HeXi/hexi/plugins/nonebot_plugin_video_analysis/utils.py

import re
import unicodedata
from pathlib import Path
from time import strftime, localtime
from typing import List


def get_data_dir() -> Path:
    """插件 data 目录:.../nonebot_plugin_video_analysis/data

    注意 utils.py 位于插件根目录，.parent 即插件根，因此这里写死回到
    插件自身 data/（cookies.txt / list.json / temp 都在此处）。
    """
    return Path(__file__).resolve().parent / "data"


def get_temp_root(sub: str = "") -> Path:
    """插件媒体临时目录:data/temp[/sub] — 下载的媒体先进这里

    发送时优先直接用这里的本地文件，失败才走 S3 链接（见 handlers/sender.py）。
    """
    root = Path(__file__).resolve().parent.parent.parent / "data" / "temp"
    if sub:
        root = root / sub
    root.mkdir(parents=True, exist_ok=True)
    return root


def slugify(text: str, max_length: int = 80) -> str:
    """
    将字符串转换为 URL slug

    规则：
    1. 去掉 #tag
    2. Unicode 归一化
    3. 转小写
    4. 空白和分隔符替换为 -
    5. 移除非法字符
    6. 合并连续 -
    7. 裁剪长度
    """

    # 去掉 #标签
    text = re.sub(r"#\S+", "", text)

    # Unicode 标准化
    text = unicodedata.normalize("NFKC", text)

    # 转小写
    text = text.lower()

    # 空白字符 -> -
    text = re.sub(r"\s+", "-", text)

    # 允许：中文、字母、数字、-
    text = re.sub(r"[^\w\-一-鿿]", "", text)

    # 合并多个 -
    text = re.sub(r"-{2,}", "-", text)

    # 去掉首尾 -
    text = text.strip("-")

    # 控制长度
    if len(text) > max_length:
        text = text[:max_length].rstrip("-")

    return text


def ensure_unique_path(base_path: Path) -> Path:
    """
    确保路径不冲突：如已存在则追加 _2, _3... 后缀
    适用于文件和目录
    """
    if not base_path.exists():
        return base_path

    parent = base_path.parent
    stem = base_path.stem
    ext = base_path.suffix  # 目录无后缀 -> ""

    counter = 2
    while True:
        new_path = parent / f"{stem}_{counter}{ext}"
        if not new_path.exists():
            return new_path
        counter += 1


def clean_filename(filename: str, max_length: int = 120) -> str:
    """
    清理文件名并添加时间前缀
    支持多扩展名，如 .tar.gz
    """

    current_time = strftime("%H-%M-%S", localtime())

    p = Path(filename)

    # 主文件名
    name = p.stem

    # 完整扩展名 (.tar.gz)
    ext = "".join(p.suffixes)

    # Unicode 标准化
    name = unicodedata.normalize("NFKC", name)

    # 去掉 #tag
    name = re.sub(r"#\S+", "", name)

    # 非法字符替换
    name = re.sub(r'[\\/:*?"<>|]', "_", name)

    # 中英文标点
    name = re.sub(r"[&'\"。，：？！《》【】|]", "_", name)

    # 空白 -> _
    name = re.sub(r"\s+", "_", name)

    # 只保留：中文、字母、数字、_
    name = re.sub(r"[^\w一-鿿_]", "", name)

    # 合并 _
    name = re.sub(r"_+", "_", name)

    # 去首尾 _
    name = name.strip("_")

    # 长度控制
    max_name_length = max_length - len(ext) - len(current_time) - 1
    if len(name) > max_name_length:
        name = name[:max_name_length].rstrip("_")

    return f"{current_time}_{name}{ext}"


def parse_netscape_cookies(file_path: str) -> List[dict]:
    """解析 Netscape 格式 cookies 文件"""
    cookies = []
    with open(file_path, "r", encoding="utf-8") as f:
        for line in f:
            line = line.strip()
            if not line or line.startswith("#"):
                continue
            parts = line.split("\t")
            if len(parts) != 7:
                continue
            domain, flag, path, secure, expiry, name, value = parts
            cookie = {
                "name": name,
                "value": value,
                "domain": domain,
                "path": path,
                "secure": secure.upper() == "TRUE",
                "sameSite": "Lax",
            }
            if expiry.isdigit() and int(expiry) > 0:
                cookie["expires"] = int(expiry)
            cookies.append(cookie)
    return cookies