HeXi/hexi/plugins/nonebot_plugin_video_analysis/handlers/entry.py

"""消息入口与分派：自动解析 / 主动解析(文本链接 + QQ小程序/分享卡片)。"""

from __future__ import annotations

import html
import re
from typing import Optional

from nonebot import on_message, logger
from nonebot.adapters import Event
from nonebot.rule import to_me
from nonebot_plugin_alconna import UniMessage
from nonebot_plugin_alconna.uniseg import get_target

from ..services.fetchers.bilibili_content import fetch_bilibili_content, resolve_short_link
from ..services.fetchers.rednote_content import fetch_rednote_content
from .douyin import parse_douyin, process_douyin_res
from .sender import PendingMedia, send_pending_media
from .universal import handle_universal
from ..list_proc import AUTO_LINK_KEYWORDS, get_group_auto_link, verify_user

URL_PATTERN = re.compile(r"(https?://\S+)")
XCX_PATTERN = r"QQ小程序(?:]|]|\])"

VALID_HOSTS = [
    "b23.tv",
    "bilibili.com",
    "youtube.com",
    "youtu.be",
    "douyin.com",
    "v.douyin.com",
    "iesdouyin.com",
    "m.douyin.com",
    "jingxuan.douyin.com",
    "x.com",
    "twitter.com",
    "xiaohongshu.com",
    "xhslink.com",
    "xhslink.cn",
]

auto_video_handler = on_message(priority=10, block=False)
active_video_handler = on_message(priority=10, block=False, rule=to_me())


async def _check_access(
    event: Event, *, auto_only: bool = False, msg: str | None = None
) -> tuple[bool, str | None]:
    """统一权限检查。

    auto_only=True  → 自动解析：需白名单 + 开启自动解析，或 auto_link 关键词命中。
    auto_only=False → 主动触发：需非黑名单，群聊还需白名单。

    Returns:
        (allowed, plan) — plan 用于 S3 路由，不允许时为 None
    """
    white, black, auto, plan = await verify_user(event)
    target = get_target(event)

    if target.private:
        if auto_only:
            logger.info("权限分析：自动解析不处理私聊")
            return False, None
        if black:
            logger.info(f"权限分析：黑名单用户私聊，不回复: {event.get_user_id()}")
            return False, None
        logger.info("权限分析：私聊，直接解析")
        return True, None

    group_id = str(event.group_id)

    if not white:
        logger.info(f"权限分析：群 {group_id} 不在白名单，不做处理")
        return False, None

    if auto_only and not auto:
        if msg is not None and await _match_auto_link(event, msg):
            logger.info(f"权限分析：群 {group_id} 未开启自动解析，但自动链接关键词命中")
        else:
            logger.info(f"权限分析：群 {group_id} 未开启自动解析")
            return False, None

    if not auto_only and black:
        logger.info(f"权限分析：黑名单用户，不回复: {event.get_user_id()}")
        return False, None

    logger.info(
        f"权限分析：群 {group_id} 权限通过 — "
        f"自动解析: {auto}, 方案: {plan or '默认(PLANC)'}"
    )
    return True, plan


async def _match_auto_link(event: Event, msg: str) -> bool:
    """消息中的 URL 是否命中群配置的 auto_link 关键词。"""
    keywords = await get_group_auto_link(event)
    if not keywords:
        return False
    urls = URL_PATTERN.findall(msg)
    if not urls:
        return False
    for kw in keywords:
        domains = AUTO_LINK_KEYWORDS.get(kw, (kw,))
        if any(any(domain in url for domain in domains) for url in urls):
            logger.info(f"自动链接：关键词 {kw} 命中消息 {urls}")
            return True
    return False


@auto_video_handler.handle()
async def handle_auto_video(event: Event):
    msg = str(event.get_message()).strip()
    allowed, plan = await _check_access(event, auto_only=True, msg=msg)
    if allowed:
        await match_message(event, plan=plan)


