From aad7e4dd1c0cacb8318aa0177281c8ad6755d25d Mon Sep 17 00:00:00 2001
From: yjc980121 <3898524+yjc980121@users.noreply.github.com>
Date: Mon, 27 Jan 2025 11:33:03 +0800
Subject: [PATCH] fix:Improve MIME type detection for remote URL uploads using
 python-magic (#12693)

---
 api/controllers/common/helpers.py | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/api/controllers/common/helpers.py b/api/controllers/common/helpers.py
index 2bae203712..fa42ce4c43 100644
--- a/api/controllers/common/helpers.py
+++ b/api/controllers/common/helpers.py
@@ -7,6 +7,7 @@ from typing import Any
 from uuid import uuid4
 
 import httpx
+import magic
 from pydantic import BaseModel
 
 from configs import dify_config
@@ -47,6 +48,13 @@ def guess_file_info_from_response(response: httpx.Response):
         # If guessing fails, use Content-Type from response headers
         mimetype = response.headers.get("Content-Type", "application/octet-stream")
 
+    # Use python-magic to guess MIME type if still unknown or generic
+    if mimetype == "application/octet-stream":
+        try:
+            mimetype = magic.from_buffer(response.content[:1024], mime=True)
+        except magic.MagicException:
+            pass
+
     extension = os.path.splitext(filename)[1]
 
     # Ensure filename has an extension