feat(scraper): WA群抓取(type=1真机验证,223群)+群成员派生(12840成员/750群)

- wa-groups 实体:businessFriendList type=1 真机验证返回群,行结构是好友字段名
  (friendUid=@g.us 群ID/nickName=群名),专用 _normalize_wa_group_row
- backfill_group_members.py:无独立成员API,从群消息派生(talker=成员,sender_name=昵称)
- full_sync_all.sh:+4步(5b WA群/语音后录音重链接/8b 群消息+成员/消息上限99999)

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

yunke-server/scripts/scrape_via_page.py

@@ -946,6 +946,84 @@ async def scrape_wa_friends(cookie_str: str, max_pages: int = 2000):
     return total_fetched, total_upserted
 
 
+def _normalize_wa_group_row(row: dict) -> dict | None:
+    """businessFriendList type=1 行 → ChatGroup 形状（真机确认 2026-08-20）。
+
+    type=1 返回的是好友字段名结构：friendUid=群 id（@g.us 后缀）、nickName=
+    群名、uid=员工 WA 号、salesNickName=员工 WA 昵称——与微信群的
+    friendWxId/friendWxNickname 完全不同，故不能复用 _normalize_chat_group。
+    非 @g.us 行（异常混入）返回 None。
+    """
+    friend_uid = str(row.get("friendUid") or "")
+    if not friend_uid.endswith("@g.us"):
+        return None
+    return {
+        "room_id": friend_uid,
+        "channel": "whatsapp",
+        "room_name": row.get("nickName"),
+        "owner_account_id": row.get("uid"),
+        "owner_account_nickname": row.get("salesNickName"),
+        "owner_user_id": row.get("userId"),
+        "owner_user_phone": row.get("salePhone"),
+        "message_count": row.get("messageGroupCount"),
+        "raw_json": row,
+    }
+
+
+async def scrape_wa_groups(cookie_str: str, max_pages: int = 200):
+    """Scrape WhatsApp GROUPS via browser fetch POST businessFriendList type=1.
+
+    Same endpoint as WA friends with ``type:"1"`` — live-verified 2026-08-20:
+    rows carry friendUid ending ``@g.us`` (group id), nickName = group name.
+    Envelope: data.overviews; upsert to chat_group (channel='whatsapp').
+    """
+    from app.db.base import async_engine
+    from sqlalchemy import text as sa_text
+    from app.storage.repos import upsert_chat_group
+
+    async with async_engine.connect() as conn:
+        row = (await conn.execute(sa_text(
+            "SELECT dept_id FROM department WHERE parent_id IS NULL LIMIT 1"
+        ))).first()
+    department_id = row[0] if row else ""
+    if not department_id:
+        logger.warning("wa-groups: no root department in DB — abort")
+        return 0, 0
+
+    page_size = 50
+    total_fetched = 0
+    total_upserted = 0
+    async with PageScraper(cookie_str) as scraper:
+        page = await _open_fetch_page(scraper)
+        page_num = 1
+        while page_num <= max_pages:
+            body = await _browser_fetch(
+                page,
+                INTERCEPT_PATHS["wa_friend"],
+                json_body={
+                    "searchInfo": "",
+                    "friendSearchInfo": "",
+                    "page": page_num,
+                    "pageSize": page_size,
+                    "departmentId": department_id,
+                    "type": "1",
+                },
+            )
+            rows = _rows_overviews(body)
+            records = [rec for r in rows if (rec := _normalize_wa_group_row(r)) is not None]
+            total_fetched += len(records)
+            await _upsert_all(upsert_chat_group, records)
+            total_upserted += len(records)
+            logger.info(f"  wa-groups page {page_num}: {len(rows)} rows, {len(records)} groups")
+            if len(rows) < page_size:
+                break
+            page_num += 1
+            await asyncio.sleep(1.5)
+
+    logger.info(f"DONE: wa-groups fetched={total_fetched}, upserted={total_upserted}")
+    return total_fetched, total_upserted
+
+
 # ---------------------------------------------------------------------------
 # Voice call records (navigation + interception, both WeChat + WA pages)
 # ---------------------------------------------------------------------------
@@ -1299,6 +1377,7 @@ async def main():
             "accounts",      # 微信员工账号 (wechatlist page interception)
             "wa-accounts",   # WA员工账号 (waBusiness/userlist interception)
             "wa-friends",    # WA客户 (waBusiness/friendlist interception)
+            "wa-groups",     # WA群 (browser fetch businessFriendList type=1)
             "voice-calls",   # 语音通话记录 (voice-call-list + wavoicecalllist)
             "voice-clips",   # 长语音 (browser fetch call/list per employee)
             "wa-messages",   # WA消息 (browser fetch chatRecords per conversation)
@@ -1337,6 +1416,8 @@ async def main():
         await scrape_wa_accounts(cookie, args.max_pages)
     elif args.entity == "wa-friends":
         await scrape_wa_friends(cookie, args.max_pages)
+    elif args.entity == "wa-groups":
+        await scrape_wa_groups(cookie, args.max_pages)
     elif args.entity == "voice-calls":
         await scrape_voice_calls(cookie, args.max_pages)
     elif args.entity == "voice-clips":