From 10cdd81d5c93fad099b4b347af5caad011bb3d63 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B5=85=E5=BF=B5?= Date: Thu, 20 Aug 2026 09:46:54 +0800 Subject: [PATCH] =?UTF-8?q?fix(scraper):=20=E6=B6=88=E6=81=AF=E5=BD=92?= =?UTF-8?q?=E4=B8=80=E5=8C=96=E8=A1=A5fileTh/fileHd=E2=86=92=E5=88=97?= =?UTF-8?q?=E6=98=A0=E5=B0=84(=E5=9B=BE=E7=89=87=E7=BC=A9=E7=95=A5?= =?UTF-8?q?=E5=9B=BEURL=E8=BF=9B=E5=88=97,=E5=AA=92=E4=BD=93=E4=B8=8B?= =?UTF-8?q?=E8=BD=BD=E5=99=A8=E5=8F=AF=E5=8F=8A)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Co-Authored-By: Claude --- yunke-server/scripts/scrape_via_page.py | 6 ++++++ 1 file changed, 6 insertions(+) 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,