convert domainCheck to regular directory

2026-04-16 13:33:06 +08:00
parent e406d73334
commit d37c444929
107 changed files with 254185 additions and 1 deletions
--- a/domainCheck/app/utils/init.py
+++ b/domainCheck/app/utils/init.py
@@ -0,0 +1,4 @@
+# -*- coding: UTF-8 -*-
+'''
+工具类模块
+'''
--- a/domainCheck/app/utils/database.py
+++ b/domainCheck/app/utils/database.py
--- a/domainCheck/app/utils/domain_utils.py
+++ b/domainCheck/app/utils/domain_utils.py
@@ -0,0 +1,195 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :domain_utils.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/9 0:05
+@explain : 域名工具类
+'''
+
+import re
+import tldextract
+from loguru import logger
+from app.utils.status_codes import DETECT_STATUS_LABELS, REGISTER_STATUS_LABELS, USE_STATUS_LABELS
+
+
+def normalize_domain(domain):
+    """
+    标准化域名
+    
+    :param domain: 域名
+    :return: str - 标准化后的域名
+    """
+    try:
+        # 转换为小写
+        domain = domain.lower()
+        
+        # 去除空格
+        domain = domain.strip()
+        
+        # 去除协议
+        domain = re.sub(r'^https?://', '', domain)
+        
+        # 去除路径和查询参数
+        domain = domain.split('/')[0]
+        domain = domain.split('?')[0]
+        
+        # 去除端口
+        domain = domain.split(':')[0]
+        
+        # 只保留主域
+        ext = tldextract.extract(domain)
+        if ext.domain and ext.suffix:
+            domain = f"{ext.domain}.{ext.suffix}"
+        
+        # 验证域名格式
+        if not is_valid_domain(domain):
+            return None
+        
+        return domain
+    except Exception as e:
+        logger.error(f"标准化域名出错: {e}")
+        return None
+
+
+def is_valid_domain(domain):
+    """
+    验证域名格式
+    
+    :param domain: 域名
+    :return: bool - 是否有效
+    """
+    try:
+        # 域名格式正则
+        pattern = r'^[a-zA-Z0-9][a-zA-Z0-9-]{0,61}[a-zA-Z0-9]\.[a-zA-Z]{2,}$'
+        return bool(re.match(pattern, domain))
+    except Exception as e:
+        logger.error(f"验证域名格式出错: {e}")
+        return False
+
+
+def extract_tld(domain):
+    """
+    提取顶级域名
+    
+    :param domain: 域名
+    :return: str - 顶级域名
+    """
+    try:
+        ext = tldextract.extract(domain)
+        return ext.suffix
+    except Exception as e:
+        logger.error(f"提取顶级域名出错: {e}")
+        return ''
+
+
+def extract_domain(domain):
+    """
+    提取主域名
+    
+    :param domain: 域名
+    :return: str - 主域名
+    """
+    try:
+        ext = tldextract.extract(domain)
+        if ext.domain and ext.suffix:
+            return f"{ext.domain}.{ext.suffix}"
+        return domain
+    except Exception as e:
+        logger.error(f"提取主域名出错: {e}")
+        return domain
+
+
+def is_com_or_net(domain):
+    """
+    检查是否为 .com 或 .net 域名
+    
+    :param domain: 域名
+    :return: bool - 是否为 .com 或 .net 域名
+    """
+    try:
+        tld = extract_tld(domain)
+        return tld in ['com', 'net']
+    except Exception as e:
+        logger.error(f"检查域名后缀出错: {e}")
+        return False
+
+
+def generate_domain_variants(domain):
+    """
+    生成域名变体
+    
+    :param domain: 域名
+    :return: list - 域名变体列表
+    """
+    try:
+        variants = []
+        
+        # 原始域名
+        variants.append(domain)
+        
+        # 添加 www
+        if not domain.startswith('www.'):
+            variants.append(f"www.{domain}")
+        
+        # 移除 www
+        if domain.startswith('www.'):
+            variants.append(domain[4:])
+        
+        return variants
+    except Exception as e:
+        logger.error(f"生成域名变体出错: {e}")
+        return [domain]
+
+
+def parse_domain_status(status_code):
+    """
+    解析域名状态码
+    
+    :param status_code: 状态码
+    :return: str - 状态描述
+    """
+    return REGISTER_STATUS_LABELS.get(status_code, '未知')
+
+
+def parse_use_status(status_code):