@active_video_handler.handle()
async def handle_active_video(event: Event):
    allowed, plan = await _check_access(event, auto_only=False)
    if allowed:
        await match_message(event, plan=plan)


async def match_message(event: Event, plan: str | None = None):
    """消息匹配与分派：文本链接 / QQ小程序卡片统一走 dispatch_url。"""
    msg = str(event.get_message()).strip()
    logger.info(f"消息解析：获取到的消息：{msg}")
    is_private = get_target(event).private

    message = None
    public_url = None

    if re.search(XCX_PATTERN, msg) or "CQ:json" in msg or "CQ:share" in msg:
        logger.info("消息解析：检测到 CQ 卡片")
        url = await _extract_xcx_url(msg)
        logger.info(f"消息解析：卡片链接：{url}")
        if not url or not any(domain in url for domain in VALID_HOSTS):
            return
        message, public_url = await dispatch_url(url, is_private, plan=plan)
        if not message:
            return
    else:
        urls = URL_PATTERN.findall(msg)
        for url in urls:
            logger.info(f"消息解析：作品链接：{url}")
            message, public_url = await dispatch_url(url, is_private, plan=plan)
            if message:
                break
        if not message:
            return

    if isinstance(message, PendingMedia):
        ok, pub = await send_pending_media(message)
        if pub:
            await UniMessage.text(f"{pub}").send()
        if not ok:
            await UniMessage.text(f"媒体发送失败：{url}").send()
    else:
        if public_url:
            await UniMessage.text(f"{public_url}").send()
        await message.send()


async def dispatch_url(
    url: str,
    is_private: bool,
    plan: str | None = None,
) -> tuple[Optional[UniMessage], Optional[str]]:
    """按平台分派解析（文本链接与小程序卡片共用）。"""
    url = url.rstrip("，。！？、；：）】》\"'）")

    if "b23.tv" in url or "bili2233.cn" in url:
        resolved = await resolve_short_link(url)
        if resolved:
            logger.info(f"b23 短链重定向: {url} -> {resolved}")
            url = resolved

    if "douyin.com" in url or "v.douyin.com" in url or "iesdouyin.com" in url:
        await UniMessage.text("检测到链接，正在处理，请稍候...").send()
        try:
            title, parsed_path, image_post = await parse_douyin(url)
            return await process_douyin_res(
                title, parsed_path, is_private, image_post, plan=plan
            )
        except Exception:
            await UniMessage.text(f"无法解析到媒体：{url}").send()
            logger.exception(f"媒体解析：无法解析到媒体：{url}")
            return None, None

    if any(
        kw in url
        for kw in (
            "bilibili.com/opus",
            "bilibili.com/dynamic",
            "t.bilibili.com",
            "bilibili.com/read",
        )
    ):
        await UniMessage.text("检测到链接，正在处理，请稍候...").send()
        try:
            title, parsed_path = await fetch_bilibili_content(url)
            if not title and parsed_path is None:
                await UniMessage.text(f"无法解析到内容：{url}").send()
                return None, None
            if parsed_path == []:
                await UniMessage.text(title).send()
                return None, None
            return await process_douyin_res(
                title, parsed_path, is_private,
                isinstance(parsed_path, list), plan=plan,
            )
        except Exception:
            await UniMessage.text(f"无法解析到内容：{url}").send()
            logger.exception(f"B站内容解析：无法解析：{url}")
            return None, None

    if "xiaohongshu.com" in url or "xhslink." in url:
        await UniMessage.text("检测到链接，正在处理，请稍候...").send()
        try:
            title, parsed_path = await fetch_rednote_content(url)
            if not title and parsed_path is None:
                await UniMessage.text(f"无法解析到内容：{url}").send()
                return None, None
            if parsed_path == []:
                await UniMessage.text(title).send()
                return None, None
            return await process_douyin_res(
                title, parsed_path, is_private,
                isinstance(parsed_path, list), plan=plan,
            )
        except Exception:
            await UniMessage.text(f"无法解析到内容：{url}").send()
            logger.exception(f"小红书解析：无法解析：{url}")
            return None, None

    if any(domain in url for domain in VALID_HOSTS):
        await UniMessage.text("检测到链接，正在处理，请稍候...").send()
        try:
            return await handle_universal(url, is_private, plan=plan)
        except Exception as e:
            logger.exception(e)
            await UniMessage.text("下载过程中出现错误。").send()
            return None, None

    return None, None


async def _extract_xcx_url(msg: str) -> Optional[str]:
    """从 CQ 卡片消息中提取跳转 URL（保留 query 参数）。"""
    match = re.search(r'"qqdocurl":"(.*?)"', msg)
    if not match:
        match = re.search(r'"jumpUrl":"(.*?)"', msg)
    if not match:
        logger.warning("未找到 qqdocurl/jumpUrl 字段")
        return None

    raw_url = match.group(1)
    unescaped = html.unescape(raw_url)
    cleaned_url = unescaped.replace(r"\/", "/")
    logger.info(f"卡片提取链接: {cleaned_url}")
    return cleaned_url