ai_wht_wechat/backend/test_basic_browser.py

"""
基础浏览器测试脚本
用于测试浏览器是否能正常加载小红书页面
"""
import asyncio
from playwright.async_api import async_playwright
import sys


async def test_basic_browser(proxy_index: int = 0):
    """基础浏览器测试"""
    print(f"\n{'='*60}")
    print(f"🔍 基础浏览器测试")
    print(f"{'='*60}")
    
    # 从代理配置获取代理信息
    from damai_proxy_config import get_proxy_config
    proxy_config = get_proxy_config(proxy_index)
    proxy_server = proxy_config['server'].replace('http://', '')
    proxy_url = f"http://{proxy_config['username']}:{proxy_config['password']}@{proxy_server}"
    
    print(f"✅ 使用代理: 代理{proxy_index + 1}")
    print(f"   代理服务器: {proxy_config['server']}")
    
    try:
        async with async_playwright() as p:
            # 配置代理
            proxy_parts = proxy_url.replace('http://', '').replace('https://', '').split('@')
            if len(proxy_parts) == 2:
                auth_part = proxy_parts[0]
                server_part = proxy_parts[1]
                username, password = auth_part.split(':')
                
                proxy_config_obj = {
                    "server": f"http://{server_part}",
                    "username": username,
                    "password": password
                }
            else:
                proxy_config_obj = {"server": proxy_url}
            
            print(f"   配置的代理对象: {proxy_config_obj}")
            
            # 启动浏览器
            browser = await p.chromium.launch(
                headless=False,  # 非无头模式，便于观察
                proxy=proxy_config_obj
            )
            
            # 创建上下文
            context = await browser.new_context(
                user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
            )
            
            # 创建页面
            page = await context.new_page()
            
            print(f"\n🌐 尝试访问百度...")
            try:
                await page.goto('https://www.baidu.com', wait_until='networkidle', timeout=15000)
                await asyncio.sleep(2)
                
                title = await page.title()
                url = page.url
                content_len = len(await page.content())
                
                print(f"   ✅ 百度访问成功")
                print(f"   标题: {title}")
                print(f"   URL: {url}")
                print(f"   内容长度: {content_len} 字符")
            except Exception as e:
                print(f"   ❌ 百度访问失败: {str(e)}")
            
            print(f"\n🌐 尝试访问小红书登录页...")
            try:
                await page.goto('https://creator.xiaohongshu.com/login', wait_until='networkidle', timeout=15000)
                await asyncio.sleep(5)  # 等待更长时间
                
                title = await page.title()
                url = page.url
                content = await page.content()
                content_len = len(content)
                
                print(f"   访问结果:")
                print(f"   标题: {title}")
                print(f"   URL: {url}")
                print(f"   内容长度: {content_len} 字符")
                
                # 检查是否有特定内容
                if content_len == 0:
                    print(f"   ⚠️  页面内容为空，可能存在加载问题")
                elif "验证" in content or "captcha" in content.lower() or "安全" in content:
                    print(f"   ⚠️  检测到验证或安全提示")
                else:
                    print(f"   ✅ 页面加载正常")
                
                # 查找页面上的所有元素
                print(f"\n🔍 分析页面元素...")
                
                # 查找所有input元素
                inputs = await page.query_selector_all('input')
                print(f"   找到 {len(inputs)} 个input元素")
                
                # 查找所有表单相关元素
                form_elements = await page.query_selector_all('input, button, select, textarea')
                print(f"   找到 {len(form_elements)} 个表单相关元素")
                
                # 打印前几个元素的信息
                for i, elem in enumerate(form_elements[:5]):
                    try:
                        tag = await elem.evaluate('el => el.tagName')
                        text = await elem.inner_text()
                        placeholder = await elem.get_attribute('placeholder')
                        class_name = await elem.get_attribute('class')
                        id_attr = await elem.get_attribute('id')
                        
                        print(f"   元素 {i+1}:")
                        print(f"     - 标签: {tag}")
                        print(f"     - 文本: {text[:50]}...")
                        print(f"     - placeholder: {placeholder}")
                        print(f"     - class: {class_name[:50]}...")
                        print(f"     - id: {id_attr}")
                    except Exception as e:
                        print(f"   元素 {i+1}: 获取信息失败 - {str(e)}")
                
            except Exception as e:
                print(f"   ❌ 小红书访问失败: {str(e)}")
                import traceback
                traceback.print_exc()
            
            print(f"\n⏸️  浏览器保持打开状态，您可以手动检查页面")
            print(f"   按 Enter 键关闭浏览器...")
            
            # 等待用户输入
            input()
            
            await browser.close()
            print(f"✅ 浏览器已关闭")
            
    except Exception as e:
        print(f"❌ 测试过程异常: {str(e)}")
        import traceback
        traceback.print_exc()


async def main():
    """主函数"""
    print("="*60)
    print("🔍 基础浏览器测试工具")
    print("="*60)
    
    proxy_choice = input("\n请选择代理 (0 或 1, 默认为0): ").strip()
    if proxy_choice not in ['0', '1']:
        proxy_choice = '0'
    proxy_idx = int(proxy_choice)
    
    await test_basic_browser(proxy_idx)
    
    print(f"\n{'='*60}")
    print("✅ 测试完成！")
    print("="*60)


if __name__ == "__main__":
    # Windows环境下设置事件循环策略
    if sys.platform == 'win32':
        asyncio.set_event_loop_policy(asyncio.WindowsProactorEventLoopPolicy())
    
    # 运行测试
    asyncio.run(main())