first commit

app/core/__init__.py

@@ -0,0 +1,4 @@
+# -*- coding: UTF-8 -*-
+'''
+核心功能模块
+'''

app/core/detect_engine.py

@@ -0,0 +1,281 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :detect_engine.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/8 23:52
+@explain : 检测引擎
+'''
+
+import time
+from loguru import logger
+from app.utils.database import Database
+from app.detectors.rdap_detector import RDAPDetector
+from app.detectors.wayback_detector import WaybackDetector
+from app.detectors.baidu_detector import BaiduDetector
+from app.detectors.qihu360_detector import Qihu360Detector
+from app.detectors.google_detector import GoogleDetector
+from app.detectors.chinaz_detector import ChinazDetector
+from app.detectors.aizhan_detector import AizhanDetector
+from app.detectors.juziseo_detector import JuziseoDetector
+from app.detectors.jucha_detector import JuchaDetector
+
+
+class DetectEngine:
+    """
+    检测引擎
+    """
+    
+    def __init__(self):
+        """
+        初始化检测引擎
+        """
+        self.db = Database()
+        self.rdap_detector = RDAPDetector()
+        self.wayback_detector = WaybackDetector()
+        self.baidu_detector = BaiduDetector()
+        self.qihu360_detector = Qihu360Detector()
+        self.google_detector = GoogleDetector()
+        self.chinaz_detector = ChinazDetector()
+        self.aizhan_detector = AizhanDetector()
+        self.juziseo_detector = JuziseoDetector()
+        self.jucha_detector = JuchaDetector()
+    
+    def detect_domain(self, domain_id):
+        """
+        检测域名
+        
+        :param domain_id: 域名ID
+        :return: bool - 是否检测成功
+        """
+        try:
+            # 获取域名信息
+            domain_info = self.db.get_domain_by_id(domain_id)
+            if not domain_info:
+                logger.error(f"域名不存在: {domain_id}")
+                return False
+            
+            domain = domain_info['domain']
+            logger.info(f"开始检测域名: {domain}")
+            
+            # 更新检测状态为检测中
+            self.db.update_domain_detect_status(domain_id, 2)  # 2 表示检测中
+            
+            # 1. 基础检测
+            if not self._basic_detect(domain_id, domain):
+                logger.info(f"基础检测失败，停止后续检测: {domain}")
+                return False
+            
+            # 2. 深度检测
+            if not self._deep_detect(domain_id, domain):
+                logger.info(f"深度检测失败: {domain}")
+                return False
+            
+            # 更新检测状态为正常
+            self.db.update_domain_detect_status(domain_id, 3)  # 3 表示正常
+            logger.info(f"域名检测完成: {domain}")
+            return True
+        except Exception as e:
+            logger.error(f"检测域名出错: {e}")
+            # 更新检测状态为检测失败
+            self.db.update_domain_detect_status(domain_id, 5)  # 5 表示检测失败
+            return False
+    
+    def _basic_detect(self, domain_id, domain):
+        """
+        基础检测
+        
+        :param domain_id: 域名ID
+        :param domain: 域名
+        :return: bool - 是否检测通过
+        """
+        # 1. 检查是否为一口价域名
+        is_ykj = self.db.is_ykj_domain(domain_id)
+        
+        # 2. 注册状态检测（一口价域名跳过）
+        if not is_ykj:
+            register_status = self.rdap_detector.check_register_status(domain)
+            self.db.update_domain_register_status(domain_id, register_status)
+        
+        # 3. 黑名单缓存检查
+        if self.db.is_blacklisted(domain):
+            logger.info(f"域名在黑名单中: {domain}")
+            self.db.update_domain_detect_status(domain_id, 4)  # 4 表示黑名单
+            return False
+        
+        # 4. 时光机快照年份采集
+        snapshot_years = self.wayback_detector.get_snapshot_years(domain)
+        if snapshot_years:
+            self.db.update_domain_snapshot_years(domain_id, ','.join(map(str, snapshot_years)))
+        
+        # 5. 时光机正文抽样与敏感词匹配
+        if self.wayback_detector.has_sensitive_content(domain):
+            logger.info(f"域名包含敏感词: {domain}")
+            self.db.update_domain_detect_status(domain_id, 4)  # 4 表示黑名单
+            self.db.add_to_blacklist(domain, "快照包含敏感词")
+            return False
+        
+        return True
+    
+    def _deep_detect(self, domain_id, domain):
+        """
+        深度检测
+        
+        :param domain_id: 域名ID
+        :param domain: 域名
+        :return: bool - 是否检测通过
+        """
+        # 1. 百度历史/Site
+        baidu_history = self.baidu_detector.check_history(domain)
+        baidu_site = self.baidu_detector.check_site(domain)
+        
+        # 2. 360 Site
+        qihu360_site = self.qihu360_detector.check_site(domain)
+        
