feat(scraper): moments 实体(浏览器fetch getFriendsterInfo,秒→ms,hashNext翻页,接入full_sync+4h调度+图片media)

- scrape_via_page:_normalize_moments(createTime秒×1000,缺id丢弃)+
  _iter_moments_pages 翻页内核(fetch回调注入,sleep可注入,hashNext假/
  信封异常/max_pages 上限即止)+ scrape_moments(逐员工遍历wechat_account,
  form小驼峰,首页code≠10000告警cookie失效,换页重试惯例)+CLI注册moments
- media:download_moments_images(image_urls JSON数组展开去重,MomentsPost无
  回链列→用Media.original_url做已下载标记,分片IN防SQLite变量上限,批间commit)
  接入scrape_media第4源
- full_sync_all.sh:9c步moments(media前,同轮图片即可本地化)+汇总加moments计数
- scheduler:4h messages job 末尾追加 moments --max-pages 3 浅扫(全量翻页
  由每日full承担);测试断言7条命令序列
- tests/test_scrape_moments.py:归一化(秒→ms/空安全/坏createTime)+翻页内核
  (两页累积停止/hashNext假单页/max_pages防死循环/丢id行/坏信封)+图片本地化
  (一帖两图/幂等跳过/非http跳过+500容错);全套440测试通过

Co-Authored-By: Claude <noreply@anthropic.com>

yunke-server/app/scraper/media.py

@@ -37,7 +37,7 @@ import httpx
 import sqlalchemy as sa
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.db.models import Media, Message, PhoneCall, VoiceClip
+from app.db.models import Media, Message, MomentsPost, PhoneCall, VoiceClip
 from app.session.yunke_client import YunkeClient
 from app.storage.object_store import ObjectStore
 from app.storage.repos import upsert_media
@@ -46,6 +46,7 @@ __all__ = [
     "download_call_recordings",
     "download_message_images",
     "download_message_media",
+    "download_moments_images",
     "download_url",
     "download_voice_clip_audio",
     "guess_mime_type",
@@ -535,3 +536,88 @@ async def download_message_images(
             localized += 1
         await session.commit()
     return attempted, localized
+
+
+async def download_moments_images(
+    client: YunkeClient,
+    store: ObjectStore,
+    session: AsyncSession,
+    *,
+    batch_size: int = 50,
+) -> tuple[int, int]:
+    """Download 员工朋友圈 images (``moments_post.image_urls`` OSS 直链) into
+    the local object store, one ``Media`` row per blob.
+
+    朋友圈与消息图片的关键差异(2026-08-25 接入时确认):``image_urls`` 是
+    JSON **数组**(一帖多图),且 :class:`MomentsPost` 没有 ``media_hash``
+    回链列 —— 已下载标记改用 ``Media.original_url``:URL 已有对应 Media 行
+    即视为已本地化并跳过(不重下载)。无回链也就无法"标记"帖子行,故候选
+    集一次物化(全表展开 + 去重),再按 ``original_url`` 剔除已下载的,分批
+    下载(批间 commit,部分进度可保留)。
+
+    Returns ``(attempted, localized)``. Resilient: a per-URL download failure is
+    logged and counted as attempted-but-not-localized; no exception escapes.
+    Failed URLs keep no Media row → retried on the NEXT run. Identical bytes are
+    stored once (:meth:`ObjectStore.put_by_hash`, sha256 dedup).
+
+    Known edge: two DISTINCT URLs hosting byte-identical content share one
+    ``media_hash`` (content-addressed PK), and the upsert refreshes
+    ``original_url`` to the latest — so the loser URL is re-fetched once per run
+    (bounded, never grows; identical bytes at two OSS paths is rare).
+    """
+    rows = (
+        await session.execute(
+            sa.select(MomentsPost.id, MomentsPost.image_urls).where(
+                MomentsPost.image_urls.is_not(None)
+            )
+        )
+    ).all()
+
+    # 一帖多图 → 展开去重(同图多帖只下载一次)
+    urls: list[str] = []
+    seen: set[str] = set()
+    for _post_id, image_urls in rows:
+        for url in image_urls or []:
+            if _is_http_url(url) and url not in seen:
+                seen.add(url)
+                urls.append(url)
+    if not urls:
+        return 0, 0
+
+    # 剔除已本地化的 URL。分片 IN —— 单次塞全部 URL 会超 SQLite 变量上限
+    # (同 download_message_images 的 tried 分片惯例,2026-08-20)。
+    existing: set[str] = set()
+    for i in range(0, len(urls), 500):
+        res = await session.execute(
+            sa.select(Media.original_url).where(
+                Media.original_url.in_(urls[i : i + 500])
+            )
+        )
+        existing.update(u for (u,) in res.fetchall() if u)
+    pending = [u for u in urls if u not in existing]
+
+    attempted = 0
+    localized = 0
+    for i in range(0, len(pending), batch_size):
+        for url in pending[i : i + batch_size]:
+            attempted += 1
+            try:
+                data = await download_url(client, url)
+            except (httpx.HTTPError, OSError) as exc:
+                logger.warning("moments image download failed for %s: %s", url, exc)
+                continue
+            ext = _ext_from_url(url)
+            sha256_hex, path = await store.put_by_hash(data, ext=ext)
+            await upsert_media(
+                session,
+                media_hash=sha256_hex,
+                channel="wechat",  # 朋友圈是微信独有实体(无 WA 朋友圈)
+                media_type="image",
+                original_url=url,
+                local_path=str(path),
+                size_bytes=len(data),
+                mime_type=guess_mime_type(ext),
+            )
+            localized += 1
+        await session.commit()
+    return attempted, localized