convert domainCheck to regular directory

domainCheck/app/detectors/jucha_detector.py

@@ -0,0 +1,228 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :jucha_detector.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/9 0:04
+@explain : 聚查检测器
+'''
+
+import requests
+from curl_cffi import requests as curl_requests
+import re
+from app.detectors.base import BaseDetector
+
+
+class JuchaDetector(BaseDetector):
+    """
+    聚查检测器
+    """
+    
+    def __init__(self):
+        """
+        初始化聚查检测器
+        """
+        super().__init__()
+        self.url = 'https://www.jucha.com'
+        self.whois_url = 'https://www.jucha.com/whois/{domain}'
+        self.beian_url = 'https://www.jucha.com/beian/{domain}'
+        self.intercept_url = 'https://www.jucha.com/intercept/{domain}'
+    
+    def check_domain(self, domain):
+        """
+        检测域名
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            # 检查WHOIS
+            whois_result = self.check_whois(domain)
+            
+            # 检查备案
+            beian_result = self.check_beian(domain)
+            
+            # 检查拦截
+            intercept_result = self.check_intercept(domain)
+            
+            return {
+                'whois': whois_result,
+                'beian': beian_result,
+                'intercept': intercept_result
+            }
+        except Exception as e:
+            return self._handle_exception(e, domain)
+    
+    def check_whois(self, domain):
+        """
+        检查WHOIS
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            # 构建查询URL
+            query_url = self.whois_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WHOIS信息
+                whois_info = self._extract_whois_info(content)
+                
+                return whois_info
+            else:
+                self._log_warning(f"聚查WHOIS查询失败: {response.status_code}")
+                return {'status': ''}
+        except Exception as e:
+            self._handle_exception(e, domain)
+            return {'status': ''}
+    
+    def check_beian(self, domain):
+        """
+        检查备案
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            # 构建查询URL
+            query_url = self.beian_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
+                
+                # 提取备案信息
+                beian_info = self._extract_beian_info(content)
+                
+                return beian_info
+            else:
+                self._log_warning(f"聚查备案查询失败: {response.status_code}")
+                return {'has_beian': False, 'beian_year': '', 'is_enterprise': False, 'beian_match': False}
+        except Exception as e:
+            self._handle_exception(e, domain)
+            return {'has_beian': False, 'beian_year': '', 'is_enterprise': False, 'beian_match': False}
+    
+    def check_intercept(self, domain):
+        """
+        检查拦截
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            # 构建查询URL
+            query_url = self.intercept_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
+                
+                # 检查是否被拦截
+                is_normal = self._check_intercept_status(content)
+                
+                return {
+                    'normal': is_normal
+                }
+            else:
+                self._log_warning(f"聚查拦截查询失败: {response.status_code}")
+                return {'normal': False}
+        except Exception as e:
+            self._handle_exception(e, domain)
+            return {'normal': False}
+    
+    def _extract_whois_info(self, content):
+        """
+        提取WHOIS信息
+        
+        :param content: 页面内容
+        :return: dict - WHOIS信息
+        """
+        try:
+            # 提取状态信息
+            pattern = r'域名状态：<span[^>]+>(.*?)</span>'
+            match = re.search(pattern, content)
+            status = match.group(1).strip() if match else ''
+            
+            return {
+                'status': status
+            }
+        except Exception as e:
+            self._handle_exception(e, 'extract_whois_info')
+            return {'status': ''}
+    
+    def _extract_beian_info(self, content):
+        """
+        提取备案信息
+        
+        :param content: 页面内容
+        :return: dict - 备案信息
+        """
+        try:
+            # 检查是否有备案
+            has_beian = '备案信息' in content
+            
+            # 提取备案年份
+            beian_year = ''
+            pattern = r'审核时间：(\d{4})-\d{2}-\d{2}'
+            match = re.search(pattern, content)
+            if match:
+                beian_year = match.group(1)
+            
+            # 提取单位性质
+            is_enterprise = '企业' in content
+            
+            # 检查首网址和备案网址是否一致
+            beian_match = '网站首页网址' in content
+            
+            return {
+                'has_beian': has_beian,
+                'beian_year': beian_year,
+                'is_enterprise': is_enterprise,
+                'beian_match': beian_match
+            }
+        except Exception as e:
+            self._handle_exception(e, 'extract_beian_info')
+            return {'has_beian': False, 'beian_year': '', 'is_enterprise': False, 'beian_match': False}
+    
+    def _check_intercept_status(self, content):
+        """
+        检查拦截状态
+        
+        :param content: 页面内容
+        :return: bool - 是否正常
+        """
+        try:
+            # 检查是否包含正常标识
+            if '正常' in content:
+                return True
+            
+            # 检查是否包含拦截标识
+            if '拦截' in content:
+                return False
+            
+            return False
+        except Exception as e:
+            self._handle_exception(e, 'check_intercept_status')
+            return False