first commit

app/detectors/baidu_detector.py

@@ -0,0 +1,151 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :baidu_detector.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/8 23:58
+@explain : 百度检测器
+'''
+
+import requests
+from curl_cffi import requests as curl_requests
+import re
+from app.detectors.base import BaseDetector
+
+
+class BaiduDetector(BaseDetector):
+    """
+    百度检测器
+    """
+    
+    def __init__(self):
+        """
+        初始化百度检测器
+        """
+        super().__init__()
+        self.site_url = 'https://www.baidu.com/s'
+        self.history_url = 'https://www.baidu.com/s'
+    
+    def check_domain(self, domain):
+        """
+        检测域名
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            # 检查百度site
+            site_result = self.check_site(domain)
+            
+            # 检查百度历史
+            history_result = self.check_history(domain)
+            
+            return {
+                'site': site_result,
+                'history': history_result
+            }
+        except Exception as e:
+            return self._handle_exception(e, domain)
+    
+    def check_site(self, domain):
+        """
+        检查百度site收录
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            params = {
+                'wd': f'site:{domain}',
+                '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"百度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 check_history(self, domain):
+        """
+        检查百度历史收录
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            params = {
+                'wd': f'cache:{domain}',
+                '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.history_url, params=params, headers=headers, impersonate='chrome', timeout=10)
+            
+            if response.status_code == 200:
+                content = response.text
+                
+                # 检查是否有历史收录
+                has_history = '百度快照' in content
+                
+                # 检查是否有灰色内容
+                has_gray = '风险提示' in content or '安全警告' in content
+                
+                return {
+                    'has_history': has_history,
+                    'has_gray': has_gray
+                }
+            else:
+                self._log_warning(f"百度历史查询失败: {response.status_code}")
+                return {'has_history': False, 'has_gray': False}
+        except Exception as e:
+            self._handle_exception(e, domain)
+            return {'has_history': False, 'has_gray': False}
+    
+    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 []