#!/usr/bin/env python3
"""
简单网页抓取测试
测试网络连接和基本功能
"""

import requests
import sqlite3
import os
import datetime

def test_network_connection():
    """测试网络连接"""
    print("🌐 测试网络连接...")
    
    test_urls = [
        "https://httpbin.org/get",  # 测试网站
        "https://api.github.com",   # GitHub API
        "https://jsonplaceholder.typicode.com/posts/1"  # 测试API
    ]
    
    for url in test_urls:
        try:
            print(f"  测试连接: {url}")
            response = requests.get(url, timeout=10)
            if response.status_code == 200:
                print(f"  ✅ {url} - 连接成功 (状态码: {response.status_code})")
                return True
            else:
                print(f"  ⚠️ {url} - 连接异常 (状态码: {response.status_code})")
        except Exception as e:
            print(f"  ❌ {url} - 连接失败: {e}")
    
    return False

def test_database():
    """测试数据库功能"""
    print("\n🗄️ 测试数据库功能...")
    
    db_path = "/home/ubuntu/nanocode/it_automation_test/data/test_simple.db"
    os.makedirs(os.path.dirname(db_path), exist_ok=True)
    
    try:
        conn = sqlite3.connect(db_path)
        cursor = conn.cursor()
        
        # 创建测试表
        cursor.execute('''
        CREATE TABLE IF NOT EXISTS test_table (
            id INTEGER PRIMARY KEY,
            name TEXT,
            value INTEGER,
            created_at TIMESTAMP
        )
        ''')
        
        # 插入测试数据
        test_data = [
            ("测试1", 100, datetime.datetime.now().isoformat()),
            ("测试2", 200, datetime.datetime.now().isoformat()),
            ("测试3", 300, datetime.datetime.now().isoformat()),
        ]
        
        cursor.executemany('INSERT INTO test_table (name, value, created_at) VALUES (?, ?, ?)', test_data)
        conn.commit()
        
        # 查询数据
        cursor.execute('SELECT COUNT(*) FROM test_table')
        count = cursor.fetchone()[0]
        
        print(f"  ✅ 数据库创建成功: {db_path}")
        print(f"  ✅ 插入 {count} 条测试数据")
        
        # 显示数据
        cursor.execute('SELECT name, value FROM test_table ORDER BY id')
        print("  📊 测试数据:")
        for row in cursor.fetchall():
            print(f"    • {row[0]}: {row[1]}")
        
        conn.close()
        return True
        
    except Exception as e:
        print(f"  ❌ 数据库测试失败: {e}")
        return False

def test_requests_library():
    """测试requests库功能"""
    print("\n📡 测试requests库功能...")
    
    try:
        # 测试简单的GET请求
        test_url = "https://httpbin.org/json"
        response = requests.get(test_url, timeout=10)
        
        if response.status_code == 200:
            data = response.json()
            print(f"  ✅ GET请求成功: {test_url}")
            print(f"  📄 响应类型: {type(data)}")
            print(f"  🔤 示例数据: {str(data)[:100]}...")
            return True
        else:
            print(f"  ❌ GET请求失败: 状态码 {response.status_code}")
            return False
            
    except Exception as e:
        print(f"  ❌ requests库测试失败: {e}")
        return False

def test_beautifulsoup():
    """测试BeautifulSoup功能"""
    print("\n🍲 测试BeautifulSoup功能...")
    
    try:
        from bs4 import BeautifulSoup
        
        # 创建测试HTML
        test_html = """
        <html>
            <head><title>测试页面</title></head>
            <body>
                <h1>标题1</h1>
                <p class="content">段落1</p>
                <p class="content">段落2</p>
                <a href="https://example.com">链接</a>
            </body>
        </html>
        """
        
        soup = BeautifulSoup(test_html, 'html.parser')
        
        # 测试选择器
        title = soup.title.string
        paragraphs = soup.find_all('p', class_='content')
        links = soup.find_all('a')
        
        print(f"  ✅ BeautifulSoup初始化成功")
        print(f"  📝 标题: {title}")
        print(f"  📄 段落数: {len(paragraphs)}")
        print(f"  🔗 链接数: {len(links)}")
        
        return True
        
    except Exception as e:
        print(f"  ❌ BeautifulSoup测试失败: {e}")
        return False

def main():
    """主测试函数"""
    print("=" * 60)
    print("🧪 开始基础功能测试")
    print("=" * 60)
    
    tests_passed = 0
    total_tests = 4
    
    # 运行测试
    if test_network_connection():
        tests_passed += 1
    
    if test_database():
        tests_passed += 1
    
    if test_requests_library():
        tests_passed += 1
    
    if test_beautifulsoup():
        tests_passed += 1
    
    # 测试结果
    print("\n" + "=" * 60)
    print("📊 测试结果汇总")
    print("=" * 60)
    print(f"✅ 通过的测试: {tests_passed}/{total_tests}")
    
    if tests_passed == total_tests:
        print("🎉 所有基础功能测试通过！")
        print("\n💡 建议：")
        print("1. 网站抓取失败可能是目标网站的反爬机制")
        print("2. 可以尝试其他网站或添加更多请求头")
        print("3. 基础库功能正常，可以进行下一步测试")
        return True
    else:
        print("⚠️ 部分测试未通过")
        print(f"❌ 失败的测试: {total_tests - tests_passed}")
        return False

if __name__ == '__main__':
    try:
        success = main()
        exit(0 if success else 1)
    except Exception as e:
        print(f"\n❌ 测试过程中出现未预期的错误: {e}")
        import traceback
        traceback.print_exc()
        exit(1)