crawlo 1.1.4__py3-none-any.whl → 1.1.5__py3-none-any.whl

tests/authenticated_proxy_example.py

@@ -0,0 +1,237 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+带认证代理使用示例
+================
+展示如何在Crawlo框架中使用带用户名密码认证的代理和非认证代理
+
+支持的代理类型:
+1. 带认证的HTTP/HTTPS代理
+2. 不带认证的HTTP/HTTPS代理
+3. SOCKS代理（带或不带认证）
+"""
+
+from crawlo import Spider, Request
+from crawlo.tools import (
+    AuthenticatedProxy,
+    create_proxy_config,
+    format_proxy_for_request,
+    get_proxy_info,
+    validate_proxy_url
+)
+
+
+def demo_proxy_parsing():
+    """演示代理URL解析"""
+    print("=== 代理URL解析演示 ===\n")
+    
+    # 测试不同类型的代理URL
+    proxy_urls = [
+        # 带认证的HTTP代理
+        "http://username:password@proxy.example.com:8080",
+        # 不带认证的HTTP代理
+        "http://proxy.example.com:8080",
+        # 带认证的HTTPS代理
+        "https://user123:pass456@secure-proxy.com:443",
+        # SOCKS5代理
+        "socks5://socks-user:socks-pass@socks-proxy.com:1080",
+        # 不带认证的SOCKS4代理
+        "socks4://socks4-proxy.com:1080"
+    ]
+    
+    for proxy_url in proxy_urls:
+        print(f"解析代理URL: {proxy_url}")
+        
+        # 验证代理URL
+        is_valid = validate_proxy_url(proxy_url)
+        print(f"  有效性: {'有效' if is_valid else '无效'}")
+        
+        if is_valid:
+            # 获取代理详细信息
+            proxy_info = get_proxy_info(proxy_url)
+            print(f"  协议: {proxy_info['scheme']}")
+            print(f"  主机: {proxy_info['hostname']}")
+            print(f"  端口: {proxy_info['port']}")
+            print(f"  有认证: {'是' if proxy_info['has_auth'] else '否'}")
+            if proxy_info['has_auth']:
+                print(f"  用户名: {proxy_info['username']}")
+            
+            # 创建代理配置
+            proxy_config = create_proxy_config(proxy_url)
+            print(f"  代理配置: {proxy_config}")
+            
+            # 格式化为不同下载器的配置
+            for downloader in ["aiohttp", "httpx", "curl_cffi"]:
+                formatted = format_proxy_for_request(proxy_config, downloader)
+                print(f"  {downloader}格式: {formatted}")
+        
+        print()
+
+
+def demo_authenticated_proxy_class():
+    """演示AuthenticatedProxy类的使用"""
+    print("=== AuthenticatedProxy类演示 ===\n")
+    
+    # 带认证的代理
+    auth_proxy = AuthenticatedProxy("http://myuser:mypass@proxy.company.com:8080")
+    print(f"代理URL: {auth_proxy}")
+    print(f"清洁URL: {auth_proxy.clean_url}")
+    print(f"用户名: {auth_proxy.username}")
+    print(f"密码: {auth_proxy.password}")
+    print(f"代理字典: {auth_proxy.proxy_dict}")
+    print(f"认证凭据: {auth_proxy.get_auth_credentials()}")
+    print(f"认证头: {auth_proxy.get_auth_header()}")
+    print(f"是否有效: {auth_proxy.is_valid()}")
+    print()
+    
+    # 不带认证的代理
+    no_auth_proxy = AuthenticatedProxy("http://public.proxy.com:8080")
+    print(f"代理URL: {no_auth_proxy}")
+    print(f"清洁URL: {no_auth_proxy.clean_url}")
+    print(f"用户名: {no_auth_proxy.username}")
+    print(f"密码: {no_auth_proxy.password}")
+    print(f"代理字典: {no_auth_proxy.proxy_dict}")
+    print(f"认证凭据: {no_auth_proxy.get_auth_credentials()}")
+    print(f"认证头: {no_auth_proxy.get_auth_header()}")
+    print(f"是否有效: {no_auth_proxy.is_valid()}")
+    print()
+
+
+class ProxySpider(Spider):
+    """使用代理的爬虫示例"""
+    name = 'proxy_spider'
+    
+    def __init__(self):
+        super().__init__()
+        # 代理列表
+        self.proxies = [
+            "http://user1:pass1@proxy1.example.com:8080",
+            "http://user2:pass2@proxy2.example.com:8080",
+            "http://proxy3.example.com:8080",  # 不带认证
+            "https://secureuser:securepass@secure.proxy.com:443"
+        ]
+        self.current_proxy_index = 0
+    
+    def get_next_proxy(self):
