Phase1: 效果数据真实化

- 替换scheduler.py中假随机数metrics_sync为知乎API自动获取
- 新增 POST /api/metrics/zhihu-fetch 知乎公开数据API端点
- metrics.html新增「数据录入」tab：手动录入表单+已有数据列表+知乎自动获取
- gitignore清理已跟踪的生成文件(outlines/research/images/cache)

platform/backend/app/api/metrics.py

@@ -4,6 +4,9 @@ from sqlalchemy import func, desc
 from typing import List, Optional
 from datetime import datetime, timedelta, date
 import logging
+import re
+import requests as http_requests
+from pydantic import BaseModel
 
 from ..database import get_db
 from ..models import ContentMetrics, Topic, ContentCalendar
@@ -302,4 +305,87 @@ def recommend_topics_from_metrics(
         return recommendations[:limit]
     except Exception as e:
         logging.getLogger(__name__).exception(f"推荐选题失败: {e}")
-        return []
+        return []
+
+
+_ZHIHU_UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+
+
+def _extract_zhihu_post_id(url: str) -> str:
+    m = re.search(r'zhuanlan\.zhihu\.com/p/(\d+)', url)
+    if m:
+        return m.group(1)
+    m = re.search(r'zhihu\.com/question/\d+/answer/(\d+)', url)
+    if m:
+        return m.group(1)
+    raise ValueError("无法从URL中提取知乎文章/回答ID")
+
+
+class ZhihuFetchRequest(BaseModel):
+    topic_id: str
+    zhihu_url: str
+
+
+@router.post("/zhihu-fetch")
+def fetch_zhihu_metrics(
+    data: ZhihuFetchRequest,
+    db: Session = Depends(get_db),
+    current_user=Depends(get_current_user)
+):
+    """从知乎专栏/回答公开API自动获取阅读/点赞/评论数据"""
+    topic = db.query(Topic).filter(Topic.id == data.topic_id).first()
+    if not topic:
+        raise HTTPException(status_code=404, detail="选题不存在")
+
+    post_id = _extract_zhihu_post_id(data.zhihu_url)
+    api_url = f"https://zhuanlan.zhihu.com/api/posts/{post_id}"
+
+    try:
+        resp = http_requests.get(api_url, headers={"User-Agent": _ZHIHU_UA}, timeout=15)
+        if resp.status_code == 404:
+            api_url = f"https://www.zhihu.com/api/v4/answers/{post_id}"
+            resp = http_requests.get(api_url, headers={"User-Agent": _ZHIHU_UA}, timeout=15)
+        if resp.status_code != 200:
+            raise HTTPException(status_code=502, detail=f"知乎API返回 {resp.status_code}")
+
+        raw = resp.json()
+        platform = "zhihu"
+
+        existing = db.query(ContentMetrics).filter(
+            ContentMetrics.topic_id == data.topic_id,
+            ContentMetrics.platform == platform
+        ).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) or raw.get("shared_count", 0),
+            "publish_url": data.zhihu_url,
+            "data_snapshot": raw,
+        }
+
+        if existing:
+            for k, v in metric_data.items():
+                setattr(existing, k, v)
+            existing.last_fetched = datetime.now()
+            db.commit()
+            db.refresh(existing)
+            return {"ok": True, "source": "updated", "data": ContentMetricsResponse.model_validate(existing)}
+        else:
+            metric = ContentMetrics(
+                topic_id=data.topic_id,
+                platform=platform,
+                **metric_data,
+                last_fetched=datetime.now()
+            )
+            db.add(metric)
+            db.commit()
+            db.refresh(metric)
+            return {"ok": True, "source": "created", "data": ContentMetricsResponse.model_validate(metric)}
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        raise HTTPException(status_code=502, detail=f"获取知乎数据失败: {str(e)}")

platform/backend/app/core/scheduler.py

@@ -165,12 +165,12 @@ class TaskScheduler:
             logger.exception("[Scheduled] Source AI optimization failed: %s", e)
 
     def _run_metrics_sync(self):
+        """定时从各平台公开API获取发布文章的效果数据（当前仅支持知乎）"""
         try:
-            logger.info("[Scheduled] Starting metrics sync...")
+            logger.info("[Scheduled] Starting metrics sync (zhihu auto-fetch)...")
             from ..database import SessionLocal
-            from ..models import Topic, ContentMetrics, PublishRecord
-            import random, math
-            from datetime import date
+            from ..models import Topic, ContentMetrics
+            import re, requests as http_requests
 
             db = SessionLocal()
             try:
@@ -182,58 +182,51 @@ class TaskScheduler:
                 db.close()
                 return
 
-            random.seed(42)
-            multipliers = {
-                "zhihu": {"v": 1.0, "l": 1.2, "f": 0.6, "c": 1.5, "s": 0.3},
-                "wechat": {"v": 1.8, "l": 0.6, "f": 0.4, "c": 0.3, "s": 2.0},
-                "xiaohongshu": {"v": 2.5, "l": 1.5, "f": 1.8, "c": 1.0, "s": 1.5},
-            }
+            ua = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
             count = 0
             for topic in topics:
-                platforms = set()
-                records = db.query(PublishRecord).filter(
-                    PublishRecord.topic_id == topic.id,
-                    PublishRecord.action == "publish",
-                    PublishRecord.status == "success"
-                ).all()
-                for rec in records:
-                    platforms.add(rec.platform)
-                if not platforms:
-                    platforms = {"zhihu", "wechat", "xiaohongshu"}
-                days = max(1, (date.today() - (topic.published_at or date.today())).days)
-                quality = (topic.compliance_score or 70) / 100.0
-                for plat in platforms:
-                    if plat not in multipliers:
+                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:
                         continue
-                    m = multipliers[plat]
-                    base = random.randint(30, 200)
-                    growth = 1 + math.log(days + 1, 2) * 0.5
-                    views = int(base * m["v"] * growth)
-                    likes = int(views * quality * 0.08 * m["l"])
-                    favs = int(likes * 0.5 * m["f"])
-                    comm = int(views * quality * 0.02 * m["c"])
-                    shar = int(views * quality * 0.03 * m["s"])
+                    raw = resp.json()
                     existing = db.query(ContentMetrics).filter(
                         ContentMetrics.topic_id == topic.id,
-                        ContentMetrics.platform == plat
+                        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:
-                        existing.views = views
-                        existing.likes = likes
-                        existing.favorites = favs
-                        existing.comments = comm
-                        existing.shares = shar
-                        existing.last_fetched = datetime.now()
+                        for k, v in metric_data.items():
+                            setattr(existing, k, v)
                     else:
-                        db.add(ContentMetrics(
-                            topic_id=topic.id, platform=plat,
-                            views=views, likes=likes, favorites=favs,
-                            comments=comm, shares=shar, last_fetched=datetime.now()
-                        ))
+                        db.add(ContentMetrics(topic_id=topic.id, platform="zhihu", **metric_data))
                     count += 1
-            db.commit()
+                except Exception:
+                    continue
+            if count:
+                db.commit()
+                logger.info("[Scheduled] Metrics sync completed: synced %d zhihu articles", count)
+            else:
+                logger.info("[Scheduled] Metrics sync: no zhihu articles to sync")
             db.close()
-            logger.info("[Scheduled] Metrics sync completed: %d entries for %d topics", count, len(topics))
         except Exception as e:
             logger.exception("[Scheduled] Metrics sync failed: %s", e)