+        # 3. Google Site
+        google_site = self.google_detector.check_site(domain)
+        
+        # 4. 站长之家
+        chinaz_info = self.chinaz_detector.check_domain(domain)
+        
+        # 5. 爱站网
+        aizhan_info = self.aizhan_detector.check_domain(domain)
+        
+        # 6. 桔子SEO
+        juziseo_info = self.juziseo_detector.check_domain(domain)
+        
+        # 7. 聚查
+        jucha_info = self.jucha_detector.check_domain(domain)
+        
+        # 检查是否有风险
+        if self._check_risk(domain_id, domain, baidu_history, baidu_site, qihu360_site, google_site, chinaz_info, aizhan_info, juziseo_info, jucha_info):
+            return False
+        
+        # 保存检测结果
+        self.db.add_detection_result(domain_id, baidu_history, baidu_site, qihu360_site, google_site, chinaz_info, aizhan_info, juziseo_info, jucha_info)
+        
+        return True
+    
+    def _check_risk(self, domain_id, domain, baidu_history, baidu_site, qihu360_site, google_site, chinaz_info, aizhan_info, juziseo_info, jucha_info):
+        """
+        检查风险
+        
+        :param domain_id: 域名ID
+        :param domain: 域名
+        :param baidu_history: 百度历史
+        :param baidu_site: 百度site
+        :param qihu360_site: 360 site
+        :param google_site: Google site
+        :param chinaz_info: 站长之家信息
+        :param aizhan_info: 爱站网信息
+        :param juziseo_info: 桔子SEO信息
+        :param jucha_info: 聚查信息
+        :return: bool - 是否有风险
+        """
+        # 检查百度历史过灰
+        if baidu_history and '灰' in str(baidu_history):
+            logger.info(f"百度历史过灰: {domain}")
+            self.db.update_domain_detect_status(domain_id, 4)  # 4 表示黑名单
+            self.db.add_to_blacklist(domain, "百度历史过灰")
+            return True
+        
+        # 检查标题敏感词
+        if chinaz_info and 'title' in chinaz_info:
+            if self._contains_sensitive_words(chinaz_info['title']):
+                logger.info(f"标题包含敏感词: {domain}")
+                self.db.update_domain_detect_status(domain_id, 4)  # 4 表示黑名单
+                self.db.add_to_blacklist(domain, "标题包含敏感词")
+                return True
+        
+        # 检查子域名
+        if baidu_site and 'subdomains' in baidu_site:
+            subdomains = baidu_site['subdomains']
+            # 排除 www, @, m
+            valid_subdomains = [sub for sub in subdomains if sub not in ['www', '@', 'm']]
+            if valid_subdomains:
+                logger.info(f"存在子域名: {domain}")
+                self.db.update_domain_detect_status(domain_id, 4)  # 4 表示黑名单
+                self.db.add_to_blacklist(domain, "存在子域名")
+                return True
+        
+        # 检查风险提示
+        if aizhan_info and 'risk' in aizhan_info:
+            if aizhan_info['risk'] in ['低风险', '疑似色情博彩风险', '严重影响权重']:
+                logger.info(f"风险提示: {domain}")
+                self.db.update_domain_detect_status(domain_id, 4)  # 4 表示黑名单
+                self.db.add_to_blacklist(domain, f"风险提示: {aizhan_info['risk']}")
+                return True
+        
+        # 检查WHOIS状态
+        if jucha_info and 'whois' in jucha_info:
+            if jucha_info['whois'].get('status') in ['clientHold', 'serverHold']:
+                logger.info(f"WHOIS状态异常: {domain}")
+                self.db.update_domain_detect_status(domain_id, 4)  # 4 表示黑名单
+                self.db.add_to_blacklist(domain, "WHOIS状态异常")
+                return True
+        
+        # 检查拦截检测
+        if jucha_info and 'intercept' in jucha_info:
+            if not jucha_info['intercept'].get('normal', True):
+                logger.info(f"拦截检测异常: {domain}")
+                self.db.update_domain_detect_status(domain_id, 4)  # 4 表示黑名单
+                self.db.add_to_blacklist(domain, "拦截检测异常")
+                return True
+        
+        return False
+    
+    def _contains_sensitive_words(self, text):
+        """
+        检查文本是否包含敏感词
+        
+        :param text: 文本
+        :return: bool - 是否包含敏感词
+        """
+        # 这里可以添加敏感词检查逻辑
+        sensitive_words = ['色情', '博彩', '赌博', '毒品', '暴力']
+        for word in sensitive_words:
+            if word in text:
+                return True
+        return False
+    
+    def process_task(self, task_id):
+        """
+        处理检测任务
+        
+        :param task_id: 任务ID
+        :return: bool - 是否处理成功
+        """
+        try:
+            # 获取任务信息
+            task = self.db.get_task_by_id(task_id)
+            if not task:
+                logger.error(f"任务不存在: {task_id}")
+                return False
+            
+            domain_id = task['domain_id']