+        """获取下一个代理"""
+        proxy_url = self.proxies[self.current_proxy_index]
+        self.current_proxy_index = (self.current_proxy_index + 1) % len(self.proxies)
+        return proxy_url
+    
+    def start_requests(self):
+        urls = [
+            'https://httpbin.org/ip',      # 查看IP地址
+            'https://httpbin.org/headers', # 查看请求头
+            'https://example.com',         # 普通网站
+        ]
+        
+        for url in urls:
+            # 获取代理
+            proxy_url = self.get_next_proxy()
+            proxy = AuthenticatedProxy(proxy_url)
+            
+            # 创建请求
+            request = Request(url=url, callback=self.parse)
+            
+            # 根据不同下载器设置代理
+            # 这里以AioHttp为例
+            if self.crawler.settings.get("DOWNLOADER_TYPE") == "aiohttp":
+                request.proxy = proxy.clean_url
+                auth = proxy.get_auth_credentials()
+                if auth:
+                    # AioHttp需要在下载器中处理认证
+                    request.meta["proxy_auth"] = auth
+            else:
+                # 其他下载器
+                request.proxy = proxy.proxy_dict
+                
+            yield request
+    
+    def parse(self, response):
+        """解析响应"""
+        print(f"成功访问: {response.url}")
+        print(f"状态码: {response.status_code}")
+        # 显示前200个字符
+        print(f"响应内容: {response.text[:200]}...\n")
+        yield {"url": response.url, "status": response.status_code}
+
+
+def demo_in_spider():
+    """演示在爬虫中使用代理"""
+    print("=== 在爬虫中使用代理 ===\n")
+    print("在爬虫项目中，您可以这样使用带认证的代理:")
+    print("""
+from crawlo import Spider, Request
+from crawlo.tools import AuthenticatedProxy
+
+class MySpider(Spider):
+    name = 'my_spider'
+    
+    def __init__(self):
+        super().__init__()
+        self.proxy_urls = [
+            "http://username:password@proxy1.example.com:8080",
+            "http://user:pass@proxy2.example.com:8080",
+            "http://proxy3.example.com:8080"  # 不带认证
+        ]
+    
+    def start_requests(self):
+        urls = ['https://httpbin.org/ip', 'https://example.com']
+        
+        for i, url in enumerate(urls):
+            # 选择代理
+            proxy_url = self.proxy_urls[i % len(self.proxy_urls)]
+            proxy = AuthenticatedProxy(proxy_url)
+            
+            # 创建请求
+            request = Request(url=url, callback=self.parse)
+            
+            # 设置代理（根据不同下载器）
+            downloader_type = self.crawler.settings.get("DOWNLOADER_TYPE", "aiohttp")
+            
+            if downloader_type == "aiohttp":
+                # AioHttp下载器
+                request.proxy = proxy.clean_url
+                auth = proxy.get_auth_credentials()
+                if auth:
+                    request.meta["proxy_auth"] = auth
+            elif downloader_type == "httpx":
+                # HttpX下载器
+                request.proxy = proxy.clean_url
+            elif downloader_type == "curl_cffi":
+                # CurlCffi下载器
+                request.proxy = proxy.proxy_dict
+                # 认证信息在URL中或通过headers传递
+                auth_header = proxy.get_auth_header()
+                if auth_header:
+                    request.headers["Proxy-Authorization"] = auth_header
+            
+            yield request
+    
+    def parse(self, response):
+        # 处理响应
+        yield {"url": response.url, "title": response.css('title::text').get()}
+    """)
+
+
+if __name__ == '__main__':
+    # 运行演示
+    demo_proxy_parsing()
+    demo_authenticated_proxy_class()
+    demo_in_spider()
+    
+    print("\n=== 配置说明 ===")
+    print("在settings.py中配置代理:")
+    print("""
+# 启用代理中间件
+MIDDLEWARES = [
+    # ... 其他中间件 ...