+    """
+    解析使用状态码
+    
+    :param status_code: 状态码
+    :return: str - 状态描述
+    """
+    return USE_STATUS_LABELS.get(status_code, '未知')
+
+
+def parse_detect_status(status_code):
+    """
+    解析检测状态码
+    
+    :param status_code: 状态码
+    :return: str - 状态描述
+    """
+    return DETECT_STATUS_LABELS.get(status_code, '未知')
+
+
+def parse_source_type(source_type):
+    """
+    解析来源类型
+    
+    :param source_type: 来源类型
+    :return: str - 来源描述
+    """
+    source_map = {
+        1: '聚名一口价',
+        2: '聚名过期删除',
+        3: 'zone file',
+        4: '搜索引擎采集',
+        5: '企业目录采集',
+        6: '手工录入',
+        7: 'TXT 导入',
+        8: '第三方接口',
+        9: '其它'
+    }
+    
+    return source_map.get(source_type, '未知')
--- a/domainCheck/app/utils/http_utils.py
+++ b/domainCheck/app/utils/http_utils.py
@@ -0,0 +1,157 @@
+# -*- coding: UTF-8 -*-
+'''
+@Project :domainScanDemo
+@File    :http_utils.py
+@IDE     :PyCharm
+@Author  :梦伴
+@Date    :2026/4/9 0:06
+@explain : HTTP工具类
+'''
+
+import requests
+from curl_cffi import requests as curl_requests
+from loguru import logger
+
+
+class HTTPUtils:
+    """
+    HTTP工具类
+    """
+    
+    @staticmethod
+    def get(url, headers=None, params=None, timeout=10, proxies=None, use_curl=False):
+        """
+        发送GET请求
+        
+        :param url: 请求URL
+        :param headers: 请求头
+        :param params: 查询参数
+        :param timeout: 超时时间
+        :param proxies: 代理
+        :param use_curl: 是否使用curl_cffi
+        :return: requests.Response - 响应对象
+        """
+        try:
+            if use_curl:
+                # 使用curl_cffi模拟浏览器
+                response = curl_requests.get(url, headers=headers, params=params, timeout=timeout, proxies=proxies, impersonate='chrome')
+            else:
+                # 使用requests
+                response = requests.get(url, headers=headers, params=params, timeout=timeout, proxies=proxies)
+            
+            response.raise_for_status()  # 检查状态码
+            return response
+        except Exception as e:
+            logger.error(f"GET请求失败: {url}, 错误: {e}")
+            return None
+    
+    @staticmethod
+    def post(url, headers=None, data=None, json=None, timeout=10, proxies=None, use_curl=False):
+        """
+        发送POST请求
+        
+        :param url: 请求URL
+        :param headers: 请求头
+        :param data: 表单数据
+        :param json: JSON数据
+        :param timeout: 超时时间
+        :param proxies: 代理
+        :param use_curl: 是否使用curl_cffi
+        :return: requests.Response - 响应对象
+        """
+        try:
+            if use_curl:
+                # 使用curl_cffi模拟浏览器
+                response = curl_requests.post(url, headers=headers, data=data, json=json, timeout=timeout, proxies=proxies, impersonate='chrome')
+            else:
+                # 使用requests
+                response = requests.post(url, headers=headers, data=data, json=json, timeout=timeout, proxies=proxies)
+            
+            response.raise_for_status()  # 检查状态码
+            return response
+        except Exception as e:
+            logger.error(f"POST请求失败: {url}, 错误: {e}")
+            return None
+    
+    @staticmethod
+    def get_random_user_agent():
+        """
+        获取随机用户代理
+        
+        :return: str - 用户代理
+        """
+        user_agents = [
+            'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36',
+            'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/145.0.0.0 Safari/537.36',
+            'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Firefox/138.0',
+            'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Edge/146.0.0.0',
+            'Mozilla/5.0 (Macintosh; Intel Mac OS X 14_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.6 Safari/605.1.15'
+        ]
