# -*- coding: UTF-8 -*-
'''
@Project :domainScanDemo
@File    :qihu360_detector.py
@IDE     :PyCharm
@Author  :梦伴
@Date    :2026/4/8 23:59
@explain : 360检测器
'''

import requests
from curl_cffi import requests as curl_requests
import re
from app.detectors.base import BaseDetector


class Qihu360Detector(BaseDetector):
    """
    360检测器
    """
    
    def __init__(self):
        """
        初始化360检测器
        """
        super().__init__()
        self.site_url = 'https://www.so.com/s'
    
    def check_domain(self, domain):
        """
        检测域名
        
        :param domain: 域名
        :return: dict - 检测结果
        """
        try:
            # 检查360 site
            site_result = self.check_site(domain)
            
            return {
                'site': site_result
            }
        except Exception as e:
            return self._handle_exception(e, domain)
    
    def check_site(self, domain):
        """
        检查360 site收录
        
        :param domain: 域名
        :return: dict - 检测结果
        """
        try:
            params = {
                'q': f'site:{domain}',
                'pn': '1',
                'rn': '50'
            }
            
            headers = {
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36'
            }
            
            # 使用curl_cffi模拟浏览器
            response = curl_requests.get(self.site_url, params=params, headers=headers, impersonate='chrome', timeout=10)
            
            if response.status_code == 200:
                content = response.text
                
                # 提取子域名
                subdomains = self._extract_subdomains(content, domain)
                
                # 检查是否有收录
                has_收录 = '没有找到相关结果' not in content
                
                return {
                    'has_收录': has_收录,
                    'subdomains': subdomains
                }
            else:
                self._log_warning(f"360 site查询失败: {response.status_code}")
                return {'has_收录': False, 'subdomains': []}
        except Exception as e:
            self._handle_exception(e, domain)
            return {'has_收录': False, 'subdomains': []}
    
    def _extract_subdomains(self, content, domain):
        """
        提取子域名
        
        :param content: 搜索结果内容
        :param domain: 主域名
        :return: list - 子域名列表
        """
        try:
            # 提取所有包含域名的链接
            pattern = r'https?://([a-zA-Z0-9-]+)\.' + re.escape(domain)
            matches = re.findall(pattern, content)
            
            # 去重并过滤空值
            subdomains = list(set(matches))
            subdomains = [sub for sub in subdomains if sub]
            
            return subdomains
        except Exception as e:
            self._handle_exception(e, domain)
            return []