crawlo 1.4.6__py3-none-any.whl → 1.4.7__py3-none-any.whl

tests/ofweek_scrapy/ofweek_scrapy/spiders/ofweek_spider.py

@@ -1,162 +0,0 @@
-import scrapy
-from urllib.parse import urljoin
-
-class OfweekSpider(scrapy.Spider):
-    name = 'ofweek'
-    allowed_domains = ['ee.ofweek.com']
-    
-    def start_requests(self):
-        """生成初始请求"""
-        headers = {
-            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
-            "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
-            "Cache-Control": "no-cache",
-            "Connection": "keep-alive",
-            "Pragma": "no-cache",
-            "Referer": "https://ee.ofweek.com/CATList-2800-8100-ee-2.html",
-            "Sec-Fetch-Dest": "document",
-            "Sec-Fetch-Mode": "navigate",
-            "Sec-Fetch-Site": "same-origin",
-            "Sec-Fetch-User": "?1",
-            "Upgrade-Insecure-Requests": "1",
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36",
-        }
-        cookies = {
-            "__utmz": "57425525.1730117117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)",
-            "Hm_lvt_abe9900db162c6d089cdbfd107db0f03": "1739244841",
-            "Hm_lvt_af50e2fc51af73da7720fb324b88a975": "1740100727",
-            "JSESSIONID": "FEA96D3B5FC31350B2285E711BF2A541",
-            "Hm_lvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477622",
-            "HMACCOUNT": "08DF0D235A291EAA",
-            "__utma": "57425525.2080994505.1730117117.1747970718.1757477622.50",
-            "__utmc": "57425525",
-            "__utmt": "1",
-            "__utmb": "57425525.2.10.1757477622",
-            "Hm_lpvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477628",
-            "index_burying_point": "c64d6c31e69d560efe319cc9f8be279f"
-        }
-
-        # 使用与Crawlo相同的页数进行公平测试
-        max_page = 50  # 原来是1851，现在改为50页进行测试
-        start_urls = []
-        for page in range(1, max_page + 1):
-            url = f'https://ee.ofweek.com/CATList-2800-8100-ee-{page}.html'
-            start_urls.append(url)
-
-        self.logger.info(f"生成了 {len(start_urls)} 个起始URL")
-
-        # 生成请求
-        for url in start_urls:
-            self.logger.info(f"添加起始URL: {url}")
-            try:
-                yield scrapy.Request(
-                    url=url,
-                    callback=self.parse,
-                    headers=headers,
-                    cookies=cookies,
-                    dont_filter=True
-                )
-            except Exception as e:
-                self.logger.error(f"创建请求失败: {url}, 错误: {e}")
-        
-        self.logger.info("start_requests方法执行完成")
-
-    def parse(self, response):
-        """解析列表页"""
-        self.logger.info(f'正在解析页面: {response.url}')
-
-        # 检查响应状态
-        if response.status != 200:
-            self.logger.warning(f"页面返回非200状态码: {response.status}, URL: {response.url}")
-            return
-
-        # ================== 数据提取 ==================
-        try:
-            rows = response.xpath('//div[@class="main_left"]/div[@class="list_model"]/div[@class="model_right model_right2"]')
-            self.logger.info(f"在页面 {response.url} 中找到 {len(rows)} 个条目")
-
-            for row in rows:
-                try:
-                    # 提取URL和标题
-                    url = row.xpath('./h3/a/@href').extract_first()
-                    title = row.xpath('./h3/a/text()').extract_first()
-
-                    # 容错处理
-                    if not url:
-                        self.logger.warning(f"条目缺少URL，跳过")
-                        continue
-
-                    if not title:
-                        self.logger.warning(f"条目缺少标题，跳过")
-                        continue
-
-                    # 确保 URL 是绝对路径
-                    absolute_url = response.urljoin(url)
-
-                    # 验证URL格式
-                    if not absolute_url.startswith(('http://', 'https://')):
-                        self.logger.warning(f"无效的URL格式，跳过: {absolute_url}")
-                        continue
-
-                    self.logger.info(f"提取到详情页链接: {absolute_url}, 标题: {title}")
-                    yield scrapy.Request(
-                        url=absolute_url,
-                        meta={
-                            "title": title.strip() if title else '',
-                            "parent_url": response.url
-                        },
-                        callback=self.parse_detail
-                    )
-                except Exception as e:
-                    self.logger.error(f"处理条目时出错: {e}")
-                    continue
-
-        except Exception as e:
-            self.logger.error(f"解析页面 {response.url} 时出错: {e}")
-
-    def parse_detail(self, response):
-        """解析详情页"""
-        self.logger.info(f'正在解析详情页: {response.url}')
-
-        # 检查响应状态
-        if response.status != 200:
-            self.logger.warning(f"详情页返回非200状态码: {response.status}, URL: {response.url}")
-            return
-
-        try:
-            title = response.meta.get('title', '')
-
-            # 提取内容，增加容错处理
-            content_elements = response.xpath('//div[@class="TRS_Editor"]|//*[@id="articleC"]')
-            if content_elements:
-                content = content_elements.xpath('.//text()').extract()
-                content = '\n'.join([text.strip() for text in content if text.strip()])
-            else:
-                content = ''
-                self.logger.warning(f"未找到内容区域: {response.url}")
-
-            # 提取发布时间
-            publish_time = response.xpath('//div[@class="time fl"]/text()').extract_first()
-            if publish_time:
-                publish_time = publish_time.strip()
-
-            source = response.xpath('//div[@class="source-name"]/text()').extract_first()
-
-            # 创建数据项
-            item = {
-                'title': title.strip() if title else '',
-                'publish_time': publish_time if publish_time else '',
-                'url': response.url,
-                'source': source if source else '',
-                'content': content
-            }
-
-            # 验证必要字段
-            if not item['title']:
-                self.logger.warning(f"详情页缺少标题: {response.url}")
-
-            self.logger.info(f"成功提取详情页数据: {item['title']}")
-            yield item
-
-        except Exception as e:
-            self.logger.error(f"解析详情页 {response.url} 时出错: {e}")