+        
+        import random
+        return random.choice(user_agents)
+    
+    @staticmethod
+    def get_default_headers():
+        """
+        获取默认请求头
+        
+        :return: dict - 请求头
+        """
+        return {
+            'User-Agent': HTTPUtils.get_random_user_agent(),
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
+            'Accept-Language': 'zh-CN,zh;q=0.9',
+            'Accept-Encoding': 'gzip, deflate, br',
+            'Connection': 'keep-alive',
+            'Upgrade-Insecure-Requests': '1',
+            'Sec-Fetch-Dest': 'document',
+            'Sec-Fetch-Mode': 'navigate',
+            'Sec-Fetch-Site': 'none',
+            'Sec-Fetch-User': '?1'
+        }
+    
+    @staticmethod
+    def retry_request(func, max_retries=3, delay=1):
+        """
+        重试请求
+        
+        :param func: 请求函数
+        :param max_retries: 最大重试次数
+        :param delay: 重试延迟
+        :return: 函数返回值
+        """
+        import time
+        
+        for i in range(max_retries):
+            try:
+                result = func()
+                if result:
+                    return result
+            except Exception as e:
+                logger.warning(f"请求失败，第 {i+1} 次重试: {e}")
+            
+            if i < max_retries - 1:
+                time.sleep(delay)
+        
+        return None
+    
+    @staticmethod
+    def check_proxy(proxy):
+        """
+        检查代理是否可用
+        
+        :param proxy: 代理URL
+        :return: bool - 是否可用
+        """
+        try:
+            proxies = {
+                'http': proxy,
+                'https': proxy
+            }
+            
+            response = requests.get('https://www.baidu.com', proxies=proxies, timeout=5)
+            return response.status_code == 200
+        except Exception as e:
+            logger.error(f"代理检查失败: {proxy}, 错误: {e}")
+            return False
--- a/domainCheck/app/utils/status_codes.py
+++ b/domainCheck/app/utils/status_codes.py
@@ -0,0 +1,66 @@
+"""Centralized status codes and labels used across detection, database and UI."""
+
+REGISTER_STATUS_PENDING = 0
+REGISTER_STATUS_AVAILABLE = 2
+REGISTER_STATUS_REGISTERED = 3
+REGISTER_STATUS_GRACE = 4
+REGISTER_STATUS_REDEMPTION = 5
+REGISTER_STATUS_PENDING_DELETE = 6
+REGISTER_STATUS_CLIENT_HOLD = 7
+REGISTER_STATUS_SERVER_HOLD = 8
+REGISTER_STATUS_UNKNOWN = 9
+REGISTER_STATUS_FAILED = 10
+
+DETECT_STATUS_PENDING = 0
+DETECT_STATUS_COMPLETED = 1
+DETECT_STATUS_RUNNING = 2
+DETECT_STATUS_BLACKLISTED = 3
+DETECT_STATUS_FAILED = 4
+
+USE_STATUS_UNUSED = 0
+USE_STATUS_USED = 1
+USE_STATUS_SOLD = 2
+USE_STATUS_RESERVED = 3
+
+REVIEW_STATUS_NONE = 0
+REVIEW_STATUS_PENDING = 1
+REVIEW_STATUS_APPROVED = 2
+REVIEW_STATUS_REJECTED = 3
+
+THIRD_PARTY_STATUS_PENDING = 0
+THIRD_PARTY_STATUS_DONE = 1
+
+REGISTER_STATUS_LABELS = {
+    REGISTER_STATUS_PENDING: '待检测',
+    REGISTER_STATUS_AVAILABLE: '可注册',
+    REGISTER_STATUS_REGISTERED: '已注册',
+    REGISTER_STATUS_GRACE: '宽限期',
+    REGISTER_STATUS_REDEMPTION: '赎回期',
+    REGISTER_STATUS_PENDING_DELETE: '删除期',
+    REGISTER_STATUS_CLIENT_HOLD: 'clientHold',
+    REGISTER_STATUS_SERVER_HOLD: 'serverHold',
+    REGISTER_STATUS_UNKNOWN: '状态未知',
+    REGISTER_STATUS_FAILED: '检测失败',
+}
+
+DETECT_STATUS_LABELS = {
+    DETECT_STATUS_PENDING: '待检测',
+    DETECT_STATUS_COMPLETED: '检测完成',
+    DETECT_STATUS_RUNNING: '检测中',
+    DETECT_STATUS_BLACKLISTED: '黑名单',
+    DETECT_STATUS_FAILED: '检测失败',
+}
+
+USE_STATUS_LABELS = {
+    USE_STATUS_UNUSED: '未使用',
+    USE_STATUS_USED: '已经使用',
+    USE_STATUS_SOLD: '已经卖出',
+    USE_STATUS_RESERVED: '已经预定',
+}
+
+REVIEW_STATUS_LABELS = {
+    REVIEW_STATUS_NONE: '无需复核',
+    REVIEW_STATUS_PENDING: '待人工复核',
+    REVIEW_STATUS_APPROVED: '人工通过',
+    REVIEW_STATUS_REJECTED: '人工拒绝',
+}