# -*- coding: UTF-8 -*-
'''
@Project :domainScanDemo
@File    :baidu.py
@IDE     :PyCharm
@Author  :梦伴
@Date    :2026/3/29 21:54
@explain : 百度域名检测工具 - 包含百度搜索结果查询和百度安全API检测功能
'''

import os
import random  # 随机数生成模块，用于随机选择浏览器类型
import re  # 正则表达式模块，用于从HTML中提取搜索结果
import threading
import time

from loguru import logger  # 日志记录模块，用于记录程序运行日志
from curl_cffi import requests  # curl_cffi库，支持浏览器模拟的HTTP请求
from typing import List, Optional, Union, Any  # 类型提示

BAIDU_SITE_TIMEOUT_PROXY = max(
    0.8,
    float(os.getenv("DOMAINCHECK_BAIDU_TIMEOUT_PROXY", "1.4") or 1.4),
)
BAIDU_SITE_TIMEOUT_DIRECT = max(
    1.0,
    float(os.getenv("DOMAINCHECK_BAIDU_TIMEOUT_DIRECT", "1.8") or 1.8),
)
BAIDU_SCAN_TIMEOUT_PROXY = max(
    1.0,
    float(os.getenv("DOMAINCHECK_BAIDU_SCAN_TIMEOUT_PROXY", "1.6") or 1.6),
)
BAIDU_SCAN_TIMEOUT_DIRECT = max(
    1.2,
    float(os.getenv("DOMAINCHECK_BAIDU_SCAN_TIMEOUT_DIRECT", "2.0") or 2.0),
)
BAIDU_SITE_URL = 'https://m.baidu.com/s'
BAIDU_SAFE_SCAN_URL = 'https://mobsec-sec.baidu.com/3.1/scanurl'
BAIDU_SITE_PATTERN = r'<!--s-text-->([^<]+)<!--/s-text-->'
_THREAD_LOCAL = threading.local()


def _resolve_baidu_timeout(proxies: dict = None, budget_seconds: Optional[float] = None, *, scan: bool = False) -> float:
    if scan:
        timeout = BAIDU_SCAN_TIMEOUT_PROXY if proxies else BAIDU_SCAN_TIMEOUT_DIRECT
    else:
        timeout = BAIDU_SITE_TIMEOUT_PROXY if proxies else BAIDU_SITE_TIMEOUT_DIRECT
    timeout = float(timeout or 0.0)
    if budget_seconds not in (None, "", 0, "0"):
        timeout = min(timeout, max(0.6, float(budget_seconds or 0.0)))
    return max(0.6, timeout)

