feat(video-analysis): 群策略 v3 / 群文件投递通道 / Web 管理页

- policy.py：per-group 正交策略（自动解析 / 自动策略 / 禁用策略 / 存储 A·B·C / 公网 / 链接 / 群文件 + 平台限定），list.json v1/v2 → v3 自动迁移，写入统一走 PolicyStore（加锁 + .tmp 原子替换 + 字段归一） - 群文件并行通道 group_file.py：打包 zip（可选 pyzipper AES-256）后优先走 S3 预签名、本地直传兜底；设了密码但 pyzipper 不可用就放弃上传，不退化成明文 - list_proc.py 收敛到「视频策略」统一入口，权限判定改走 policy - Web 管理页 /hub/video_analysis（群策略 + 链接解析面板）与 services/web_jobs.py （只复用纯函数层，Web 上下文不发消息；内存任务表 + 并发闸门 + 超时） - 媒体命名统一到 utils.py（{作者}_{作者id}/{作品名}[_短码]），cleanup 回收空目录 - 测试：policy / 命名 / 群文件 / web_jobs 四组顺带 pyproject 的 pytest 加 testpaths=tests（避免收进 debug/ 下的调试脚本）。 Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-09-22 14:23:32 +08:00
parent 51b08ccb68
commit 4badcfcf32
29 changed files with 4838 additions and 670 deletions
@@ -16,7 +16,8 @@ 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
+from ..list_proc import get_policy, is_group_whitelisted, is_user_blacklisted
+from ..policy import Policy, match_platform

 URL_PATTERN = re.compile(r"(https?://\S+)")
 XCX_PATTERN = r"QQ小程序(?:&amp;#93;|&#93;|\])"
@@ -44,106 +45,119 @@ 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]:
+) -> tuple[bool, Policy | 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。
+    auto_only=True  → 自动解析：需白名单群 + （开启自动解析或消息命中自动策略）。
+    auto_only=False → 主动触发：需白名单群 + 非黑名单用户。
+
+    私聊不做自动解析，读 default 节策略后直接解析。
+    禁用策略（ban_link）是消息级的（按链接判定），见 match_message。

    Returns:
-        (allowed, plan) — plan 用于 S3 路由，不允许时为 None
+        (allowed, policy) — policy 决定存储/投递，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:
+        if is_user_blacklisted(event):
            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
+        return True, get_policy(event)

    group_id = str(event.group_id)

-    if not white:
+    if not is_group_whitelisted(event):
        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:
+    if is_user_blacklisted(event):
        logger.info(f"权限分析：黑名单用户，不回复: {event.get_user_id()}")
        return False, None

+    policy = get_policy(event)
+
+    if auto_only and not policy.auto and not _match_auto_link(msg or "", policy):
+        logger.info(f"权限分析：群 {group_id} 未开启自动解析且未命中自动策略")
+        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)'}"
+        f"权限分析：群 {group_id} 权限通过 — 自动解析: {policy.auto}, "
+        f"存储: {policy.plan}, 公网: {policy.upload_public}, "
+        f"群文件: {policy.upload_group_file}"
    )
-    return True, plan
+    return True, policy


-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:
+def _match_auto_link(msg: str, policy: Policy) -> bool:
+    """消息中的 URL 是否命中群策略的自动策略（auto_link）。"""
+    if not policy.auto_link:
        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}")
+    for url in URL_PATTERN.findall(msg):
+        platform = policy.auto_matched(url)
+        if platform:
+            logger.info(f"自动策略：{platform} 命中消息 {url}")
            return True
    return False


+def _skip_banned(url: str, policy: Policy) -> bool:
+    """链接是否命中禁用策略（命中即静默丢弃，只记日志）。"""
+    platform = policy.banned(url)
+    if platform:
+        logger.info(f"禁用策略：{platform} 已禁用，忽略链接 {url}")
+        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)
+    allowed, policy = await _check_access(event, auto_only=True, msg=msg)
+    if allowed and policy is not None:
+        await match_message(event, policy)


@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)
+    allowed, policy = await _check_access(event, auto_only=False)
+    if allowed and policy is not None:
+        await match_message(event, policy)


-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。"""
+async def match_message(event: Event, policy: Policy):
+    """消息匹配与分派：文本链接 / QQ小程序卡片统一走 dispatch_url。
+
+    命中禁用策略的链接在这里丢弃；消息里还有其它可用链接则继续解析。
+    """
    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
+    url = ""

    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)
+        url = await _extract_xcx_url(msg) or ""
        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 _skip_banned(url, policy):
+            return
+        message, public_url = await dispatch_url(url, is_private, policy)
        if not message:
            return
    else:
-        urls = URL_PATTERN.findall(msg)
+        urls = [u for u in URL_PATTERN.findall(msg) if not _skip_banned(u, policy)]
        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)
+            message, public_url = await dispatch_url(url, is_private, policy)
            if message:
                break
        if not message:
@@ -151,12 +165,12 @@ async def match_message(event: Event, plan: str | None = None):

    if isinstance(message, PendingMedia):
        ok, pub = await send_pending_media(message, event)
-        if pub:
+        if pub and policy.sends_link:
            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:
+        if public_url and policy.sends_link:
            await UniMessage.text(f"{public_url}").send()
        await message.send()

@@ -164,7 +178,7 @@ async def match_message(event: Event, plan: str | None = None):
 async def dispatch_url(
    url: str,
    is_private: bool,
-    plan: str | None = None,
+    policy: Policy,
 ) -> tuple[UniMessage | None, str | None]:
    """按平台分派解析（文本链接与小程序卡片共用）。"""
    url = url.rstrip("，。！？、；：）】》\"'）")
@@ -175,6 +189,9 @@ async def dispatch_url(
            logger.info(f"b23 短链重定向: {url} -> {resolved}")
            url = resolved

+    # 平台标签：短链重定向之后再判定（群文件限定平台用）
+    platform = match_platform(url)
+
    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:
@@ -186,7 +203,8 @@ async def dispatch_url(
                logger.warning(f"媒体解析：未能获取到作品：{url}")
                return None, None
            return await process_douyin_res(
-                title, parsed_path, is_private, image_post, plan=plan
+                title, parsed_path, is_private, image_post,
+                policy=policy, platform=platform,
            )
        except Exception:
            await UniMessage.text(f"无法解析到媒体：{url}").send()
@@ -213,7 +231,7 @@ async def dispatch_url(
                return None, None
            return await process_douyin_res(
                title, parsed_path, is_private,
-                isinstance(parsed_path, list), plan=plan,
+                isinstance(parsed_path, list), policy=policy, platform=platform,
            )
        except Exception:
            await UniMessage.text(f"无法解析到内容：{url}").send()
@@ -232,7 +250,7 @@ async def dispatch_url(
                return None, None
            return await process_douyin_res(
                title, parsed_path, is_private,
-                isinstance(parsed_path, list), plan=plan,
+                isinstance(parsed_path, list), policy=policy, platform=platform,
            )
        except Exception:
            await UniMessage.text(f"无法解析到内容：{url}").send()
@@ -242,7 +260,7 @@ async def dispatch_url(
    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)
+            return await handle_universal(url, is_private, policy, platform)
        except Exception as e:
            logger.exception(e)
            await UniMessage.text("下载过程中出现错误。").send()