+    'crawlo.middleware.proxy.ProxyMiddleware',
+]
+
+# 代理配置
+PROXY_ENABLED = True
+PROXY_API_URL = "https://api.proxyprovider.com/get"  # 代理API地址
+PROXY_EXTRACTOR = "proxy"  # 从API响应中提取代理的字段路径
+PROXY_REFRESH_INTERVAL = 60  # 代理刷新间隔（秒）
+""")

tests/cleaners_example.py

@@ -0,0 +1,161 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+Crawlo框架数据清洗工具使用示例
+"""
+from crawlo.cleaners 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.cleaners 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/config_validation_demo.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+配置验证演示脚本
+演示如何使用配置验证器来验证Crawlo配置
+"""
+import sys
+import os
+
+# 添加项目根目录到路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.config import CrawloConfig
+from crawlo.config_validator import print_validation_report
+
+
+def demonstrate_config_validation():
+    """演示配置验证功能"""
+    print("=== 配置验证功能演示 ===\n")
+    
+    # 1. 有效的单机配置
+    print("1. 有效的单机配置:")
+    valid_standalone_config = {
+        'PROJECT_NAME': 'demo_project',
+        'QUEUE_TYPE': 'memory',
+        'CONCURRENCY': 8,
+        'DOWNLOAD_DELAY': 1.0,
+        'LOG_LEVEL': 'INFO',
+        'MIDDLEWARES': [
+            'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
+            'crawlo.middleware.download_delay.DownloadDelayMiddleware'
+        ],
+        'PIPELINES': [
+            'crawlo.pipelines.console_pipeline.ConsolePipeline'
+        ]
+    }
+    
+    print_validation_report(valid_standalone_config)
+    print()
+    
+    # 2. 有效的分布式配置
+    print("2. 有效的分布式配置:")
+    valid_distributed_config = {
+        'PROJECT_NAME': 'demo_project',
+        'QUEUE_TYPE': 'redis',
+        'CONCURRENCY': 16,
+        'DOWNLOAD_DELAY': 1.0,
+        'SCHEDULER_QUEUE_NAME': 'crawlo:demo_project:queue:requests',
+        'REDIS_HOST': '127.0.0.1',
+        'REDIS_PORT': 6379,
+        'LOG_LEVEL': 'INFO',
+        'MIDDLEWARES': [
+            'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
+            'crawlo.middleware.download_delay.DownloadDelayMiddleware'
+        ],
+        'PIPELINES': [
+            'crawlo.pipelines.console_pipeline.ConsolePipeline'
+        ]
+    }
+    
+    print_validation_report(valid_distributed_config)
+    print()
+    
+    # 3. 无效配置示例
+    print("3. 无效配置示例:")
+    invalid_config = {
+        'PROJECT_NAME': '',  # 空项目名称
+        'QUEUE_TYPE': 'invalid_type',  # 无效队列类型
+        'CONCURRENCY': -1,  # 负并发数
+        'REDIS_PORT': 99999,  # 无效端口
+        'LOG_LEVEL': 'INVALID_LEVEL'  # 无效日志级别
+    }
+    
+    print_validation_report(invalid_config)
+    print()
+    
+    # 4. 使用配置工厂创建配置并验证
+    print("4. 使用配置工厂创建配置并验证:")
+    try:
+        # 创建有效的配置
+        config = CrawloConfig.standalone(
+            concurrency=8,
+            download_delay=1.0
+        )
+        print("✅ 单机模式配置创建成功")
+        config.print_summary()
+        print()
+        
+        # 尝试创建无效配置（会抛出异常）
+        try:
+            invalid_config_dict = {
+                'CONCURRENCY': -1  # 负并发数
+            }
+            invalid_config_obj = CrawloConfig.custom(invalid_config_dict)
+        except ValueError as e:
+            print(f"✅ 捕获到配置验证异常: {e}")
+        
+    except Exception as e:
+        print(f"❌ 配置创建失败: {e}")
+
+
+if __name__ == "__main__":
+    demonstrate_config_validation()