tests/test_authenticated_proxy.py

@@ -1,142 +0,0 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-测试带认证代理的功能
-"""
-
-import asyncio
-import aiohttp
-import httpx
-from crawlo.network.request import Request
-from crawlo.tools import AuthenticatedProxy
-
-
-async def test_proxy_with_aiohttp():
-    """测试AioHttp与认证代理"""
-    print("=== 测试AioHttp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()}")
-    
-    # 使用aiohttp直接测试
-    try:
-        auth = proxy.get_auth_credentials()
-        if auth:
-            basic_auth = aiohttp.BasicAuth(auth['username'], auth['password'])
-        else:
-            basic_auth = None
-            
-        async with aiohttp.ClientSession() as session:
-            async with session.get(
-                "https://httpbin.org/ip",
-                proxy=proxy.clean_url,
-                proxy_auth=basic_auth
-            ) as response:
-                print(f"AioHttp测试成功!")
-                print(f"状态码: {response.status}")
-                content = await response.text()
-                print(f"响应内容: {content[:200]}...")
-                
-    except Exception as e:
-        print(f"AioHttp测试失败: {e}")
-        import traceback
-        traceback.print_exc()
-
-
-def test_proxy_with_httpx():
-    """测试HttpX与认证代理"""
-    print("\n=== 测试HttpX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"
-    }
-    
-    # 使用httpx直接测试
-    try:
-        # HttpX可以直接使用带认证的URL作为proxy参数
-        proxy_url = proxy_config["http"]
-        
-        with httpx.Client(proxy=proxy_url) as client:
-            response = client.get("https://httpbin.org/ip")
-            print(f"HttpX测试成功!")
-            print(f"状态码: {response.status_code}")
-            print(f"响应内容: {response.text[:200]}...")
-                
-    except Exception as e:
-        print(f"HttpX测试失败: {e}")
-        import traceback
-        traceback.print_exc()
-
-
-async def test_proxy_with_curl_cffi():
-    """测试CurlCffi与认证代理"""
-    print("\n=== 测试CurlCffi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"代理字典: {proxy.proxy_dict}")
-    print(f"认证头: {proxy.get_auth_header()}")
-    
-    # 使用curl-cffi直接测试
-    try:
-        from curl_cffi import requests as curl_requests
-        
-        # 设置代理和认证头
-        proxies = proxy.proxy_dict
-        headers = {}
-        auth_header = proxy.get_auth_header()
-        if auth_header:
-            headers["Proxy-Authorization"] = auth_header
-            
-        response = curl_requests.get(
-            "https://httpbin.org/ip",
-            proxies=proxies,
-            headers=headers
-        )
-        
-        print(f"CurlCffi测试成功!")
-        print(f"状态码: {response.status_code}")
-        print(f"响应内容: {response.text[:200]}...")
-                
-    except Exception as e:
-        print(f"CurlCffi测试失败: {e}")
-        import traceback
-        traceback.print_exc()
-
-
-async def main():
-    """主测试函数"""
-    print("开始测试带认证代理的功能...\n")
-    
-    # 测试各个库
-    await test_proxy_with_aiohttp()
-    test_proxy_with_httpx()
-    await test_proxy_with_curl_cffi()
-    
-    print("\n所有测试完成!")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

