diff --git a/yunke-server/scripts/scrape_via_page.py b/yunke-server/scripts/scrape_via_page.py
index 791e0eb..12c59ac 100644
--- a/yunke-server/scripts/scrape_via_page.py
+++ b/yunke-server/scripts/scrape_via_page.py
@@ -550,6 +550,9 @@ async def scrape_messages(cookie_str: str, max_conversations: int = 100):
                             "type_raw": row.get("type"),
                             "text": row.get("content") or row.get("text") or "",
                             "file_url": row.get("file") or row.get("fileUrl"),
+                            # fileTh/fileHd 常在 file 为空时仍带完整 OSS URL——映射进列,媒体下载器才够得着
+                            "file_th_url": row.get("fileTh"),
+                            "file_hd_url": row.get("fileHd"),
                             "timestamp": ts,
                             "sender_name": row.get("name") or row.get("senderName"),
                             "raw_json": row,
@@ -627,6 +630,9 @@ def _normalize_group_message(row: dict, owner_id: str, room_id: str) -> dict | N
         "type_raw": row.get("type"),
         "text": row.get("content") or row.get("text") or "",
         "file_url": row.get("file") or row.get("fileUrl"),
+        # 同 1:1:fileTh/fileHd 的 OSS URL 必须映射进列,媒体下载器才够得着
+        "file_th_url": row.get("fileTh"),
+        "file_hd_url": row.get("fileHd"),
         "timestamp": ts,
         "sender_name": row.get("name") or row.get("senderName"),
         "raw_json": row,