+            
+            # 更新任务状态为执行中
+            self.db.update_task_status(task_id, 1)  # 1 表示执行中
+            
+            # 执行检测
+            success = self.detect_domain(domain_id)
+            
+            # 更新任务状态
+            if success:
+                self.db.update_task_status(task_id, 2)  # 2 表示完成
+            else:
+                # 增加重试次数
+                retry_count = task.get('retry_count', 0) + 1
+                if retry_count < 3:
+                    self.db.update_task_retry_count(task_id, retry_count)
+                    self.db.update_task_status(task_id, 0)  # 0 表示待执行
+                else:
+                    self.db.update_task_status(task_id, 3)  # 3 表示失败
+            
+            return success
+        except Exception as e:
+            logger.error(f"处理任务出错: {e}")
+            # 更新任务状态为失败
+            self.db.update_task_status(task_id, 3)  # 3 表示失败
+            return False

app/core/domain_collector.py

@@ -0,0 +1,261 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :domain_collector.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/8 23:50
+@explain : 域名收集器
+'''
+
+import re
+import tldextract
+from loguru import logger
+from app.utils.database import Database
+from app.utils.domain_utils import normalize_domain
+from app.config import config
+
+
+class DomainCollector:
+    """
+    域名收集器
+    """
+    
+    def __init__(self):
+        """
+        初始化域名收集器
+        """
+        self.db = Database(
+            host=config.DB_HOST,
+            port=config.DB_PORT,
+            database=config.DB_DATABASE,
+            user=config.DB_USER,
+            password=config.DB_PASSWORD
+        )
+    
+    def add_domain(self, domain, source_type):
+        """
+        添加域名
+        
+        :param domain: 域名
+        :param source_type: 来源类型
+        :return: bool - 是否添加成功
+        """
+        try:
+            # 标准化域名
+            normalized_domain = normalize_domain(domain)
+            if not normalized_domain:
+                logger.warning(f"无效域名: {domain}")
+                return False
+            
+            # 提取顶级域名
+            ext = tldextract.extract(normalized_domain)
+            tld = ext.suffix
+            
+            # 只保留 .com 和 .net
+            if tld not in ['com', 'net']:
+                logger.warning(f"不支持的顶级域名: {tld}")
+                return False
+            
+            # 检查是否已存在
+            if self.db.domain_exists(normalized_domain):
+                logger.info(f"域名已存在: {normalized_domain}")
+                return False
+            
+            # 添加域名
+            domain_id = self.db.add_domain(normalized_domain, tld, source_type)
+            if domain_id:
+                # 创建检测任务
+                self.db.create_detect_task(domain_id, 1)  # 1 表示基础检测
+                logger.info(f"成功添加域名: {normalized_domain}")
+                return True
+            else:
+                logger.error(f"添加域名失败: {normalized_domain}")
+                return False
+        except Exception as e:
+            logger.error(f"添加域名出错: {e}")
+            return False
+    
+    def add_domains_batch(self, domains, source_type, batch_size=1000, dry_run=False):
+        """
+        批量添加域名
+        
+        :param domains: 域名列表
+        :param source_type: 来源类型
+        :param batch_size: 批量大小
+        :param dry_run: 是否仅进行干运行（不实际添加域名）
+        :return: dict - 统计信息
+        """
+        try:
+            # 统计信息
+            stats = {
+                'total': len(domains),
+                'valid': 0,
+                'added': 0,
+                'exists': 0,
+                'invalid': 0,
+                'failed': 0
+            }
+            
+            # 处理大规模数据时，分批进行标准化和过滤
+            normalized_domains = []
+            batch_domains = []
+            
+            for i, domain in enumerate(domains):
+                normalized = normalize_domain(domain)
+                if not normalized:
+                    stats['invalid'] += 1
+                    continue
+                
+                # 提取顶级域名
+                ext = tldextract.extract(normalized)
+                tld = ext.suffix
+                
+                # 只保留 .com 和 .net
+                if tld not in ['com', 'net']:
+                    stats['invalid'] += 1
+                    continue
+                
+                normalized_domains.append((normalized, tld))
+                batch_domains.append(normalized)
+                stats['valid'] += 1
+                
+                # 每1000个域名检查一次，避免内存占用过高
+                if (i + 1) % 1000 == 0:
