"""
参数捕获工具
使用Playwright监听网络请求，捕获API的验签参数
"""
import json
import re
from urllib.parse import urlparse, parse_qs
from playwright.sync_api import sync_playwright


def extract_params_from_url(url: str) -> dict:
    """从URL中提取所有参数"""
    parsed = urlparse(url)
    params = parse_qs(parsed.query)
    
    # 将列表值转换为单个值
    return {k: v[0] if len(v) == 1 else v for k, v in params.items()}


def analyze_request(url: str, headers: dict, post_data: str = None):
    """分析请求参数"""
    print("\n" + "="*80)
    print("🔍 捕获到API请求")
    print("="*80)
    
    # 解析URL
    parsed_url = urlparse(url)
    print(f"\n📍 URL: {parsed_url.scheme}://{parsed_url.netloc}{parsed_url.path}")
    
    # 提取参数
    params = extract_params_from_url(url)
    
    # 关键验签参数
    sign_params = {
        'verifyFp': params.get('verifyFp', 'N/A'),
        'fp': params.get('fp', 'N/A'),
        'msToken': params.get('msToken', 'N/A'),
        'a_bogus': params.get('a_bogus', 'N/A'),
    }
    
    print("\n🔑 关键验签参数:")
    for key, value in sign_params.items():
        if value != 'N/A':
            # 截断显示长参数
            display_value = value if len(value) <= 60 else value[:60] + "..."
            print(f"  {key:12} = {display_value}")
    
    # 业务参数
    business_params = {k: v for k, v in params.items() 
                      if k not in sign_params}
    
    if business_params:
        print("\n📋 业务参数:")
        for key, value in business_params.items():
            print(f"  {key:20} = {value}")
    
    # 关键请求头
    important_headers = ['cookie', 'user-agent', 'referer', 'origin']
    print("\n📨 关键请求头:")
    for key in important_headers:
        value = headers.get(key, headers.get(key.title(), 'N/A'))
        if value != 'N/A':
            display_value = value if len(str(value)) <= 60 else str(value)[:60] + "..."
            print(f"  {key:15} = {display_value}")
    
    # POST数据
    if post_data:
        print("\n📦 POST数据:")
        try:
            data = json.loads(post_data)
            print(json.dumps(data, indent=2, ensure_ascii=False))
        except:
            print(post_data[:200] + "..." if len(post_data) > 200 else post_data)
    
    print("\n" + "="*80)


def capture_api_requests(target_url: str, api_pattern: str = "getInstituteDarenData"):
    """
    捕获API请求参数
    
    Args:
        target_url: 要访问的页面URL
        api_pattern: 要捕获的API接口名称模式
    """
    print(f"\n🚀 启动参数捕获工具")
    print(f"📱 目标页面: {target_url}")
    print(f"🎯 监听接口: {api_pattern}")
    print("\n⏳ 正在启动浏览器...")
    
    with sync_playwright() as p:
        # 启动浏览器
        browser = p.chromium.launch(
            headless=False,
            args=[
                '--start-maximized',
                '--disable-blink-features=AutomationControlled'
            ]
        )
        
        context = browser.new_context(
            viewport={'width': 1920, 'height': 1080},
            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'
        )
        
        page = context.new_page()
        
        # 监听所有请求
        captured_count = 0
        
        def handle_request(request):
            nonlocal captured_count
            url = request.url
            
            # 检查是否是目标API
            if api_pattern in url:
                captured_count += 1
                headers = request.headers
                post_data = request.post_data
                
                analyze_request(url, headers, post_data)
                
                print(f"\n✅ 已捕获 {captured_count} 个请求")
                print("💡 提示: 继续操作页面可以捕获更多请求...")
        
        def handle_response(response):
            """捕获响应数据"""
            url = response.url
            if api_pattern in url:
                print(f"\n📥 响应状态: {response.status}")
                try:
                    data = response.json()
                    print(f"📊 响应数据预览:")
                    # 只显示结构，不显示完整数据
                    if isinstance(data, dict):
                        print(f"  - 响应字段: {list(data.keys())}")
                        if 'data' in data:
                            if isinstance(data['data'], list):
                                print(f"  - 数据数量: {len(data['data'])} 条")
                            elif isinstance(data['data'], dict):
                                print(f"  - 数据字段: {list(data['data'].keys())}")
                except Exception as e:
                    print(f"  ⚠️ 无法解析响应: {e}")
        
        page.on('request', handle_request)
        page.on('response', handle_response)
        
        # 访问页面
        print(f"\n🌐 正在访问页面...")
        page.goto(target_url, wait_until='networkidle', timeout=60000)
        
        print(f"\n✨ 页面已加载完成")
        print(f"💡 请在浏览器中进行操作（如登录、点击等），工具会自动捕获API请求")
        print(f"⌨️  按 Ctrl+C 停止捕获\n")
        
        # 保持浏览器打开，直到用户关闭
        try:
            page.wait_for_timeout(3600000)  # 等待1小时
        except KeyboardInterrupt:
            print("\n\n👋 停止捕获")
        finally:
            browser.close()
            
            if captured_count > 0:
                print(f"\n📊 捕获统计:")
                print(f"  - 总共捕获: {captured_count} 个请求")
                print(f"  - 接口名称: {api_pattern}")
            else:
                print(f"\n⚠️  未捕获到任何请求")
                print(f"💡 提示:")
                print(f"  1. 确保在浏览器中触发了相关操作")
                print(f"  2. 检查接口名称是否正确")


def main():
    """主函数"""
    import sys
    
    # 默认参数
    default_url = "https://buyin.jinritemai.com/mpa/account/institution-role-select"
    default_pattern = "getInstituteDarenData"
    
    # 从命令行参数获取
    if len(sys.argv) > 1:
        target_url = sys.argv[1]
    else:
        target_url = default_url
    
    if len(sys.argv) > 2:
        api_pattern = sys.argv[2]
    else:
        api_pattern = default_pattern
    
    capture_api_requests(target_url, api_pattern)


if __name__ == "__main__":
    main()