BAIDU_SITE_COOKIES = {
    'BIDUPSID': '053DBE4D820C6EFB729DC7B13B1F82B2',
    'PSTM': '1775657119',
    'H_PS_PSSID': '63148_67862_67986_68002_68142_68148_68152_68141_68165_68189_68226_68267_68296_68336_68369_68453_68438_68464_68541_68546_68558_68520_68589_68621_68615_68606_68601_68682_68671_68735_68544_68733_68766_68807_68901_68918_68836_68921_68955_68976_68997_69007_69010_69018_69024_69014',
    'BAIDUID': '053DBE4D820C6EFB729DC7B13B1F82B2:FG=1',
    'BDORZ': 'B490B5EBF6F3CD402E515D22BCDA1598',
    'BAIDUID_BFESS': '053DBE4D820C6EFB729DC7B13B1F82B2:FG=1',
    'BA_HECTOR': 'ah0l24210la4050l0g0k0g2g0h20071ktcocj27',
    'ZFY': 'Qxyr75Xm7o8zUxYzuFnYoW7cnS:AnVp:BpnrNVkr3usno:C',
    'delPer': '0',
    'BAIDUID_REF': '053DBE4D820C6EFB729DC7B13B1F82B2:FG=1',
    'H_WISE_SIDS': '110085_661771_667681_673676_683089_682564_685373_660925_687556_686285_690306_690303_690478_690576_690334_691545_685595_690883_692754_692777_692118_692910_693221_693364_693403_693656_693941_694124_693392_694171_694236_693996_694316_694324_693886_694409_694379_694696_694780_694783_692006_694884_694918_694996_694991_695032_695118_694840_695140_695193_695110_695262_688610_694933_695278_694865_695214_695374_690651_694577_692378_695452_695457_695480_695603_695642_695631_695668_695824_695843_695866_695888_695892_695897_695975_694177_695900_695939_696145_696150_696153_696069_696078_696066_694359_696288_696308_694985_696297_695715_696128_696313_696457_696431_696473_696492_696590_693385_696610_696682_696679_696662_696651_696655_696658_696673_696643_696110_696729_696733_696772_8000116_8000133_8000138_8000159_8000163_8000167_8000176_8000186_8000190_8000204',
    'H_WISE_SIDS_BFESS': '110085_661771_667681_673676_683089_682564_685373_660925_687556_686285_690306_690303_690478_690576_690334_691545_685595_690883_692754_692777_692118_692910_693221_693364_693403_693656_693941_694124_693392_694171_694236_693996_694316_694324_693886_694409_694379_694696_694780_694783_692006_694884_694918_694996_694991_695032_695118_694840_695140_695193_695110_695262_688610_694933_695278_694865_695214_695374_690651_694577_692378_695452_695457_695480_695603_695642_695631_695668_695824_695843_695866_695888_695892_695897_695975_694177_695900_695939_696145_696150_696153_696069_696078_696066_694359_696288_696308_694985_696297_695715_696128_696313_696457_696431_696473_696492_696590_693385_696610_696682_696679_696662_696651_696655_696658_696673_696643_696110_696729_696733_696772_8000116_8000133_8000138_8000159_8000163_8000167_8000176_8000186_8000190_8000204',
    'MSA_PBT': '147',
    'MSA_ZOOM': '1000',
    'wpr': '0',
    'COOKIE_SESSION': '0_0_0_0_0_0_0_0_0_0_0_0_0_1775657396%7C1%230_0_0_0_0_0_0_0_1775657396%7C1',
    'MSA_PHY_WH': '1440_3440',
    'POLYFILL': '0',
    'MSA_WH': '1254_940',
    'kleck': '7ce2abac229d2e8ba435a8bcc6256f57f53e9d08954443bf',
    'PSCBD': '16%3A1%3A3',
    'SE_LAUNCH': '5%3A1775657396_16%3A29594323%3A3',
    'BDSVRTM': '3',
    'PSINO': '6',
    '__bsi': '17976785662214065461_00_7_R_R_6_0303_c02f_Y',
}

BAIDU_SITE_HEADERS = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'Sec-Fetch-Dest': 'document',
    'Sec-Fetch-Mode': 'navigate',
    'Sec-Fetch-Site': 'none',
    'Sec-Fetch-User': '?1',
    'Upgrade-Insecure-Requests': '1',
    '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 Edg/146.0.0.0',
    'sec-ch-ua': '"Chromium";v="146", "Not-A.Brand";v="24", "Microsoft Edge";v="146"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Windows"',
}

BAIDU_SAFE_SCAN_HEADERS = {
    'Cache-Control': 'no-cache',
    'Content-Type': 'application/json; charset=utf-8',
    'Host': 'mobsec-sec.baidu.com',
    'User-Agent': 'okhttp/3.12.12',
}

BAIDU_SAFE_SCAN_PARAMS = {
    'auth_ver': '2',
    'appkey': '4665fd2c6b0922a551e8ae74',
    'nonce': '1751309255340',
    'lc': '77qHTv4VtmRiXYtd',
    'pkg': 'com.baidu.searchbox',
    'vc': '-1',
    'cuid': 'CF0E6FCCD824D146605C16AC1C8BAC95%7CVFWAO56TC',
    'tk': '',
    'type': '3',
    'vn': '2.6.0',
    's': 'fdfef2ce96c1c7193f9b80425020f63e',
}


def _get_thread_session():
    session = getattr(_THREAD_LOCAL, "session", None)
    if session is None:
        session = requests.Session()
        _THREAD_LOCAL.session = session
    return session

def check_site(domain: str, sensitive_words: Optional[List[str]] = None, proxies: dict = None, budget_seconds: Optional[float] = None) -> Union[
    None, tuple[bool, str], list[Any]]:
    '''
    通过百度搜索查询域名的相关信息
    