+                    logger.info(f"已处理 {i + 1}/{len(domains)} 个域名")
+            
+            logger.info(f"域名标准化完成，有效域名: {stats['valid']}")
+            
+            # 提取所有域名
+            all_domains = [domain for domain, tld in normalized_domains]
+            
+            # 批量检查域名是否存在
+            existing_domains = self.db.check_domains_exist(all_domains)
+            existing_set = set(existing_domains)
+            
+            # 准备批量添加数据
+            batch_data = []
+            for domain, tld in normalized_domains:
+                if domain not in existing_set:
+                    batch_data.append((domain, tld, source_type))
+            
+            stats['exists'] = len(existing_domains)
+            stats['valid'] = len(normalized_domains)
+            
+            # 干运行模式下直接返回统计信息
+            if dry_run:
+                stats['added'] = len(batch_data)
+                logger.info(f"干运行模式：准备添加 {len(batch_data)} 个新域名")
+                return stats
+            
+            logger.info(f"准备添加 {len(batch_data)} 个新域名")
+            
+            # 分批次添加
+            for i in range(0, len(batch_data), batch_size):
+                batch = batch_data[i:i+batch_size]
+                added_count = self.db.add_domains_batch(batch)
+                stats['added'] += added_count
+                stats['failed'] += len(batch) - added_count
+                
+                # 每处理一批，记录一次进度
+                if (i + len(batch)) % (batch_size * 10) == 0:
+                    logger.info(f"已添加 {i + len(batch)}/{len(batch_data)} 个域名")
+            
+            logger.info(f"批量添加域名完成: {stats}")
+            return stats
+        except Exception as e:
+            logger.error(f"批量添加域名出错: {e}")
+            return {
+                'total': len(domains),
+                'valid': 0,
+                'added': 0,
+                'exists': 0,
+                'invalid': 0,
+                'failed': len(domains)
+            }
+    
+    def import_from_file(self, file_path, source_type, batch_size=1000):
+        """
+        从文件导入域名
+        
+        :param file_path: 文件路径
+        :param source_type: 来源类型
+        :param batch_size: 批量大小
+        :return: dict - 导入统计信息
+        """
+        try:
+            with open(file_path, 'r', encoding='utf-8') as f:
+                domains = f.readlines()
+            
+            # 提取域名
+            domain_list = []
+            for domain in domains:
+                domain = domain.strip()
+                if domain:
+                    domain_list.append(domain)
+            
+            # 批量添加域名
+            stats = self.add_domains_batch(domain_list, source_type, batch_size)
+            
+            logger.info(f"从文件导入完成: {stats}")
+            return stats
+        except Exception as e:
+            logger.error(f"从文件导入出错: {e}")
+            return {
+                'total': 0,
+                'valid': 0,
+                'added': 0,
+                'exists': 0,
+                'invalid': 0,
+                'failed': 0
+            }
+    
+    def collect_from_juming(self, type_='一口价'):
+        """
+        从聚名网收集域名
+        
+        :param type_: 类型，一口价或过期删除
+        :return: int - 收集到的域名数量
+        """
+        # 这里可以添加从聚名网收集域名的逻辑
+        logger.info(f"从聚名网收集 {type_} 域名")
+        # 模拟收集结果
+        return 0
+    
+    def collect_from_search_engine(self, keyword, limit=100):
+        """
+        从搜索引擎收集域名
+        
+        :param keyword: 关键词
+        :param limit: 限制数量
+        :return: int - 收集到的域名数量
+        """
+        # 这里可以添加从搜索引擎收集域名的逻辑
+        logger.info(f"从搜索引擎收集域名，关键词: {keyword}, 限制: {limit}")
+        # 模拟收集结果
+        return 0
+    
+    def collect_from_enterprise_directory(self, url, limit=100):
+        """
+        从企业目录收集域名
+        
+        :param url: 企业目录URL
+        :param limit: 限制数量
+        :return: int - 收集到的域名数量
+        """
+        # 这里可以添加从企业目录收集域名的逻辑
+        logger.info(f"从企业目录收集域名，URL: {url}, 限制: {limit}")
+        # 模拟收集结果
+        return 0
+    
+    def collect_from_zone_file(self, file_path):
+        """
+        从Zone File收集域名
+        
+        :param file_path: Zone File路径
+        :return: int - 收集到的域名数量
+        """
+        # 这里可以添加从Zone File收集域名的逻辑
+        logger.info(f"从Zone File收集域名，文件: {file_path}")
+        # 模拟收集结果
+        return 0

app/core/domain_processor.py

@@ -0,0 +1,150 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :domain_processor.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/8 23:51
+@explain : 域名处理器
+'''
+
+import re
