first commit

app/detectors/juziseo_detector.py

@@ -0,0 +1,214 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :juziseo_detector.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/9 0:03
+@explain : 桔子SEO检测器
+'''
+
+import requests
+from curl_cffi import requests as curl_requests
+import re
+from app.detectors.base import BaseDetector
+
+
+class JuziseoDetector(BaseDetector):
+    """
+    桔子SEO检测器
+    """
+    
+    def __init__(self):
+        """
+        初始化桔子SEO检测器
+        """
+        super().__init__()
+        self.url = 'https://seo.juziseo.com'
+        self.history_url = 'https://seo.juziseo.com/history/{domain}'
+        self.backlink_url = 'https://seo.juziseo.com/backlink/{domain}'
+    
+    def check_domain(self, domain):
+        """
+        检测域名
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            # 检查历史信息
+            history_result = self.check_history(domain)
+            
+            # 检查外链
+            backlink_result = self.check_backlink(domain)
+            
+            return {
+                'history': history_result,
+                'backlink': backlink_result
+            }
+        except Exception as e:
+            return self._handle_exception(e, domain)
+    
+    def check_history(self, domain):
+        """
+        检查历史信息
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            # 构建查询URL
+            query_url = self.history_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
+                
+                # 提取历史信息
+                history_info = self._extract_history_info(content)
+                
+                # 检查是否包含敏感词
+                has_sensitive = self._check_sensitive(history_info)
+                
+                # 检查是否有百度历史收录
+                has_baidu_history = '百度历史收录' in content
+                
+                # 检查是否有子域名
+                has_subdomains = '子域名' in content
+                
+                # 检查是否为简体中文
+                is_simplified = self._check_simplified(content)
+                
+                return {
+                    'has_sensitive': has_sensitive,
+                    'has_baidu_history': has_baidu_history,
+                    'has_subdomains': has_subdomains,
+                    'is_simplified': is_simplified
+                }
+            else:
+                self._log_warning(f"桔子SEO历史查询失败: {response.status_code}")
+                return {'has_sensitive': False, 'has_baidu_history': False, 'has_subdomains': False, 'is_simplified': True}
+        except Exception as e:
+            self._handle_exception(e, domain)
+            return {'has_sensitive': False, 'has_baidu_history': False, 'has_subdomains': False, 'is_simplified': True}
+    
+    def check_backlink(self, domain):
+        """
+        检查外链
+        
+        :param domain: 域名
+        :return: dict - 检测结果
+        """
+        try:
+            # 构建查询URL
+            query_url = self.backlink_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
+                
+                # 检查是否包含敏感词
+                has_sensitive = self._check_backlink_sensitive(content)
+                
+                # 检查是否有子域名
+                has_subdomains = '子域名' in content
+                
+                return {
+                    'has_sensitive': has_sensitive,
+                    'has_subdomains': has_subdomains
+                }
+            else:
+                self._log_warning(f"桔子SEO外链查询失败: {response.status_code}")
+                return {'has_sensitive': False, 'has_subdomains': False}
+        except Exception as e:
+            self._handle_exception(e, domain)
+            return {'has_sensitive': False, 'has_subdomains': False}
+    
+    def _extract_history_info(self, content):
+        """
+        提取历史信息
+        
+        :param content: 页面内容
+        :return: str - 历史信息
+        """
+        try:
+            # 这里需要根据实际页面结构调整正则表达式
+            pattern = r'<div class="history-info">(.*?)</div>'
+            match = re.search(pattern, content, re.DOTALL)
+            if match:
+                return match.group(1).strip()
+            return ''
+        except Exception as e:
+            self._handle_exception(e, 'extract_history_info')
+            return ''
+    
+    def _check_sensitive(self, history_info):
+        """
+        检查是否包含敏感词
+        
+        :param history_info: 历史信息
+        :return: bool - 是否包含敏感词
+        """
+        # 敏感词
+        sensitive_words = [
+            '色情', '赌博', '博彩', '毒品', '暴力', '诈骗',
+            '足球', '直播', '证券', '配资', '软件',
+            '体育', '商行', '下载', '影视', '网络',
+            '计算', 'app', 'HTML SiteMap', '模拟器', '传媒',
+            '二次元', '成人', '米乐', '小说', '凯发',
+            '人才', '华体', '娱乐', '开户'
+        ]
+        
+        for word in sensitive_words:
+            if word in history_info:
+                return True
+        
+        return False
+    
+    def _check_simplified(self, content):
+        """
+        检查是否为简体中文
+        
+        :param content: 页面内容
+        :return: bool - 是否为简体中文
+        """
+        # 检查是否包含简体中文标识
+        if '简体中文' in content:
+            return True
+        
+        # 检查是否包含繁体中文标识
+        if '繁体中文' in content:
+            return False
+        
+        return True
+    
+    def _check_backlink_sensitive(self, content):
+        """
+        检查外链是否包含敏感词
+        
+        :param content: 页面内容
+        :return: bool - 是否包含敏感词
+        """
+        # 敏感词
+        sensitive_words = [
+            '内幕', '猛料', '精料', '高手', '绝杀',
+            '权威', '澳门', '色情', '赌博', '博彩'
+        ]
+        
+        for word in sensitive_words:
+            if word in content:
+                return True
+        
+        return False