feat: 创作工作台统一 + AI味检测/白标 + 移动端补全 + 合规发布闭环

- 新增创作工作台 studio.html：合并选题/内容工厂/文章管理为单一 tab 入口（iframe embed 模式） - 新增 AI味检测模块（ai_slop API + 页面，合规软硬问题分级） - 新增白标品牌配置（branding API + 页面 + deploy 私有化交付包） - 发布闭环：publishing 放宽至 editor + records/mark-published 接口 - 移动端响应式补全（admin/calendar/ai-slop 表格卡片兜底） - 修复菜单幂等播种缺陷（按 path 对齐，避免功能页孤立） - 新增短视频脚本 shortvideo.py 与 2026 市场调研简报
2026-07-11 12:36:01 +08:00
parent 3d596275d5
commit 7e953afbd2
39 changed files with 2418 additions and 311 deletions
@@ -25,8 +25,7 @@ def _get_cmd(topic_ids: List[str] = None):
    cmd = [str(venv_python), str(script_path)] if venv_python.exists() else ["python3", str(script_path)]
    if topic_ids:
        cmd.extend(["--topic-ids", ','.join(topic_ids)])
-    else:
-        cmd.append("--today-only")
+    # 不再使用 --today-only，避免三平台串行撰写时小红书文章错过审查窗口
    return cmd

 def run_optimizer(topic_ids: List[str] = None):
@@ -58,6 +58,7 @@ MODULES = {
    "scheduled_task_monitor": {"name": "⏰ 任务监控", "cron": "*"},
    "scheduled_rank_tracker": {"name": "🔍 搜索排名追踪", "cron": "07:00"},
    "scheduled_geo_tracker": {"name": "🌐 AI 搜索引用追踪", "cron": "07:30"},
+    "scheduled_shortvideo": {"name": "🎬 短视频拆条", "cron": "08:00"},
 }

 LOG_FILE_MAP = {
@@ -71,6 +72,7 @@ LOG_FILE_MAP = {
    "scheduled_task_monitor": "task_monitor",
    "scheduled_rank_tracker": "rank_tracker",
    "scheduled_geo_tracker": "geo_tracker",
+    "scheduled_shortvideo": "shortvideo",
 }

 def _log_to_file(module_id: str, status: str, message: str = None, error_trace: str = None):
@@ -188,6 +190,7 @@ class TaskScheduler:
            ("scheduled_reset_search_usage", self._run_reset_search_usage, "搜索用量重置"),
            ("scheduled_rank_tracker", self._run_rank_tracker, "搜索排名追踪"),
            ("scheduled_geo_tracker", self._run_geo_tracker, "AI 搜索引用追踪"),
+            ("scheduled_shortvideo", self._run_shortvideo, "短视频拆条"),
        ]