+import tldextract
+from loguru import logger
+from app.utils.database import Database
+from app.utils.domain_utils import normalize_domain
+
+
+class DomainProcessor:
+    """
+    域名处理器
+    """
+    
+    def __init__(self):
+        """
+        初始化域名处理器
+        """
+        self.db = Database()
+    
+    def process_domain(self, domain):
+        """
+        处理域名
+        
+        :param domain: 域名
+        :return: dict - 处理结果
+        """
+        result = {
+            'original': domain,
+            'normalized': None,
+            'tld': None,
+            'valid': False,
+            'reason': ''
+        }
+        
+        try:
+            # 标准化域名
+            normalized = normalize_domain(domain)
+            if not normalized:
+                result['reason'] = '无效域名格式'
+                return result
+            
+            # 提取顶级域名
+            ext = tldextract.extract(normalized)
+            tld = ext.suffix
+            
+            # 检查顶级域名
+            if tld not in ['com', 'net']:
+                result['reason'] = '不支持的顶级域名'
+                return result
+            
+            result['normalized'] = normalized
+            result['tld'] = tld
+            result['valid'] = True
+            
+            return result
+        except Exception as e:
+            logger.error(f"处理域名出错: {e}")
+            result['reason'] = f"处理出错: {str(e)}"
+            return result
+    
+    def batch_process(self, domains):
+        """
+        批量处理域名
+        
+        :param domains: 域名列表
+        :return: list - 处理结果列表
+        """
+        results = []
+        for domain in domains:
+            result = self.process_domain(domain)
+            results.append(result)
+        return results
+    
+    def filter_valid_domains(self, domains):
+        """
+        过滤有效的域名
+        
+        :param domains: 域名列表
+        :return: list - 有效的域名列表
+        """
+        valid_domains = []
+        for domain in domains:
+            result = self.process_domain(domain)
+            if result['valid']:
+                valid_domains.append(result['normalized'])
+        return valid_domains
+    
+    def update_domain_status(self, domain_id, status_type, status_value):
+        """
+        更新域名状态
+        
+        :param domain_id: 域名ID
+        :param status_type: 状态类型
+        :param status_value: 状态值
+        :return: bool - 是否更新成功
+        """
+        try:
+            if status_type == 'use_status':
+                return self.db.update_domain_use_status(domain_id, status_value)
+            elif status_type == 'detect_status':
+                return self.db.update_domain_detect_status(domain_id, status_value)
+            elif status_type == 'register_status':
+                return self.db.update_domain_register_status(domain_id, status_value)
+            else:
+                logger.error(f"未知的状态类型: {status_type}")
+                return False
+        except Exception as e:
+            logger.error(f"更新域名状态出错: {e}")
+            return False
+    
+    def blacklist_domain(self, domain_id, reason):
+        """
+        将域名加入黑名单
+        
+        :param domain_id: 域名ID
+        :param reason: 黑名单原因
+        :return: bool - 是否操作成功
+        """
+        try:
+            # 更新检测状态为黑名单
+            if self.db.update_domain_detect_status(domain_id, 4):  # 4 表示黑名单
+                # 添加到黑名单表
+                domain = self.db.get_domain_by_id(domain_id)
+                if domain:
+                    return self.db.add_to_blacklist(domain['domain'], reason)
+            return False
+        except Exception as e:
+            logger.error(f"将域名加入黑名单出错: {e}")
+            return False
+    
+    def get_domain_statistics(self):
+        """
+        获取域名统计信息
+        
+        :return: dict - 统计信息
+        """
+        try:
+            return self.db.get_domain_statistics()
+        except Exception as e:
+            logger.error(f"获取域名统计信息出错: {e}")
+            return {}

app/core/export_manager.py

@@ -0,0 +1,273 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :export_manager.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/8 23:54
+@explain : 导出管理器
+'''
+
+import os
+from loguru import logger
+from app.utils.database import Database
+
+
+class ExportManager:
+    """
+    导出管理器
+    """
+    
+    def __init__(self):
+        """
+        初始化导出管理器
+        """
+        self.db = Database()
+    
+    def export_domains(self, filter_conditions, output_file):
+        """
+        导出域名
+        
+        :param filter_conditions: 筛选条件
