fix(RECIPE-0006): complete iteration 0 — fix Instagram recipe extraction

src/tests/instagram-caption-extraction.e2e.spec.ts

@@ -0,0 +1,47 @@
+import { describe, it, expect } from 'vitest';
+import { extractTextAndThumbnail } from '$lib/server/extraction';
+
+describe('Instagram Caption Extraction E2E', () => {
+	it('should extract complete recipe without metadata prefix', async () => {
+		const testUrl = 'https://www.instagram.com/reel/DP6oN7JCEo8/?utm_source=ig_web_button_share_sheet';
+		
+		const result = await extractTextAndThumbnail(testUrl);
+		
+		// Verify extraction succeeded
+		expect(result).toBeDefined();
+		expect(result.bodyText).toBeDefined();
+		expect(result.bodyText.length).toBeGreaterThan(100);
+		
+		console.log('[Test] Extracted text length:', result.bodyText.length);
+		console.log('[Test] First 200 chars:', result.bodyText.substring(0, 200));
+		
+		// Should NOT contain metadata prefix patterns
+		expect(result.bodyText).not.toMatch(/^\d+K?\s+likes,/);
+		expect(result.bodyText).not.toMatch(/^\d+\s+likes,/);
+		expect(result.bodyText).not.toMatch(/\d+\s+comments/);
+		expect(result.bodyText).not.toMatch(/\w+\s+on\s+\w+\s+\d+/);
+		
+		// Should start with recipe title
+		expect(result.bodyText).toMatch(/^La cacio e pepe/i);
+		
+		// Should NOT contain hashtags at the end
+		expect(result.bodyText).not.toMatch(/#\w+\s*$/);
+		expect(result.bodyText).not.toContain('#cacioepepe');
+		expect(result.bodyText).not.toContain('#ricettefacili');
+		
+		// Should contain ingredients section
+		expect(result.bodyText).toContain('pecorino');
+		expect(result.bodyText).toContain('pepe');
+		
+		// Should contain procedure section  
+		expect(result.bodyText).toContain('pasta');
+		expect(result.bodyText).toContain('acqua');
+		
+		// Should NOT be truncated
+		expect(result.bodyText).not.toContain('...');
+	}, 30000);
+
+	it.skip('should handle invalid Instagram URL gracefully', async () => {
+		// Placeholder for future test
+	});
+});