crawlo 1.3.3__py3-none-any.whl → 1.3.5__py3-none-any.whl

tests/cleaners_example.py

@@ -1,161 +1,161 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-Crawlo框架数据清洗工具使用示例
-"""
-from crawlo.tools import (
-    TextCleaner,
-    DataFormatter,
-    remove_html_tags,
-    decode_html_entities,
-    clean_text,
-    extract_numbers,
-    extract_emails,
-    extract_urls,
-    format_number,
-    format_currency,
-    format_phone_number,
-    format_chinese_id_card
-)
-
-
-def demo_text_cleaner():
-    """演示文本清洗工具的使用"""
-    print("=== 文本清洗工具演示 ===\n")
-    
-    # 1. 移除HTML标签
-    print("1. 移除HTML标签:")
-    html_text = "<p>这是一个<b>测试</b>文本</p>"
-    clean_text_result = remove_html_tags(html_text)
-    print(f"  原始文本: {html_text}")
-    print(f"  清洗后: {clean_text_result}")
-    
-    print()
-    
-    # 2. 解码HTML实体
-    print("2. 解码HTML实体:")
-    entity_text = "这是一个&nbsp;<b>测试</b>&amp;文本"
-    decoded_text = decode_html_entities(entity_text)
-    print(f"  原始文本: {entity_text}")
-    print(f"  解码后: {decoded_text}")
-    
-    print()
-    
-    # 3. 移除多余空白字符
-    print("3. 移除多余空白字符:")
-    whitespace_text = "这是   一个\t\t测试\n\n文本"
-    clean_whitespace = TextCleaner.remove_extra_whitespace(whitespace_text)
-    print(f"  原始文本: {repr(whitespace_text)}")
-    print(f"  清洗后: {repr(clean_whitespace)}")
-    
-    print()
-    
-    # 4. 综合清洗
-    print("4. 综合清洗:")
-    complex_text = "<p>这是&nbsp;一个<b>测试</b>&amp;文本&nbsp;&nbsp;</p>"
-    cleaned = clean_text(complex_text)
-    print(f"  原始文本: {complex_text}")
-    print(f"  清洗后: {cleaned}")
-    
-    print()
-    
-    # 5. 提取信息
-    print("5. 提取信息:")
-    info_text = "联系邮箱: test@example.com, 电话: 13812345678, 价格: ¥123.45"
-    numbers = extract_numbers(info_text)
-    emails = extract_emails(info_text)
-    urls = extract_urls(info_text)
-    print(f"  原始文本: {info_text}")
-    print(f"  提取的数字: {numbers}")
-    print(f"  提取的邮箱: {emails}")
-    print(f"  提取的URL: {urls}")
-
-
-def demo_data_formatter():
-    """演示数据格式化工具的使用"""
-    print("\n=== 数据格式化工具演示 ===\n")
-    
-    # 1. 数字格式化
-    print("1. 数字格式化:")
-    number = 1234567.891
-    formatted_num1 = format_number(number, precision=2, thousand_separator=False)
-    formatted_num2 = format_number(number, precision=2, thousand_separator=True)
-    print(f"  原始数字: {number}")
-    print(f"  格式化(无千位分隔符): {formatted_num1}")
-    print(f"  格式化(有千位分隔符): {formatted_num2}")
-    
-    print()
-    
-    # 2. 货币格式化
-    print("2. 货币格式化:")
-    price = 1234.567
-    formatted_currency1 = format_currency(price, "¥", 2)
-    formatted_currency2 = format_currency(price, "$", 2)
-    print(f"  原始价格: {price}")
-    print(f"  人民币格式: {formatted_currency1}")
-    print(f"  美元格式: {formatted_currency2}")
-    
-    print()
-    
-    # 3. 电话号码格式化
-    print("3. 电话号码格式化:")
-    phone = "13812345678"
-    formatted_phone1 = format_phone_number(phone, "+86", "international")
-    formatted_phone2 = format_phone_number(phone, "", "domestic")
-    formatted_phone3 = format_phone_number(phone, "", "plain")
-    print(f"  原始号码: {phone}")
-    print(f"  国际格式: {formatted_phone1}")
-    print(f"  国内格式: {formatted_phone2}")
-    print(f"  纯数字格式: {formatted_phone3}")
-    
-    print()
-    
-    # 4. 身份证号码格式化
-    print("4. 身份证号码格式化:")
-    id_card = "110101199001011234"
-    formatted_id = format_chinese_id_card(id_card)
-    print(f"  原始号码: {id_card}")