+        :param output_file: 输出文件路径
+        :return: int - 导出的域名数量
+        """
+        try:
+            # 查询符合条件的域名
+            domains = self.db.get_domains_by_conditions(filter_conditions)
+            
+            if not domains:
+                logger.warning("没有符合条件的域名")
+                return 0
+            
+            # 导出到文件
+            with open(output_file, 'w', encoding='utf-8') as f:
+                for domain in domains:
+                    f.write(domain['domain'] + '\n')
+            
+            logger.info(f"成功导出 {len(domains)} 个域名到 {output_file}")
+            return len(domains)
+        except Exception as e:
+            logger.error(f"导出域名出错: {e}")
+            return 0
+    
+    def export_with_details(self, filter_conditions, output_file):
+        """
+        导出域名及其详细信息
+        
+        :param filter_conditions: 筛选条件
+        :param output_file: 输出文件路径
+        :return: int - 导出的域名数量
+        """
+        try:
+            # 查询符合条件的域名及其详细信息
+            domains = self.db.get_domains_with_details(filter_conditions)
+            
+            if not domains:
+                logger.warning("没有符合条件的域名")
+                return 0
+            
+            # 导出到文件
+            with open(output_file, 'w', encoding='utf-8') as f:
+                # 写入表头
+                f.write('域名,注册状态,使用状态,检测状态,备案历史,备案年份,快照年份,友情链接数量\n')
+                
+                # 写入数据
+                for domain in domains:
+                    line = f"{domain['domain']},{domain['register_status']},{domain['use_status']},{domain['detect_status']},{domain['has_beian']},{domain['beian_year']},{domain['snapshot_years']},{domain['backlink_count']}\n"
+                    f.write(line)
+            
+            logger.info(f"成功导出 {len(domains)} 个域名及其详细信息到 {output_file}")
+            return len(domains)
+        except Exception as e:
+            logger.error(f"导出域名详细信息出错: {e}")
+            return 0
+    
+    def batch_update_status(self, domain_ids, status_type, status_value):
+        """
+        批量更新域名状态
+        
+        :param domain_ids: 域名ID列表
+        :param status_type: 状态类型
+        :param status_value: 状态值
+        :return: int - 更新成功的域名数量
+        """
+        try:
+            success_count = 0
+            for domain_id in domain_ids:
+                if self.db.update_domain_status(domain_id, status_type, status_value):
+                    success_count += 1
+            
+            logger.info(f"成功更新 {success_count} 个域名的状态")
+            return success_count
+        except Exception as e:
+            logger.error(f"批量更新域名状态出错: {e}")
+            return 0
+    
+    def get_filtered_domains(self, filter_conditions, limit=1000):
+        """
+        获取符合条件的域名
+        
+        :param filter_conditions: 筛选条件
+        :param limit: 限制数量
+        :return: list - 域名列表
+        """
+        try:
+            domains = self.db.get_domains_by_conditions(filter_conditions, limit)
+            logger.info(f"获取到 {len(domains)} 个符合条件的域名")
+            return domains
+        except Exception as e:
+            logger.error(f"获取符合条件的域名出错: {e}")
+            return []
+    
+    def generate_report(self, output_file):
+        """
+        生成统计报告
+        
+        :param output_file: 输出文件路径
+        :return: bool - 是否生成成功
+        """
+        try:
+            # 获取域名统计信息
+            domain_stats = self.db.get_domain_statistics()
+            
+            # 获取任务统计信息
+            task_stats = self.db.get_task_statistics()
+            
+            # 生成报告
+            with open(output_file, 'w', encoding='utf-8') as f:
+                f.write('域名库系统统计报告\n')
+                f.write('=' * 50 + '\n')
+                
+                f.write('\n域名统计:\n')
+                f.write(f'总域名数: {domain_stats.get("total", 0)}\n')
+                f.write(f'可注册域名: {domain_stats.get("available", 0)}\n')
+                f.write(f'已注册域名: {domain_stats.get("registered", 0)}\n')
+                f.write(f'黑名单域名: {domain_stats.get("blacklisted", 0)}\n')
+                
+                f.write('\n任务统计:\n')
+                f.write(f'总任务数: {task_stats.get("total", 0)}\n')
+                f.write(f'待执行任务: {task_stats.get("pending", 0)}\n')
+                f.write(f'执行中任务: {task_stats.get("running", 0)}\n')
+                f.write(f'已完成任务: {task_stats.get("completed", 0)}\n')
+                f.write(f'失败任务: {task_stats.get("failed", 0)}\n')
+            
+            logger.info(f"成功生成统计报告到 {output_file}")
+            return True
+        except Exception as e:
+            logger.error(f"生成统计报告出错: {e}")
