fix: 给采集结果填 content/summary(主站资源库对空 content 拒收)

- ScrapedItem 加 content/summary 字段;to_ingest_dict 输出它们,content 为空时回退用 title
- scraper 新增 _extract_description:抓 meta/og/jsonld 描述 + 详情面板文本 + 标签,拼成 content

core/models.py

@@ -20,6 +20,9 @@ class ScrapedItem:
     cover_image: str | None = None
     # 视频 URL(上传 MinIO 后改为 MinIO 地址,否则是 xchina 限时签名 m3u8)
     video_url: str | None = None
+    # 简介 / 正文(主站资源库要求 content 非空才入库;为空时回退用 title)
+    summary: str | None = None
+    content: str | None = None
     # 列表页页码(单详情页直采时为 1)
     page_no: int = 1
     # xchina 详情页里的 id 段;作 MinIO object key 前缀
@@ -36,6 +39,8 @@ class ScrapedItem:
         if self.video_id:
             extra_data["video_id"] = self.video_id
         extra_data.update(self.extra or {})
+        # 主站 ingest 对空 content 直接拒收 —— 兜底用 title,确保非空
+        content = (self.content or "").strip() or (self.title or "").strip() or self.source_url
         return {
             "source_type": "video",
             "source_name": self.source_name,
@@ -43,6 +48,8 @@ class ScrapedItem:
             "content_type": "video",
             "title": self.title,
             "cover_image": self.cover_image,
+            "summary": (self.summary or None),
+            "content": content,
             "video_url": self.video_url,
             "extra_data": extra_data,
         }

core/scraper.py

@@ -324,13 +324,16 @@ class XChinaScraper:
             await self._assert_not_blocked(page)
             await self._handle_interstitial_ad(page, detail_url)
             title = await self._extract_title(page)
+            summary, content = await self._extract_description(page, title)
             cover_url = await self._find_cover_url(page)
             video_url = await self._find_video_url(page, media_urls)
-            self.log(f"采集: {title} | cover={'有' if cover_url else '无'} | video={video_url or '无'}")
+            self.log(f"采集: {title} | cover={'有' if cover_url else '无'} | video={video_url or '无'} | content={len(content or '')}字")
             from .media import extract_video_id
             return ScrapedItem(
                 source_url=detail_url,
                 title=title,
+                summary=summary,
+                content=content,
                 cover_image=cover_url,
                 video_url=video_url,
                 page_no=page_no,
@@ -458,6 +461,51 @@ class XChinaScraper:
         low = title.lower()
         return not any(w.lower() in low for w in bad)
 
+    # ---- description / content -------------------------------------------
+
+    async def _extract_description(self, page, title: str) -> tuple[str | None, str]:
+        """返回 (summary, content)。content 保证非空(实在没有就用 title)——
+        主站资源库 ingest 对空 content 直接拒收。"""
+        data = await page.evaluate(
+            """() => {
+                function clean(t){ return (t || '').replace(/\\s+/g,' ').trim(); }
+                const out = {};
+                const m = document.querySelector('meta[name="description"], meta[property="og:description"], meta[name="twitter:description"]');
+                out.meta_desc = clean(m && m.getAttribute('content'));
+                for (const s of document.querySelectorAll('script[type="application/ld+json"]')) {
+                    try { const d = JSON.parse(s.textContent||'null'); const rows = Array.isArray(d)?d:[d];
+                        for (const r of rows) { if (r && r.description) { out.jsonld_desc = clean(r.description); break; } } } catch(_){}
+                }
+                // 影片信息 / 详情面板里的文本(键值对、简介等)
+                const panel = document.querySelector('.video-detail') || document.querySelector('.tab-content.active') || document.querySelector('.tab-content');
+                out.panel = panel ? clean(panel.innerText).slice(0, 4000) : '';
+                // 标签
+                const tags = [];
+                for (const a of document.querySelectorAll('.tags a, .tag a, a[href*="/tags/"], .video-detail .item a')) {
+                    const t = clean(a.innerText); if (t && t.length<=20 && !tags.includes(t)) tags.push(t);
+                }
+                out.tags = tags.slice(0, 30);
+                return out;
+            }"""
+        )
+        meta_desc = (data.get("meta_desc") or "").strip()
+        jsonld_desc = (data.get("jsonld_desc") or "").strip()
+        panel = (data.get("panel") or "").strip()
+        tags = data.get("tags") or []
+        # content: 优先详情面板文本(信息量最大),否则 og/jsonld 描述,再否则 标签拼接,最后 title
+        parts: list[str] = []
+        body = panel or jsonld_desc or meta_desc
+        if body:
+            parts.append(body)
+        if tags:
+            parts.append("标签: " + " ".join(tags))
+        content = "\n".join(parts).strip()
+        if not content:
+            content = title
+        # summary: og/jsonld 描述,或 content 头一截
+        summary = (meta_desc or jsonld_desc or content)[:300].strip() or None
+        return summary, content
+
     # ---- cover -----------------------------------------------------------
 
     # 明显不是封面的图: 站点 logo / 占位图 / 图标 / 广告