tests/test_comprehensive.py

@@ -1,147 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-综合测试
-验证所有改进的集成效果
-"""
-import sys
-import os
-import asyncio
-import unittest
-from unittest.mock import patch, MagicMock
-
-# 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.env_config import get_env_var, get_redis_config, get_runtime_config
-from crawlo.utils.error_handler import ErrorHandler, handle_exception
-from crawlo.core.engine import Engine
-from crawlo.settings.setting_manager import SettingManager
-from crawlo.settings import default_settings
-from crawlo.queue.queue_manager import QueueManager, QueueConfig, QueueType
-
-
-class TestComprehensiveIntegration(unittest.TestCase):
-    """综合集成测试"""
-
-    def setUp(self):
-        """测试前准备"""
-        # 设置测试环境变量
-        self.test_env = {
-            'PROJECT_NAME': 'test_project',
-            'CONCURRENCY': '4',
-            'REDIS_HOST': 'localhost',
-            'REDIS_PORT': '6379'
-        }
-        self.original_env = {}
-        for key, value in self.test_env.items():
-            self.original_env[key] = os.environ.get(key)
-            os.environ[key] = value
-
-    def tearDown(self):
-        """测试后清理"""
-        # 恢复原始环境变量
-        for key, value in self.original_env.items():
-            if value is None:
-                os.environ.pop(key, None)
-            else:
-                os.environ[key] = value
-
-    def test_env_config_integration(self):
-        """测试环境变量配置集成"""
-        # 验证环境变量工具正常工作
-        project_name = get_env_var('PROJECT_NAME', 'default', str)
-        self.assertEqual(project_name, 'test_project')
-        
-        concurrency = get_env_var('CONCURRENCY', 1, int)
-        self.assertEqual(concurrency, 4)
-        
-        # 验证Redis配置工具
-        redis_config = get_redis_config()
-        self.assertEqual(redis_config['REDIS_HOST'], 'localhost')
-        self.assertEqual(redis_config['REDIS_PORT'], 6379)
-
-    def test_error_handler_integration(self):
-        """测试错误处理集成"""
-        # 验证错误处理模块正常工作
-        error_handler = ErrorHandler("test")
-        
-        # 测试错误处理
-        try:
-            error_handler.handle_error(ValueError("Test error"), raise_error=False)
-        except Exception:
-            self.fail("Error handler should not raise exception when raise_error=False")
-        
-        # 测试安全调用
-        result = error_handler.safe_call(lambda x: x*2, 5, default_return=0)
-        self.assertEqual(result, 10)
-        
-        # 测试装饰器
-        @handle_exception(raise_error=False)
-        def failing_function():
-            raise RuntimeError("Test")
-        
-        try:
-            failing_function()
-        except Exception:
-            self.fail("Decorated function should not raise exception")
-
-    def test_settings_integration(self):
-        """测试设置管理器集成"""
-        # 重新加载默认设置以获取环境变量
-        import importlib
-        import crawlo.settings.default_settings
-        importlib.reload(crawlo.settings.default_settings)
-        
-        # 创建设置管理器
-        settings = SettingManager()
-        settings.set_settings(crawlo.settings.default_settings)
-        
-        # 验证设置正确加载
-        self.assertEqual(settings.get('PROJECT_NAME'), 'test_project')
-        self.assertEqual(settings.get_int('CONCURRENCY'), 4)
-        self.assertEqual(settings.get('REDIS_HOST'), 'localhost')
-
-    def test_queue_manager_config(self):
-        """测试队列管理器配置"""
-        # 重新加载默认设置
-        import importlib
-        import crawlo.settings.default_settings
-        importlib.reload(crawlo.settings.default_settings)
-        
-        # 创建设置管理器
-        settings = SettingManager()
-        settings.set_settings(crawlo.settings.default_settings)
-        
-        # 从设置创建队列配置
-        queue_config = QueueConfig.from_settings(settings)
-        
-        # 验证配置正确
-        self.assertEqual(queue_config.queue_type, QueueType.AUTO)
-        self.assertIn('test_project', queue_config.queue_name)
-
-    async def test_async_components(self):
-        """测试异步组件"""
-        # 测试异步错误处理装饰器
-        @handle_exception(raise_error=False)
-        async def async_failing_function():
-            raise RuntimeError("Async test")
-        
-        try:
-            await async_failing_function()
-        except Exception:
-            self.fail("Async decorated function should not raise exception")
-
-
-if __name__ == '__main__':
-    # 运行同步测试
-    unittest.main(exit=False)
-    
-    # 运行异步测试
-    async def run_async_tests():
-        test_instance = TestComprehensiveIntegration()
-        test_instance.setUp()
-        await test_instance.test_async_components()
-        test_instance.tearDown()
-    
-    asyncio.run(run_async_tests())

tests/test_dynamic_downloaders_proxy.py

@@ -1,125 +0,0 @@
-#!/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

@@ -1,93 +0,0 @@
-#!/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())