-    print(f"  格式化后: {formatted_id}")
-
-
-def demo_in_spider():
-    """演示在爬虫中使用数据清洗工具"""
-    print("\n=== 在爬虫中使用数据清洗工具 ===\n")
-    print("在爬虫项目中，您可以这样使用数据清洗工具:")
-    print("""
-from crawlo import Spider, Request, Item, Field
-from crawlo.tools import clean_text, format_currency, extract_numbers
-
-class ProductItem(Item):
-    name = Field()
-    price = Field()
-    description = Field()
-
-class ProductSpider(Spider):
-    def parse(self, response):
-        # 从网页中提取数据
-        name = response.css('.product-name::text').get()
-        price_text = response.css('.price::text').get()
-        description = response.css('.description::text').get()
-        
-        # 清洗和格式化数据
-        clean_name = clean_text(name) if name else None
-        price_numbers = extract_numbers(price_text) if price_text else []
-        clean_price = format_currency(price_numbers[0]) if price_numbers else None
-        clean_description = clean_text(description) if description else None
-        
-        # 创建数据项
-        item = ProductItem()
-        item['name'] = clean_name
-        item['price'] = clean_price
-        item['description'] = clean_description
-        
-        yield item
-    """)
-
-
-if __name__ == '__main__':
-    # 运行演示
-    demo_text_cleaner()
-    demo_data_formatter()
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+Crawlo框架数据清洗工具使用示例
+"""
+from crawlo.tools import (
+    TextCleaner,
+    DataFormatter,
+    remove_html_tags,
+    decode_html_entities,
+    clean_text,
+    extract_numbers,
+    extract_emails,
+    extract_urls,
+    format_number,
+    format_currency,
+    format_phone_number,
+    format_chinese_id_card
+)
+
+
+def demo_text_cleaner():
+    """演示文本清洗工具的使用"""
+    print("=== 文本清洗工具演示 ===\n")
+    
+    # 1. 移除HTML标签
+    print("1. 移除HTML标签:")
+    html_text = "<p>这是一个<b>测试</b>文本</p>"
+    clean_text_result = remove_html_tags(html_text)
+    print(f"  原始文本: {html_text}")
+    print(f"  清洗后: {clean_text_result}")
+    
+    print()
+    
+    # 2. 解码HTML实体
+    print("2. 解码HTML实体:")
+    entity_text = "这是一个&nbsp;<b>测试</b>&amp;文本"
+    decoded_text = decode_html_entities(entity_text)
+    print(f"  原始文本: {entity_text}")
+    print(f"  解码后: {decoded_text}")
+    
+    print()
+    
+    # 3. 移除多余空白字符
+    print("3. 移除多余空白字符:")
+    whitespace_text = "这是   一个\t\t测试\n\n文本"
+    clean_whitespace = TextCleaner.remove_extra_whitespace(whitespace_text)
+    print(f"  原始文本: {repr(whitespace_text)}")
+    print(f"  清洗后: {repr(clean_whitespace)}")
+    
+    print()
+    
+    # 4. 综合清洗
+    print("4. 综合清洗:")
+    complex_text = "<p>这是&nbsp;一个<b>测试</b>&amp;文本&nbsp;&nbsp;</p>"
+    cleaned = clean_text(complex_text)
+    print(f"  原始文本: {complex_text}")
+    print(f"  清洗后: {cleaned}")
+    
+    print()
+    
+    # 5. 提取信息
+    print("5. 提取信息:")
+    info_text = "联系邮箱: test@example.com, 电话: 13812345678, 价格: ¥123.45"
+    numbers = extract_numbers(info_text)
+    emails = extract_emails(info_text)
+    urls = extract_urls(info_text)
+    print(f"  原始文本: {info_text}")
+    print(f"  提取的数字: {numbers}")
+    print(f"  提取的邮箱: {emails}")
+    print(f"  提取的URL: {urls}")
+
+
+def demo_data_formatter():
+    """演示数据格式化工具的使用"""
+    print("\n=== 数据格式化工具演示 ===\n")
+    
+    # 1. 数字格式化
+    print("1. 数字格式化:")
+    number = 1234567.891
+    formatted_num1 = format_number(number, precision=2, thousand_separator=False)
