Momento/memento-note/app/api/link-preview/route.ts

import { NextRequest, NextResponse } from 'next/server'
import { auth } from '@/auth'
import { redis } from '@/lib/redis'

export async function GET(req: NextRequest) {
  const session = await auth()
  if (!session?.user?.id) {
    return NextResponse.json({ error: 'Unauthorized' }, { status: 401 })
  }

  const url = req.nextUrl.searchParams.get('url')
  if (!url) {
    return NextResponse.json({ error: 'Missing url' }, { status: 400 })
  }

  const cacheKey = `linkpreview:${session.user.id}:${Buffer.from(url).toString('base64url').slice(0, 80)}`
  try {
    const cached = await redis.get(cacheKey)
    if (cached) {
      return NextResponse.json(JSON.parse(cached), {
        headers: { 'Cache-Control': 'public, s-maxage=86400' },
      })
    }
  } catch {}

  try {
    const parsed = new URL(url)
    if (!['http:', 'https:'].includes(parsed.protocol)) {
      return NextResponse.json({ error: 'Invalid protocol' }, { status: 400 })
    }

    const hostname = parsed.hostname
    if (
      hostname === 'localhost' ||
      hostname === '127.0.0.1' ||
      hostname.startsWith('10.') ||
      hostname.startsWith('192.168.') ||
      hostname.startsWith('169.254.') ||
      hostname.startsWith('172.16.') ||
      hostname.startsWith('172.17.') ||
      hostname.startsWith('172.18.') ||
      hostname.startsWith('172.19.') ||
      hostname.startsWith('172.20.') ||
      hostname.startsWith('172.21.') ||
      hostname.startsWith('172.22.') ||
      hostname.startsWith('172.23.') ||
      hostname.startsWith('172.24.') ||
      hostname.startsWith('172.25.') ||
      hostname.startsWith('172.26.') ||
      hostname.startsWith('172.27.') ||
      hostname.startsWith('172.28.') ||
      hostname.startsWith('172.29.') ||
      hostname.startsWith('172.30.') ||
      hostname.startsWith('172.31.') ||
      hostname === '0.0.0.0' ||
      hostname.endsWith('.local') ||
      hostname.endsWith('.internal')
    ) {
      return NextResponse.json({ error: 'Blocked' }, { status: 403 })
    }

    const controller = new AbortController()
    const timeout = setTimeout(() => controller.abort(), 8000)

    const res = await fetch(url, {
      signal: controller.signal,
      headers: {
        'User-Agent': 'Mozilla/5.0 (compatible; MementoBot/1.0)',
        'Accept': 'text/html',
      },
      redirect: 'follow',
    })

    clearTimeout(timeout)

    if (!res.ok) {
      return NextResponse.json({ error: 'Fetch failed' }, { status: 502 })
    }

    const html = await res.text()
    const data = extractMetadata(html, parsed)

    try { await redis.setex(cacheKey, 300, JSON.stringify(data)) } catch {}

    return NextResponse.json(data, {
      headers: { 'Cache-Control': 'public, s-maxage=86400' },
    })
  } catch {
    return NextResponse.json({ error: 'Failed to fetch' }, { status: 502 })
  }
}

function extractMetadata(html: string, url: URL) {
  const getMeta = (pattern: RegExp): string | null => {
    const m = html.match(pattern)
    return m?.[1]?.trim() || null
  }

  const getMetaProperty = (prop: string): string | null => {
    return getMeta(new RegExp(`<meta[^>]+(?:property|name)=["']${prop}["'][^>]+content=["']([^"']+)["']`, 'i'))
    || getMeta(new RegExp(`<meta[^>]+content=["']([^"']+)["'][^>]+(?:property|name)=["']${prop}["']`, 'i'))
  }

  const title =
    getMetaProperty('og:title') ||
    getMeta(new RegExp('<title[^>]*>([^<]+)</title>', 'i')) ||
    null

  const description =
    getMetaProperty('og:description') ||
    getMetaProperty('description') ||
    getMetaProperty('twitter:description') ||
    null

  const image =
    getMetaProperty('og:image') ||
    getMetaProperty('twitter:image') ||
    null

  const siteName =
    getMetaProperty('og:site_name') ||
    null

  const favicon = image
    ? null
    : `https://www.google.com/s2/favicons?domain=${url.hostname}&sz=32`

  const finalImage = image
    ? (image.startsWith('http') ? image : new URL(image, url.origin).href)
    : null

  return {
    title: title ? decodeEntities(title) : null,
    description: description ? decodeEntities(description).slice(0, 200) : null,
    image: finalImage,
    favicon,
    siteName: siteName || url.hostname.replace('www.', ''),
  }
}

function decodeEntities(text: string): string {
  return text
    .replace(/&amp;/g, '&')
    .replace(/&lt;/g, '<')
    .replace(/&gt;/g, '>')
    .replace(/&quot;/g, '"')
    .replace(/&#39;/g, "'")
    .replace(/&#x27;/g, "'")
    .replace(/&nbsp;/g, ' ')
}