xinyouhe/yunke
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(scraper): 消息归一化补fileTh/fileHd→列映射(图片缩略图URL进列,媒体下载器可及)

Browse Source 
Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
浅念
2026-08-20 09:46:54 +08:00
parent 5923cd05b1
commit 10cdd81d5c
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
yunke-server/scripts/scrape_via_page.py
+6
View File
@@ -550,6 +550,9 @@ async def scrape_messages(cookie_str: str, max_conversations: int = 100):
"type_raw": row.get("type"), "type_raw": row.get("type"),
"text": row.get("content") or row.get("text") or "", "text": row.get("content") or row.get("text") or "",
"file_url": row.get("file") or row.get("fileUrl"), "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, "timestamp": ts,
"sender_name": row.get("name") or row.get("senderName"), "sender_name": row.get("name") or row.get("senderName"),
"raw_json": row, "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"), "type_raw": row.get("type"),
"text": row.get("content") or row.get("text") or "", "text": row.get("content") or row.get("text") or "",
"file_url": row.get("file") or row.get("fileUrl"), "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, "timestamp": ts,
"sender_name": row.get("name") or row.get("senderName"), "sender_name": row.get("name") or row.get("senderName"),
"raw_json": row, "raw_json": row,