+            return False
+    
+    def export_to_excel(self, domains, output_file):
+        """
+        导出域名到Excel文件
+        
+        :param domains: 域名列表
+        :param output_file: 输出文件路径
+        :return: int - 导出的域名数量
+        """
+        try:
+            # 尝试导入openpyxl
+            try:
+                from openpyxl import Workbook
+            except ImportError:
+                # 如果没有安装openpyxl，使用CSV格式作为替代
+                logger.warning("openpyxl库未安装，将使用CSV格式导出")
+                return self.export_to_csv(domains, output_file.replace('.xlsx', '.csv'))
+            
+            # 创建工作簿
+            wb = Workbook()
+            ws = wb.active
+            
+            # 写入表头
+            headers = ['域名', '注册状态', '使用状态', '检测状态', '人工复核状态', '过期时间', '单位性质', '网站首页网址', '检测时间', '备案历史', '备案年份', '快照年份', '百度历史', '百度Site', '是否中文标题', '360 Site', 'Google Site', '友情链接数量']
+            ws.append(headers)
+            
+            # 写入数据
+            for domain in domains:
+                row = [
+                    domain.get('domain', ''),
+                    domain.get('register_status', ''),
+                    domain.get('use_status', ''),
+                    domain.get('detect_status', ''),
+                    domain.get('review_status', ''),
+                    domain.get('expire_date', ''),
+                    domain.get('company_type', ''),
+                    domain.get('website_url', ''),
+                    domain.get('detect_time', ''),
+                    domain.get('has_beian', ''),
+                    domain.get('beian_year', ''),
+                    domain.get('snapshot_years', ''),
+                    domain.get('baidu_history', ''),
+                    domain.get('baidu_site', ''),
+                    domain.get('is_chinese_title', ''),
+                    domain.get('qihu360_site', ''),
+                    domain.get('google_site', ''),
+                    domain.get('backlink_count', '')
+                ]
+                ws.append(row)
+            
+            # 保存文件
+            wb.save(output_file)
+            
+            logger.info(f"成功导出 {len(domains)} 个域名到Excel文件: {output_file}")
+            return len(domains)
+        except Exception as e:
+            logger.error(f"导出Excel文件出错: {e}")
+            # 尝试使用CSV格式作为替代
+            try:
+                csv_file = output_file.replace('.xlsx', '.csv')
+                logger.info(f"尝试使用CSV格式导出到: {csv_file}")
+                return self.export_to_csv(domains, csv_file)
+            except Exception as e2:
+                logger.error(f"导出CSV文件也失败: {e2}")
+                raise
+    
+    def export_to_csv(self, domains, output_file):
+        """
+        导出域名到CSV文件
+        
+        :param domains: 域名列表
+        :param output_file: 输出文件路径
+        :return: int - 导出的域名数量
+        """
+        try:
+            import csv
+            
+            # 写入文件
+            with open(output_file, 'w', encoding='utf-8', newline='') as f:
+                writer = csv.writer(f)
+                
+                # 写入表头
+                headers = ['域名', '注册状态', '使用状态', '检测状态', '人工复核状态', '过期时间', '单位性质', '网站首页网址', '检测时间', '备案历史', '备案年份', '快照年份', '百度历史', '百度Site', '是否中文标题', '360 Site', 'Google Site', '友情链接数量']
+                writer.writerow(headers)
+                
+                # 写入数据
+                for domain in domains:
+                    row = [
+                        domain.get('domain', ''),
+                        domain.get('register_status', ''),
+                        domain.get('use_status', ''),
+                        domain.get('detect_status', ''),
+                        domain.get('review_status', ''),
+                        domain.get('expire_date', ''),
+                        domain.get('company_type', ''),
+                        domain.get('website_url', ''),
+                        domain.get('detect_time', ''),
+                        domain.get('has_beian', ''),
+                        domain.get('beian_year', ''),
+                        domain.get('snapshot_years', ''),
+                        domain.get('baidu_history', ''),
+                        domain.get('baidu_site', ''),
+                        domain.get('is_chinese_title', ''),
+                        domain.get('qihu360_site', ''),
+                        domain.get('google_site', ''),
+                        domain.get('backlink_count', '')
+                    ]
+                    writer.writerow(row)
+            
+            logger.info(f"成功导出 {len(domains)} 个域名到CSV文件: {output_file}")