+    formatted_num2 = format_number(number, precision=2, thousand_separator=True)
+    print(f"  原始数字: {number}")
+    print(f"  格式化(无千位分隔符): {formatted_num1}")
+    print(f"  格式化(有千位分隔符): {formatted_num2}")
+    
+    print()
+    
+    # 2. 货币格式化
+    print("2. 货币格式化:")
+    price = 1234.567
+    formatted_currency1 = format_currency(price, "¥", 2)
+    formatted_currency2 = format_currency(price, "$", 2)
+    print(f"  原始价格: {price}")
+    print(f"  人民币格式: {formatted_currency1}")
+    print(f"  美元格式: {formatted_currency2}")
+    
+    print()
+    
+    # 3. 电话号码格式化
+    print("3. 电话号码格式化:")
+    phone = "13812345678"
+    formatted_phone1 = format_phone_number(phone, "+86", "international")
+    formatted_phone2 = format_phone_number(phone, "", "domestic")
+    formatted_phone3 = format_phone_number(phone, "", "plain")
+    print(f"  原始号码: {phone}")
+    print(f"  国际格式: {formatted_phone1}")
+    print(f"  国内格式: {formatted_phone2}")
+    print(f"  纯数字格式: {formatted_phone3}")
+    
+    print()
+    
+    # 4. 身份证号码格式化
+    print("4. 身份证号码格式化:")
+    id_card = "110101199001011234"
+    formatted_id = format_chinese_id_card(id_card)
+    print(f"  原始号码: {id_card}")
+    print(f"  格式化后: {formatted_id}")
+
+
+def demo_in_spider():
+    """演示在爬虫中使用数据清洗工具"""
+    print("\n=== 在爬虫中使用数据清洗工具 ===\n")
+    print("在爬虫项目中，您可以这样使用数据清洗工具:")
+    print("""
+from crawlo import Spider, Request, Item, Field
+from crawlo.tools import clean_text, format_currency, extract_numbers
+
+class ProductItem(Item):
+    name = Field()
+    price = Field()
+    description = Field()
+
+class ProductSpider(Spider):
+    def parse(self, response):
+        # 从网页中提取数据
+        name = response.css('.product-name::text').get()
+        price_text = response.css('.price::text').get()
+        description = response.css('.description::text').get()
+        
+        # 清洗和格式化数据
+        clean_name = clean_text(name) if name else None
+        price_numbers = extract_numbers(price_text) if price_text else []
+        clean_price = format_currency(price_numbers[0]) if price_numbers else None
+        clean_description = clean_text(description) if description else None
+        
+        # 创建数据项
+        item = ProductItem()
+        item['name'] = clean_name
+        item['price'] = clean_price
+        item['description'] = clean_description
+        
+        yield item
+    """)
+
+
+if __name__ == '__main__':
+    # 运行演示
+    demo_text_cleaner()
+    demo_data_formatter()
     demo_in_spider()

tests/comprehensive_framework_test.py

@@ -0,0 +1,213 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+综合框架测试脚本
+全面测试框架的所有核心功能
+"""
+
+import sys
+import os
+import asyncio
+import time
+
+# 添加项目根目录到Python路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.spider import Spider
+from crawlo import Request
+
+
+class TestSpider(Spider):
+    """测试爬虫"""
+    name = 'framework_test_spider'
+    
+    def start_requests(self):
+        """发起测试请求"""
+        # 生成一些测试请求
+        for i in range(3):
+            yield Request(f'https://httpbin.org/get?page={i}', callback=self.parse)
+    
+    def parse(self, response):
+        """解析响应"""
+        print(f"成功获取响应: {response.url}")
+        print(f"状态码: {response.status_code}")
+        return []
+
+
+async def test_framework_initialization():
+    """测试框架初始化"""
+    print("测试框架初始化...")
