "VALUES(`publish_time`)" in batch_sql:
+            print("✗ 批量插入中发现弃用的 VALUES() 函数用法，会产生警告")
+            return False
+        else:
+            print("✓ 批量插入未发现弃用的 VALUES() 函数用法")
+        
+        if "AS `excluded`" in batch_sql and "ON DUPLICATE KEY UPDATE" in batch_sql:
+            print("✓ 批量插入正确使用了新的 MySQL 语法")
+        else:
+            print("✗ 批量插入未正确使用新的 MySQL 语法")
+            return False
+        
+        # 检查批量更新子句
+        if "`title`=`excluded`.`title`" in batch_sql and "`publish_time`=`excluded`.`publish_time`" in batch_sql:
+            print("✓ 批量插入更新子句正确使用了 excluded 别名")
+        else:
+            print("✗ 批量插入更新子句语法不正确")
+            return False
+    
+    print("\n=== 验证完成 ===")
+    print("✓ 所有语法检查通过，应该不会再出现 MySQL 的 VALUES() 函数弃用警告")
+    return True
+
+
+if __name__ == "__main__":
+    success = verify_mysql_syntax()
+    if success:
+        print("\n🎉 MySQL 语法问题已解决！")
+    else:
+        print("\n❌ 仍存在 MySQL 语法问题需要修复")

crawlo/middleware/simple_proxy.py

@@ -1,65 +0,0 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-简化版代理中间件
-提供基础的代理功能，避免过度复杂的实现
-"""
-import random
-from typing import Optional, List
-
-from crawlo import Request, Response
-from crawlo.exceptions import NotConfiguredError
-from crawlo.utils.log import get_logger
-
-
-class SimpleProxyMiddleware:
-    """简化版代理中间件"""
-
-    def __init__(self, settings, log_level):
-        self.logger = get_logger(self.__class__.__name__, log_level)
-
-        # 获取代理列表
-        self.proxies: List[str] = settings.get("PROXY_LIST", [])
-        self.enabled = settings.get_bool("PROXY_ENABLED", False)
-
-        if not self.enabled:
-            self.logger.info("SimpleProxyMiddleware disabled")
-            return
-
-        if not self.proxies:
-            raise NotConfiguredError("PROXY_LIST not configured, SimpleProxyMiddleware disabled")
-
-        self.logger.info(f"SimpleProxyMiddleware enabled with {len(self.proxies)} proxies")
-
-    @classmethod
-    def create_instance(cls, crawler):
-        return cls(settings=crawler.settings, log_level=crawler.settings.get("LOG_LEVEL"))
-
-    async def process_request(self, request: Request, spider) -> Optional[Request]:
-        """为请求分配代理"""
-        if not self.enabled:
-            return None
-
-        if request.proxy:
-            # 请求已指定代理，不覆盖
-            return None
-
-        if self.proxies:
-            # 随机选择一个代理
-            proxy = random.choice(self.proxies)
-            request.proxy = proxy
-            self.logger.debug(f"Assigned proxy {proxy} to {request.url}")
-
-        return None
-
-    def process_response(self, request: Request, response: Response, spider) -> Response:
-        """处理响应"""
-        if request.proxy:
-            self.logger.debug(f"Proxy request successful: {request.proxy} | {request.url}")
-        return response
-
-    def process_exception(self, request: Request, exception: Exception, spider) -> Optional[Request]:
-        """处理异常"""
-        if request.proxy:
-            self.logger.warning(f"Proxy request failed: {request.proxy} | {request.url} | {repr(exception)}")
-        return None