# -*- coding: UTF-8 -*-
'''
@Project :domainScanDemo
@File    :chinaz_detector.py
@IDE     :PyCharm
@Author  :梦伴
@Date    :2026/4/9 0:01
@explain : 站长之家检测器
'''

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


class ChinazDetector(BaseDetector):
    """
    站长之家检测器
    """
    
    def __init__(self):
        """
        初始化站长之家检测器
        """
        super().__init__()
        self.url = 'https://seo.chinaz.com'
        self.query_url = 'https://seo.chinaz.com/{domain}'
    
    def check_domain(self, domain):
        """
        检测域名
        
        :param domain: 域名
        :return: dict - 检测结果
        """
        try:
            # 构建查询URL
            query_url = self.query_url.format(domain=domain)
            
            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(query_url, headers=headers, impersonate='chrome', timeout=10)
            
            if response.status_code == 200:
                content = response.text
                
                # 提取标题
                title = self._extract_title(content)
                
                # 提取网站分类
                category = self._extract_category(content)
                
                # 检查是否包含敏感词
                has_sensitive = self._check_sensitive(title, category)
                
                return {
                    'title': title,
                    'category': category,
                    'has_sensitive': has_sensitive
                }
            else:
                self._log_warning(f"站长之家查询失败: {response.status_code}")
                return {'error': f'HTTP {response.status_code}'}
        except Exception as e:
            return self._handle_exception(e, domain)
    
    def _extract_title(self, content):
        """
        提取标题
        
        :param content: 页面内容
        :return: str - 标题
        """
        try:
            pattern = r'<title>(.*?)</title>'
            match = re.search(pattern, content)
            if match:
                return match.group(1).strip()
            return ''
        except Exception as e:
            self._handle_exception(e, 'extract_title')
            return ''
    
    def _extract_category(self, content):
        """
        提取网站分类
        
        :param content: 页面内容
        :return: str - 分类
        """
        try:
            # 这里需要根据实际页面结构调整正则表达式
            pattern = r'网站分类：<a[^>]+>(.*?)</a>'
            match = re.search(pattern, content)
            if match:
                return match.group(1).strip()
            return ''
        except Exception as e:
            self._handle_exception(e, 'extract_category')
            return ''
    
    def _check_sensitive(self, title, category):
        """
        检查是否包含敏感词
        
        :param title: 标题
        :param category: 分类
        :return: bool - 是否包含敏感词
        """
        # 敏感分类
        sensitive_categories = ['视频电影', '体育运动', '常用查询']
        
        # 敏感词
        sensitive_words = ['色情', '赌博', '博彩', '毒品', '暴力', '诈骗']
        
        # 检查分类
        for cat in sensitive_categories:
            if cat in category:
                return True
        
        # 检查标题
        for word in sensitive_words:
            if word in title:
                return True
        
        return False