        for module_id, fn, name in MODULE_JOBS:
@@ -418,41 +421,48 @@ class TaskScheduler:
            count = 0
            for topic in topics:
                platform_urls = topic.platform_urls or {}
-                zhihu_url = platform_urls.get("zhihu", "")
-                if not zhihu_url:
-                    continue
-                m = re.search(r'zhuanlan\.zhihu\.com/p/(\d+)', zhihu_url)
-                if not m:
-                    continue
-                post_id = m.group(1)
-                api_url = f"https://zhuanlan.zhihu.com/api/posts/{post_id}"
-                try:
-                    resp = http_requests.get(api_url, headers={"User-Agent": ua}, timeout=10)
-                    if resp.status_code != 200:
+                for platform, url in platform_urls.items():
+                    if not url:
+                        continue
+                    if platform == "zhihu":
+                        m = re.search(r'zhuanlan\.zhihu\.com/p/(\d+)', url)
+                        if not m:
+                            continue
+                        post_id = m.group(1)
+                        api_url = f"https://zhuanlan.zhihu.com/api/posts/{post_id}"
+                        try:
+                            resp = http_requests.get(api_url, headers={"User-Agent": ua}, timeout=10)
+                            if resp.status_code != 200:
+                                continue
+                            raw = resp.json()
+                            existing = db.query(ContentMetrics).filter(
+                                ContentMetrics.topic_id == topic.id,
+                                ContentMetrics.platform == "zhihu"
+                            ).first()
+                            metric_data = {
+                                "views": raw.get("voteup_count", raw.get("views_count", 0)),
+                                "likes": raw.get("voteup_count", 0),
+                                "favorites": raw.get("favorite_count", 0),
+                                "comments": raw.get("comment_count", raw.get("comments_count", 0)),
+                                "shares": raw.get("share_count", 0),
+                                "last_fetched": datetime.now(),
+                                "publish_url": url,
+                                "data_snapshot": raw,
+                            }
+                            if existing:
+                                for k, v in metric_data.items():
+                                    setattr(existing, k, v)
+                            else:
+                                db.add(ContentMetrics(topic_id=topic.id, platform="zhihu", **metric_data))
+                            count += 1
+                        except Exception:
+                            continue
+                    elif platform in ("wechat_mp", "xiaohongshu"):
+                        logger.info("平台 %s 无公开指标 API，跳过", platform)
                        continue
-                    raw = resp.json()
-                    existing = db.query(ContentMetrics).filter(
-                        ContentMetrics.topic_id == topic.id,
-                        ContentMetrics.platform == "zhihu"
-                    ).first()
-                    metric_data = {
-                        "views": raw.get("voteup_count", raw.get("views_count", 0)),
-                        "likes": raw.get("voteup_count", 0),
-                        "favorites": raw.get("favorite_count", 0),
-                        "comments": raw.get("comment_count", raw.get("comments_count", 0)),
-                        "shares": raw.get("share_count", 0),
-                        "last_fetched": datetime.now(),
-                        "publish_url": zhihu_url,
-                        "data_snapshot": raw,
-                    }
-                    if existing:
-                        for k, v in metric_data.items():
-                            setattr(existing, k, v)
                    else:
-                        db.add(ContentMetrics(topic_id=topic.id, platform="zhihu", **metric_data))
-                    count += 1
-                except Exception:
-                    continue
+                        logger.info("平台 %s 暂无指标同步支持，跳过", platform)
+                        continue
            if count:
                db.commit()
                logger.info("[Scheduled] Metrics sync completed: synced %d zhihu articles", count)
@@ -661,6 +671,46 @@ class TaskScheduler:
                      started_at=started, finished_at=datetime.now(timezone.utc))
            logger.exception("[GeoTracker] AI 搜索引用追踪失败: %s", e)

+    def _run_shortvideo(self):
+        """每日将前一日「待发布」选题的长文拆条为短视频脚本"""
+        started = datetime.now(timezone.utc)
+        log_id = _log_task("scheduled_shortvideo", "running", started_at=started)
+        try:
+            from ..database import SessionLocal
+            from ..models import Topic
+            db = SessionLocal()
+            try:
+                topics = db.query(Topic).filter(
+                    Topic.status.in_(["ready", "待发布", "pending_publish"])
+                ).order_by(Topic.ready_at.desc().nullslast()).limit(3).all()
+            finally:
+                db.close()
+            if not topics:
+                _log_task("scheduled_shortvideo", "success", log_id=log_id,
+                          message="无待拆条选题", started_at=started, finished_at=datetime.now(timezone.utc))
+                return
+            import subprocess
+            total = 0
+            for t in topics:
+                res = subprocess.run(
+                    [sys.executable, str(PROJECT_ROOT / "scripts" / "shortvideo.py"), "--topic-id", t.id, "--count", "3"],
+                    capture_output=True, text=True, timeout=600
+                )
+                if res.returncode == 0:
+                    total += 1
+            _log_task("scheduled_shortvideo", "success", log_id=log_id,
+                      message=f"拆条完成: {total}/{len(topics)} 选题",
+                      result_data={"topics": len(topics), "done": total},
+                      started_at=started, finished_at=datetime.now(timezone.utc))
+            logger.info("[ShortVideo] 拆条完成: %d/%d", total, len(topics))
+        except Exception as e:
+            import traceback
+            _log_task("scheduled_shortvideo", "failed", log_id=log_id,
+                      message=str(e),
+                      error_trace=traceback.format_exc(),
+                      started_at=started, finished_at=datetime.now(timezone.utc))
+            logger.exception("[ShortVideo] 拆条失败: %s", e)
+
    def get_jobs(self):
        """返回当前所有定时任务的状态"""
        jobs = []