+    
+    from crawlo.initialization import initialize_framework
+    
+    # 测试默认配置
+    settings = initialize_framework()
+    print(f"默认配置 - RUN_MODE: {settings.get('RUN_MODE')}")
+    print(f"默认配置 - QUEUE_TYPE: {settings.get('QUEUE_TYPE')}")
+    
+    # 测试自定义配置
+    custom_settings = {
+        'PROJECT_NAME': 'framework_test',
+        'SCHEDULER_MAX_QUEUE_SIZE': 50
+    }
+    
+    settings = initialize_framework(custom_settings)
+    print(f"自定义配置 - PROJECT_NAME: {settings.get('PROJECT_NAME')}")
+    print(f"自定义配置 - SCHEDULER_MAX_QUEUE_SIZE: {settings.get('SCHEDULER_MAX_QUEUE_SIZE')}")
+
+
+async def test_crawler_execution():
+    """测试爬虫执行"""
+    print("测试爬虫执行...")
+    
+    from crawlo.initialization import initialize_framework
+    from crawlo.crawler import CrawlerProcess
+    
+    # 初始化框架
+    settings = initialize_framework({
+        'PROJECT_NAME': 'framework_test'
+    })
+    
+    # 创建爬虫进程
+    process = CrawlerProcess(settings=settings)
+    
+    # 运行爬虫
+    await process.crawl(TestSpider)
+
+
+async def test_queue_system():
+    """测试队列系统"""
+    print("测试队列系统...")
+    
+    from crawlo.queue.queue_manager import QueueConfig, QueueManager
+    from crawlo import Request
+    
+    # 创建小队列配置进行测试
+    queue_config = QueueConfig(
+        queue_type='memory',
+        max_queue_size=5
+    )
+    
+    # 创建队列管理器
+    queue_manager = QueueManager(queue_config)
+    await queue_manager.initialize()
+    
+    # 测试添加请求
+    print("添加请求到队列...")
+    for i in range(3):
+        request = Request(f'https://example.com/test{i}')
+        await queue_manager.put(request)
+        print(f"添加请求 {i}")
+    
+    # 测试获取请求
+    print("从队列获取请求...")
+    for i in range(3):
+        request = await queue_manager.get(timeout=1.0)
+        if request:
+            print(f"获取请求: {request.url}")
+    
+    # 关闭队列
+    await queue_manager.close()
+
+
+async def test_spider_registry():
+    """测试爬虫注册系统"""
+    print("测试爬虫注册系统...")
+    
+    from crawlo.spider import get_global_spider_registry, is_spider_registered, get_spider_names
+    
+    # 检查测试爬虫是否已注册
+    spider_name = TestSpider.name
+    is_registered = is_spider_registered(spider_name)
+    print(f"爬虫 '{spider_name}' 是否已注册: {is_registered}")
+    
+    # 获取所有注册的爬虫名称
+    spider_names = get_spider_names()
+    print(f"所有注册的爬虫: {spider_names}")
+
+
+async def test_logging_system():
+    """测试日志系统"""
+    print("测试日志系统...")
+    
+    from crawlo.logging import get_logger, configure_logging
+    
+    # 配置日志系统
+    configure_logging({
+        'LOG_LEVEL': 'INFO',
+        'LOG_FILE': 'logs/test_framework.log'
+    })
+    
+    # 获取logger并记录日志
+    logger = get_logger('test_framework')
+    logger.info("这是测试日志信息")
+    logger.warning("这是测试警告信息")
+    logger.error("这是测试错误信息")
+
+
+async def test_settings_system():
+    """测试配置系统"""
+    print("测试配置系统...")
+    
+    from crawlo.settings.setting_manager import SettingManager
+    
+    # 创建配置管理器
+    settings = SettingManager()
+    
+    # 测试配置项
+    settings.set('TEST_KEY', 'test_value')
+    test_value = settings.get('TEST_KEY')
+    print(f"配置项 TEST_KEY 的值: {test_value}")
+    
+    # 测试不同类型的配置项
+    settings.set('TEST_INT', 42)
+    test_int = settings.get_int('TEST_INT')
+    print(f"配置项 TEST_INT 的值: {test_int}")
+    
+    settings.set('TEST_BOOL', True)
+    test_bool = settings.get_bool('TEST_BOOL')
+    print(f"配置项 TEST_BOOL 的值: {test_bool}")
+
+
+async def main():
+    """主函数"""
+    print("开始综合框架测试...")