    使用curl_cffi模拟浏览器访问百度搜索，获取site:domain的搜索结果标题
    
    :param domain: 待查询的域名（如：www.baidu.com）
    :param proxies: 代理配置（如：{'http': 'http://127.0.0.1:7890', 'https': 'http://127.0.0.1:7890'}）
    :return: list - 搜索结果标题列表，如果查询失败则返回空列表
    '''
    # 初始化敏感词列表
    if sensitive_words is None:
        sensitive_words = []

    try:  # try-except块，用于捕获网络请求中的异常
            # 构建搜索查询参数
            # wd: 搜索关键词，格式为site:域名
            params = {
                'wd': f'site:{domain}'  # 搜索site:domain，限制搜索结果为指定域名
            }

            session = _get_thread_session()
            request_started_at = time.perf_counter()
            logger.info(
                f"百度site阶段: domain={domain} | stage=request_start | proxy={'yes' if proxies else 'no'}"
            )
            response = session.get(
                BAIDU_SITE_URL,
                params=params,
                headers=BAIDU_SITE_HEADERS,
                cookies=BAIDU_SITE_COOKIES,
                timeout=_resolve_baidu_timeout(proxies, budget_seconds=budget_seconds, scan=False),
                proxies=proxies,
            )
            logger.info(
                f"百度site阶段: domain={domain} | stage=request_done | status={response.status_code} "
                f"| elapsed_ms={int((time.perf_counter() - request_started_at) * 1000)}"
            )
            response_text = response.content.decode('utf-8', errors='ignore')
            # 使用正则表达式提取搜索结果标题
            # re.findall()返回所有匹配的结果列表
            # 正则解释：匹配 <!--s-text--> 和 <!--/s-text--> 之间的内容
            match = re.findall(BAIDU_SITE_PATTERN, response_text, re.S)

            # 返回匹配结果列表，如果没有匹配则返回空列表
            search_results= match if match else []
            logger.info(
                f"百度site阶段: domain={domain} | stage=parsed | result_count={len(search_results)}"
            )

            # 如果没有搜索结果，直接返回通过
            if not search_results:
                return True, ''

            # 检查每个搜索结果是否包含敏感词
            for result in search_results:
                for sensitive_word in sensitive_words:
                    # 使用正则表达式检查是否包含敏感词
                    if re.search(sensitive_word, result, re.IGNORECASE):
                        logger.warning(f'检测到敏感词: {sensitive_word} 在结果: {result}')
                        return False, f'检测到敏感词: {sensitive_word} 在结果: {result}'

            # 所有搜索结果都不包含敏感词，返回通过
            return True, ''
    except Exception as e:  # 捕获所有异常
        logger.error(f"百度site检测失败: {domain}, 错误: {e}")
        return False, str(e)


def baidu(domain: str, proxies: dict = None, budget_seconds: Optional[float] = None) -> str:
    '''
    通过百度安全API检测域名安全状态
    
    调用百度移动安全API检测域名是否为风险网站
    
    :param domain: 待检测的域名（如：www.baidu.com）
    :param proxies: 代理配置（如：{'http': 'http://127.0.0.1:7890', 'https': 'http://127.0.0.1:7890'}
    :return: str - 安全状态描述（"风险网站提示"、"高危网站提示"或"正常"），如果检测失败则返回错误信息
    '''
    # 构建JSON请求数据
    json_data = {
        'url': f'https://{domain}/',  # 待检测的URL（添加https协议头）
    }

