feat: OG image scraper - auto-fetch recipe images from Pinterest/URLs

- New backend service: og-scraper.service.ts (extracts og:image, og:title, og:description)
- Pinterest support via Twitterbot UA (gets original resolution from i.pinimg.com)
- Works with Chefkoch, Allrecipes, blogs, any site with og:image meta tags
- GET /api/og-preview?url= for preview
- POST /api/recipes/:id/fetch-image to download + process with sharp
- Frontend: 'Bild holen' button appears when source URL is filled
- Auto-fills title & description from OG data if empty
- Images processed to WebP, max 1200px wide
This commit is contained in:
clawd
2026-02-18 10:15:18 +00:00
parent ee452efa6a
commit 60ca01fb94
8 changed files with 216 additions and 10 deletions

View File

@@ -0,0 +1,76 @@
import { FastifyInstance } from 'fastify';
import { scrapeOgData } from '../services/og-scraper.service.js';
import { getDb } from '../db/connection.js';
import sharp from 'sharp';
import fs from 'fs';
import path from 'path';
import { fileURLToPath } from 'url';
const __dirname = path.dirname(fileURLToPath(import.meta.url));
const DATA_DIR = path.resolve(__dirname, '../../data');
export async function ogScrapeRoutes(app: FastifyInstance) {
// Preview: Just fetch OG data without downloading
app.get('/api/og-preview', async (request, reply) => {
const { url } = request.query as { url?: string };
if (!url) return reply.status(400).send({ error: 'url parameter required' });
try {
const data = await scrapeOgData(url);
return data;
} catch (err: any) {
return reply.status(502).send({ error: `Failed to scrape: ${err.message}` });
}
});
// Download OG image and attach to recipe
app.post('/api/recipes/:id/fetch-image', async (request, reply) => {
const { id } = request.params as { id: string };
const { url } = request.body as { url: string };
if (!url) return reply.status(400).send({ error: 'url required' });
const db = getDb();
const recipe = db.prepare('SELECT id FROM recipes WHERE id = ?').get(id) as any;
if (!recipe) return reply.status(404).send({ error: 'Recipe not found' });
try {
// Scrape OG data
const ogData = await scrapeOgData(url);
if (!ogData.image) return reply.status(404).send({ error: 'No image found at URL' });
// Download image
const imgRes = await fetch(ogData.image, {
headers: { 'User-Agent': 'Mozilla/5.0' },
signal: AbortSignal.timeout(15000),
});
if (!imgRes.ok) throw new Error(`Image download failed: ${imgRes.status}`);
const buffer = Buffer.from(await imgRes.arrayBuffer());
// Process with sharp → WebP, max 1200px wide
const imgDir = path.join(DATA_DIR, 'images', 'recipes', id);
fs.mkdirSync(imgDir, { recursive: true });
const imgPath = path.join(imgDir, 'hero.webp');
await sharp(buffer)
.resize(1200, null, { withoutEnlargement: true })
.webp({ quality: 85 })
.toFile(imgPath);
// Update recipe
const imageUrl = `/images/recipes/${id}/hero.webp`;
db.prepare('UPDATE recipes SET image_url = ?, source_url = ?, updated_at = datetime(\'now\') WHERE id = ?')
.run(imageUrl, url, id);
return {
ok: true,
image_url: imageUrl,
og_title: ogData.title,
og_description: ogData.description,
};
} catch (err: any) {
return reply.status(502).send({ error: `Failed: ${err.message}` });
}
});
}