+    print("=" * 50)
+    
+    try:
+        # 1. 测试框架初始化
+        await test_framework_initialization()
+        print()
+        
+        # 2. 测试配置系统
+        await test_settings_system()
+        print()
+        
+        # 3. 测试日志系统
+        await test_logging_system()
+        print()
+        
+        # 4. 测试队列系统
+        await test_queue_system()
+        print()
+        
+        # 5. 测试爬虫注册系统
+        await test_spider_registry()
+        print()
+        
+        # 6. 测试爬虫执行
+        await test_crawler_execution()
+        print()
+        
+        print("=" * 50)
+        print("所有测试通过！框架工作正常。")
+        
+    except Exception as e:
+        print("=" * 50)
+        print(f"测试失败: {e}")
+        import traceback
+        traceback.print_exc()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

tests/comprehensive_test.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+综合测试脚本
+测试Crawlo框架的所有优化功能
+"""
+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 import Spider, Request
+from crawlo.crawler import CrawlerProcess
+
+
+class ComprehensiveSpider(Spider):
+    name = 'comprehensive_test'
+    
+    def start_requests(self):
+        # 测试多个URL
+        urls = [
+            'https://www.baidu.com/',
+            'https://www.baidu.com/s?wd=python',
+            'https://www.baidu.com/s?wd=爬虫',
+            'https://www.baidu.com/s?wd=框架',
+            'https://www.baidu.com/s?wd=异步',
+        ]
+        
+        for i, url in enumerate(urls):
+            # 设置不同的优先级
+            priority = -i  # 负数表示优先级，数值越小优先级越高
+            yield Request(url, callback=self.parse, priority=priority)
+    
+    def parse(self, response):
+        self.logger.info(f"访问URL: {response.url}")
+        self.logger.info(f"响应状态码: {response.status_code}")
+        self.logger.info(f"页面标题: {response.xpath('//title/text()').get()}")
+        
+        # 提取一些链接用于进一步测试
+        links = response.xpath('//a/@href').getall()[:3]  # 只取前3个链接
+        
+        # 跟进链接，设置不同的深度
+        for link in links:
+            if link.startswith('http'):
+                # 创建新的请求，增加深度
+                meta = response.meta.copy()
+                meta['depth'] = meta.get('depth', 0) + 1
+                yield Request(link, callback=self.parse_link, meta=meta)
+    
+    def parse_link(self, response):
+        self.logger.info(f"跟进链接: {response.url}")
+        self.logger.info(f"响应状态码: {response.status_code}")
+        self.logger.info(f"页面深度: {response.meta.get('depth', 0)}")
+
+
+async def main():
+    # 创建爬虫进程
+    process = CrawlerProcess(settings={
+        'CONCURRENCY': 4,  # 设置并发数
+        'DOWNLOAD_DELAY': 0.5,  # 设置下载延迟
+        'LOG_LEVEL': 'INFO',  # 设置日志级别
+        'SCHEDULER_MAX_QUEUE_SIZE': 100,  # 设置队列最大大小
+    })
+    
+    # 运行爬虫
+    await process.crawl(ComprehensiveSpider)
+    
+    # 输出统计信息
+    if hasattr(process, 'get_metrics'):
+        metrics = process.get_metrics()
+        print(f"\n=== 爬虫统计信息 ===")
+        print(f"总执行时间: {metrics.get('total_duration', 0):.2f}秒")
+        print(f"总请求数: {metrics.get('total_requests', 0)}")
+        print(f"成功请求数: {metrics.get('total_success', 0)}")
+        print(f"错误请求数: {metrics.get('total_errors', 0)}")
+        print(f"平均成功率: {metrics.get('average_success_rate', 0):.2f}%")
+
+
+if __name__ == '__main__':
+    asyncio.run(main())