+            return len(domains)
+        except Exception as e:
+            logger.error(f"导出CSV文件出错: {e}")
+            raise

app/core/task_scheduler.py

@@ -0,0 +1,162 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :task_scheduler.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/8 23:53
+@explain : 任务调度器
+'''
+
+import time
+import threading
+from loguru import logger
+from app.utils.database import Database
+from app.core.detect_engine import DetectEngine
+
+
+class TaskScheduler:
+    """
+    任务调度器
+    """
+    
+    def __init__(self):
+        """
+        初始化任务调度器
+        """
+        self.db = Database()
+        self.detect_engine = DetectEngine()
+        self.running = False
+        self.threads = []
+        self.max_threads = 10
+    
+    def start(self):
+        """
+        启动任务调度器
+        """
+        if self.running:
+            logger.info("任务调度器已经在运行中")
+            return
+        
+        self.running = True
+        logger.info("启动任务调度器")
+        
+        # 启动多个线程处理任务
+        for i in range(self.max_threads):
+            thread = threading.Thread(target=self._process_tasks, daemon=True)
+            thread.start()
+            self.threads.append(thread)
+            logger.info(f"启动任务处理线程 {i+1}")
+    
+    def stop(self):
+        """
+        停止任务调度器
+        """
+        self.running = False
+        logger.info("停止任务调度器")
+        
+        # 等待线程结束
+        for thread in self.threads:
+            thread.join(timeout=5)
+        
+        self.threads.clear()
+        logger.info("任务调度器已停止")
+    
+    def _process_tasks(self):
+        """
+        处理任务
+        """
+        while self.running:
+            try:
+                # 获取待执行的任务
+                task = self.db.get_pending_task()
+                if not task:
+                    # 没有任务，休眠一段时间
+                    time.sleep(1)
+                    continue
+                
+                task_id = task['id']
+                domain_id = task['domain_id']
+                
+                logger.info(f"处理任务: {task_id}, 域名ID: {domain_id}")
+                
+                # 执行任务
+                success = self.detect_engine.process_task(task_id)
+                
+                if success:
+                    logger.info(f"任务处理成功: {task_id}")
+                else:
+                    logger.warning(f"任务处理失败: {task_id}")
+                
+                # 短暂休眠，避免过于频繁的数据库操作
+                time.sleep(0.1)
+            except Exception as e:
+                logger.error(f"处理任务出错: {e}")
+                # 休眠一段时间，避免出错后无限循环
+                time.sleep(5)
+    
+    def add_task(self, domain_id, task_type=1, priority=0):
+        """
+        添加任务
+        
+        :param domain_id: 域名ID
+        :param task_type: 任务类型，1-基础检测，2-深度检测
+        :param priority: 优先级，0-低，1-中，2-高
+        :return: int - 任务ID
+        """
+        try:
+            task_id = self.db.create_detect_task(domain_id, task_type, priority)
+            logger.info(f"添加任务成功: {task_id}, 域名ID: {domain_id}")
+            return task_id
+        except Exception as e:
+            logger.error(f"添加任务失败: {e}")
+            return None
+    
+    def get_task_stats(self):
+        """
+        获取任务统计信息
+        
+        :return: dict - 任务统计信息
+        """
+        try:
+            return self.db.get_task_statistics()
+        except Exception as e:
+            logger.error(f"获取任务统计信息出错: {e}")
+            return {}
+    
+    def retry_failed_tasks(self):
+        """
+        重试失败的任务
+        
+        :return: int - 重试的任务数量
+        """
+        try:
+            tasks = self.db.get_failed_tasks()
+            retry_count = 0
+            
+            for task in tasks:
+                task_id = task['id']
+                self.db.update_task_status(task_id, 0)  # 0 表示待执行
+                self.db.update_task_retry_count(task_id, 0)  # 重置重试次数
+                retry_count += 1
+            
+            logger.info(f"重试 {retry_count} 个失败的任务")
+            return retry_count
+        except Exception as e:
+            logger.error(f"重试失败任务出错: {e}")
+            return 0
+    
+    def clear_completed_tasks(self, days=7):
+        """
+        清理已完成的任务
+        
+        :param days: 保留天数
+        :return: int - 清理的任务数量
+        """
+        try:
+            count = self.db.clear_completed_tasks(days)
+            logger.info(f"清理 {count} 个已完成的任务")
+            return count
+        except Exception as e:
+            logger.error(f"清理已完成任务出错: {e}")
+            return 0