1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
interface OGResponse {
title: string
description: string
image?: string
}
function isValidUrl(urlString: string): boolean {
try {
const url = new URL(urlString)
return url.protocol === "http:" || url.protocol === "https:"
} catch {
return false
}
}
function isPrivateHost(hostname: string): boolean {
const lowerHost = hostname.toLowerCase()
if (
lowerHost === "localhost" ||
lowerHost === "127.0.0.1" ||
lowerHost === "::1" ||
lowerHost.startsWith("127.") ||
lowerHost.startsWith("0.0.0.0")
) {
return true
}
const privateIpPatterns = [
/^10\./,
/^172\.(1[6-9]|2[0-9]|3[01])\./,
/^192\.168\./,
]
return privateIpPatterns.some((pattern) => pattern.test(hostname))
}
// File extensions that are not HTML and can't be scraped for OG data
const NON_HTML_EXTENSIONS = [
".pdf",
".doc",
".docx",
".xls",
".xlsx",
".ppt",
".pptx",
".zip",
".rar",
".7z",
".tar",
".gz",
".mp3",
".mp4",
".avi",
".mov",
".wmv",
".flv",
".webm",
".wav",
".ogg",
".jpg",
".jpeg",
".png",
".gif",
".webp",
".svg",
".ico",
".bmp",
".tiff",
".exe",
".dmg",
".iso",
".bin",
]
function isNonHtmlUrl(url: string): boolean {
try {
const urlObj = new URL(url)
const pathname = urlObj.pathname.toLowerCase()
return NON_HTML_EXTENSIONS.some((ext) => pathname.endsWith(ext))
} catch {
return false
}
}
function extractImageUrl(image: unknown): string | undefined {
if (!image) return undefined
if (typeof image === "string") {
return image
}
if (Array.isArray(image) && image.length > 0) {
const first = image[0]
if (first && typeof first === "object" && "url" in first) {
return String(first.url)
}
}
return ""
}
function extractMetaTag(html: string, patterns: RegExp[]): string {
for (const pattern of patterns) {
const match = html.match(pattern)
if (match?.[1]) {
return match[1]
.replace(/&/g, "&")
.replace(/</g, "<")
.replace(/>/g, ">")
.replace(/"/g, '"')
.replace(/'/g, "'")
.trim()
}
}
return ""
}
function resolveImageUrl(
imageUrl: string | undefined,
baseUrl: string,
): string | undefined {
if (!imageUrl) return undefined
try {
const url = new URL(imageUrl)
return url.href
} catch {
try {
const base = new URL(baseUrl)
return new URL(imageUrl, base.href).href
} catch {
return undefined
}
}
}
export async function GET(request: Request) {
try {
const { searchParams } = new URL(request.url)
const url = searchParams.get("url")
if (!url || !url.trim()) {
return Response.json(
{ error: "Missing or invalid url parameter" },
{ status: 400 },
)
}
const trimmedUrl = url.trim()
if (!isValidUrl(trimmedUrl)) {
return Response.json(
{ error: "Invalid URL. Must be http:// or https://" },
{ status: 400 },
)
}
const urlObj = new URL(trimmedUrl)
if (isPrivateHost(urlObj.hostname)) {
return Response.json(
{ error: "Private/localhost URLs are not allowed" },
{ status: 400 },
)
}
// Skip OG scraping for non-HTML files (PDFs, images, etc.)
if (isNonHtmlUrl(trimmedUrl)) {
return Response.json(
{ title: "", description: "" },
{
headers: {
"Cache-Control":
"public, s-maxage=3600, stale-while-revalidate=86400",
},
},
)
}
const controller = new AbortController()
const timeoutId = setTimeout(() => controller.abort(), 8000)
const response = await fetch(trimmedUrl, {
signal: controller.signal,
headers: {
"User-Agent":
"Mozilla/5.0 (compatible; SuperMemory/1.0; +https://supermemory.ai)",
},
})
clearTimeout(timeoutId)
if (!response.ok) {
return Response.json(
{ error: "Failed to fetch URL" },
{ status: response.status },
)
}
const html = await response.text()
const titlePatterns = [
/<meta\s+property=["']og:title["']\s+content=["']([^"']+)["']/i,
/<meta\s+content=["']([^"']+)["']\s+property=["']og:title["']/i,
/<meta\s+name=["']twitter:title["']\s+content=["']([^"']+)["']/i,
/<title>([^<]+)<\/title>/i,
]
const descriptionPatterns = [
/<meta\s+property=["']og:description["']\s+content=["']([^"']+)["']/i,
/<meta\s+content=["']([^"']+)["']\s+property=["']og:description["']/i,
/<meta\s+name=["']twitter:description["']\s+content=["']([^"']+)["']/i,
/<meta\s+name=["']description["']\s+content=["']([^"']+)["']/i,
]
const imagePatterns = [
/<meta\s+property=["']og:image["']\s+content=["']([^"']+)["']/i,
/<meta\s+content=["']([^"']+)["']\s+property=["']og:image["']/i,
/<meta\s+name=["']twitter:image["']\s+content=["']([^"']+)["']/i,
]
const title = extractMetaTag(html, titlePatterns)
const description = extractMetaTag(html, descriptionPatterns)
const imageUrl = extractMetaTag(html, imagePatterns)
const resolvedImageUrl = resolveImageUrl(imageUrl, trimmedUrl)
const ogResponse: OGResponse = {
title,
description,
...(resolvedImageUrl && { image: resolvedImageUrl }),
}
return Response.json(ogResponse, {
headers: {
"Cache-Control": "public, s-maxage=3600, stale-while-revalidate=86400",
},
})
} catch (error) {
if (error instanceof Error && error.name === "AbortError") {
return Response.json({ error: "Request timeout" }, { status: 504 })
}
console.error("OG route error:", error)
return Response.json({ error: "Internal server error" }, { status: 500 })
}
}
|