i/next-ai-draw-io
1
0
Fork 0
mirror of https://github.com/DayuanJiang/next-ai-draw-io.git synced 2026-09-02 01:20:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: return clear error for PDF URLs in content extraction (#694)

Browse Source 
* fix: return clear error for PDF urls

* handle timeout thoroughly + use hoisting for user agent
This commit is contained in:
Elshad Humbatli
2026-02-13 04:44:59 -05:00
committed by GitHub
parent ac3570c1b0
commit 89d3968733
1 changed files with 27 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
app/api/parse-url/route.ts
View File

@@ -5,6 +5,7 @@ import { allowPrivateUrls, isPrivateUrl } from "@/lib/ssrf-protection"
const MAX_CONTENT_LENGTH = 150000 // Match PDF limit
const EXTRACT_TIMEOUT_MS = 15000
const USER_AGENT = "Mozilla/5.0 (compatible; NextAIDrawio/1.0)"
export async function POST(req: Request) {
try {
@@ -34,6 +35,31 @@ export async function POST(req: Request) {
{ status: 400 },
)
}
const headController = new AbortController()
const headTimeout = setTimeout(() => headController.abort(), 3000)
try {
const headResponse = await fetch(url, {
method: "HEAD",
headers: { "User-Agent": USER_AGENT },
signal: headController.signal,
})
const contentType = headResponse.headers.get("content-type")
if (contentType?.includes("application/pdf")) {
return NextResponse.json(
{
error: "PDF URLs are not supported. Please download and upload the PDF file directly",
},
{ status: 422 },
)
}
} catch (err) {
console.warn(
"HEAD pre-check failed, proceeding with extraction:",
err,
)
} finally {
clearTimeout(headTimeout)
}
// Extract article content with timeout to avoid tying up server resources
const controller = new AbortController()
@@ -44,9 +70,7 @@ export async function POST(req: Request) {
let article
try {
article = await extract(url, undefined, {
headers: {
"User-Agent": "Mozilla/5.0 (compatible; NextAIDrawio/1.0)",
},
headers: { "User-Agent": USER_AGENT },
signal: controller.signal,
})
} catch (err: any) {