    # 提取URL作为后续获取结果的键
    key = json_data['url']

    try:  # try-except块，用于捕获API调用中的异常
            # 发送POST请求到百度安全API
            # url: API接口地址
            # params: 查询参数
            # headers: HTTP请求头
            # json: JSON请求数据
            # proxies: 代理配置
            # .json(): 解析JSON响应
            session = _get_thread_session()
            request_started_at = time.perf_counter()
            logger.info(
                f"百度安全阶段: domain={domain} | stage=request_start | proxy={'yes' if proxies else 'no'}"
            )
            response = session.post(
                BAIDU_SAFE_SCAN_URL,
                params=BAIDU_SAFE_SCAN_PARAMS,
                headers=BAIDU_SAFE_SCAN_HEADERS,
                json=json_data,
                proxies=proxies,
                timeout=_resolve_baidu_timeout(proxies, budget_seconds=budget_seconds, scan=True),
            )
            logger.info(
                f"百度安全阶段: domain={domain} | stage=request_done | status={response.status_code} "
                f"| elapsed_ms={int((time.perf_counter() - request_started_at) * 1000)}"
            )
            response = response.json()

            # # 记录API响应（调试用）
            # logger.info(response)

            # 安全状态码映射表
            msgs = {
                2193: '风险网站提示',  # 风险网站
                2243: '高危网站提示',  # 高危网站
                '_': '正常'  # 默认正常
            }

            # 从响应中获取安全等级并映射为状态描述
            # response['response']['datas'][key].get('grand_level', 'level'): 获取安全等级，默认值为'level'
            # msgs.get(): 根据安全等级获取对应的状态描述，默认值为'正常'
            return msgs.get(response['response']['datas'][key].get('grand_level', 'level'), '正常')

    except Exception as e:  # 捕获所有异常
        logger.error(f"百度网页安全中心检测失败: {domain}, 错误: {e}")
        return str(e)


# # ========================= 【测试代码】 =========================
# if __name__ == '__main__':  # 程序入口，当直接运行此文件时执行以下代码
#     # proxies = get_proxies()
#     proxies = None
#     # 测试用例1：查询域名搜索结果
#     logger.info("=== 测试百度搜索结果查询 ===")
#     test_domain_1 = '920zl.com'
#     logger.info(f"查询域名: {test_domain_1}")
#
#     result_1 = check_site(test_domain_1, proxies=proxies)
#     logger.info(result_1)

    #
    # # 测试用例3：检测域名安全状态
    # logger.info("=== 测试域名安全检测 ===")
    # test_domain_3 = 'baidu.com'
    # logger.info(f"检测域名: {test_domain_3}")
    #
    # result_3 = baidu(test_domain_3, proxies=proxies)
    # logger.info(f"安全状态: {result_3}")
    # logger.debug(proxies)

    # domains = ['Lqyingye.com', 'tjjinLikeji.com', 'guokangLxs.com', 'zhuoyijz.com', 'jiandanrongyi.com', 'fromhhc.com',
    #           'djxow.com', '725game.com', 'gcLpchd.cn', '6rdb.com.cn', 'sunmantech.com', 'hroxa.com', 'guLhu65.cn',
    #           'xxjdch.com', '7e7fm1.cn', 'kaoxueb.com', 'jabas.cn', 'shzhongyi.com', 'figuangze.com', 'eztw9k.cn',
    #           'foxok.com', 'oLLbmr.com', 'vwpwwkp.cn', 'cbmrs.com', 'zaozhuang56.com', 'hengxiangracing.com',
    #           'jdyfbpq.cn', 'czca.cn', 'shibingxiongdi.com', 'ubxbm.cn', 'ydbaoshi.com', '2046hd.cn', 'mffmcp.com',
    #           'hgLdhzz.com', 'okswmi.cn', 'caidaozg.com', 'dkdywx.cn', 'qkjps.com', 'Lwxgk.cn', 'drtechnoLogy.cn',
    #           'akcie.cn', '588uu.com', 'kuaiyijian.net', 'c5b.cn', 'faka866.cn', 'wiraf03.cn', 'bobjibar.com',
    #           '166233.cn', 'adLfjcjq.cn', 'whrsom.com']
    # for domain in domains:
    #     result_1 = check_site(domain)
    #     logger.info(f"搜索结果标题数: {len(result_1)}")
    #     for i, title in enumerate(result_1, 1):
    #         logger.info(f"  结果{i}: {title}")
    #     time.sleep(1)