fix: harden alicdn image downloads

scripts/test_alicdn_download.py

@@ -0,0 +1,74 @@
+import asyncio
+from pathlib import Path
+
+import httpx
+
+
+TEST_URL = "https://img.alicdn.com/imgextra/i1/O1CN01959PmC2MK7jvMhqXF_!!4611686018427385312-0-amp.jpg"
+OUTPUT_DIR = Path(__file__).resolve().parents[1] / "tmp_alicdn_download"
+
+CONTENT_TYPE_TO_SUFFIX = {
+    "image/jpeg": ".jpg",
+    "image/jpg": ".jpg",
+    "image/png": ".png",
+    "image/webp": ".webp",
+    "image/avif": ".avif",
+}
+
+DEFAULT_HEADERS = {
+    "User-Agent": (
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+        "AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/133.0.0.0 Safari/537.36"
+    ),
+    "Accept": "image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8",
+    "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
+    "Cache-Control": "no-cache",
+    "Pragma": "no-cache",
+    "Referer": "https://www.taobao.com/",
+}
+
+
+async def download_once(client: httpx.AsyncClient, url: str):
+    response = await client.get(url, headers=DEFAULT_HEADERS)
+    print(f"HTTP {response.status_code}")
+    content_type = response.headers.get("content-type", "").split(";", 1)[0].strip().lower()
+    print(f"Content-Type: {content_type}")
+    if response.status_code != 200:
+        print(response.text[:300])
+        response.raise_for_status()
+
+    suffix = CONTENT_TYPE_TO_SUFFIX.get(content_type, ".bin")
+    output_path = OUTPUT_DIR / f"alicdn_test{suffix}"
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    output_path.write_bytes(response.content)
+    print(f"Saved to: {output_path}")
+    print(f"Size: {output_path.stat().st_size} bytes")
+
+
+async def main():
+    timeout = httpx.Timeout(60.0, connect=20.0)
+    async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
+        last_error = None
+        referers = [
+            "https://www.taobao.com/",
+            "https://item.taobao.com/",
+            "https://detail.tmall.com/",
+        ]
+        for idx, referer in enumerate(referers, 1):
+            try:
+                DEFAULT_HEADERS["Referer"] = referer
+                print(f"Attempt {idx} with Referer={referer}")
+                await download_once(client, TEST_URL)
+                print("Download success")
+                return
+            except Exception as e:
+                last_error = e
+                print(f"Attempt {idx} failed: {type(e).__name__}: {e}")
+                await asyncio.sleep(1)
+
+        raise RuntimeError(f"All attempts failed: {last_error}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())