# 安装 Maigret
pip install maigret

# 搜索一个用户名
maigret john_doe

# 扫描全部 3000+ 网站（默认只扫 500 个）
maigret john_doe -a

# 只扫描特定分类的网站
maigret john_doe --tags photo,video
            

class MaigretSite:
    # 已确认存在的用户名（用于自检）
    username_claimed = ""
    # 已确认不存在的用户名
    username_unclaimed = ""
    # URL 模板，{username} 会被替换
    url = ""
    # 网站分类标签
    tags: List[str] = []
    # 标识符类型
    type = "username"
    # 页面中"用户存在"的线索文字
    presense_strs: List[str] = []
    # 页面中"用户不存在"的线索文字
    absence_strs: List[str] = []
            

# checking.py 中定义的所有支持的 ID 类型
SUPPORTED_IDS = (
    "username",
    "yandex_public_id",
    "gaia_id",
    "vk_id",
    "ok_id",
    "wikimapia_uid",
    "steam_id",
    "uidme_uguid",
    "yelp_userid",
)
            

class AsyncioSimpleExecutor:
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        # 用信号量控制最大并发数
        self.semaphore = asyncio.Semaphore(
            kwargs.get('in_parallel', 100)
        )

    async def _run(self, tasks):
        async def sem_task(f, args, kwargs):
            # 获取信号量 —— 等待空位
            async with self.semaphore:
                return await f(*args, **kwargs)

        futures = [
            sem_task(f, args, kwargs)
            for f, args, kwargs in tasks
        ]
        # 同时启动所有任务，但信号量会限制并发
        return await asyncio.gather(*futures)
            

async def _make_request(
    self, session, url, headers,
    allow_redirects, timeout, method, logger,
    payload=None
):
    if method.lower() == 'get':
        request_method = session.get
    elif method.lower() == 'post':
        request_method = session.post

    kwargs = {
        'url': url,
        'headers': headers,
        'allow_redirects': allow_redirects,
        'timeout': timeout,
    }
    async with request_method(**kwargs) as response:
        status_code = response.status
        content = await response.content.read()
        decoded = content.decode(
            response.charset or "utf-8", "ignore"
        )
        return decoded, status_code, error
            

class MaigretCheckStatus(Enum):
    # 用户名已被占用（找到了！）
    CLAIMED = "Claimed"
    # 用户名没人用（没找到）
    AVAILABLE = "Available"
    # 检查过程出错（不确定）
    UNKNOWN = "Unknown"
    # 用户名格式不合法
    ILLEGAL = "Illegal"
            

# 从 maigret.py 中的信息提取逻辑
from socid_extractor import extract, parse

def extract_ids_from_page(url, logger, timeout=5):
    results = {}
    page, _ = parse(url, cookies_str='',
                     headers=None,
                     timeout=timeout)
    info = extract(page)
    for k, v in info.items():
        if 'username' in k:
            results[v] = 'username'
        if k in SUPPORTED_IDS:
            results[v] = k
    return results
            

# 从 maigret.py 中提取新发现的身份标识符
def extract_ids_from_results(
    results, db
):
    ids_results = {}
    for website_name in results:
        dictionary = results[website_name]
        if not dictionary:
            continue

        # 从页面中提取的用户名
        new_usernames = dictionary.get(
            'ids_usernames'
        )
        if new_usernames:
            for u, utype in \
                new_usernames.items():
                ids_results[u] = utype

        # 从链接中提取的 ID
        for url in dictionary.get(
            'ids_links', []
        ):
            ids_results.update(
                db.extract_ids_from_url(url)
            )

    return ids_results
            

class Permute:
    def __init__(self, elements: dict):
        # 支持的分隔符
        self.separators = ["", "_", "-", "."]
        self.elements = elements

    def gather(self, method="strict"):
        perms = {}
        for i in range(1,
            len(self.elements) + 1):
            for subset in \
                permutations(self.elements, i):
                for sep in self.separators:
                    perm = sep.join(subset)
                    perms[perm] = \
                        self.elements[subset[0]]
        return perms
            

# ai.py 中的 API Key 解析逻辑
def resolve_api_key(settings) -> str | None:
    """Resolve OpenAI API key
    Priority: settings > env var"""
    key = getattr(settings, "openai_api_key",
                  None)
    if key:
        return key
    return os.environ.get("OPENAI_API_KEY")

def load_ai_prompt() -> str:
    """Load system prompt"""
    maigret_path = os.path.dirname(
        os.path.realpath(__file__)
    )
    prompt_path = os.path.join(
        maigret_path, "resources",
        "ai_prompt.txt"
    )
    with open(prompt_path, "r") as f:
        return f.read()