feat: amazon scraper with playwright + html parser tests

2026-05-25 14:09:44 +00:00
parent f86055b85d
commit 98fc938f91
3 changed files with 7649 additions and 0 deletions
--- a/tests/fixtures/amazon-ps5.html
+++ b/tests/fixtures/amazon-ps5.html
--- a/tests/scrapers/amazon.test.ts
+++ b/tests/scrapers/amazon.test.ts
@@ -0,0 +1,23 @@
+import { describe, it, expect } from 'vitest'
+import { readFileSync } from 'node:fs'
+import { join } from 'node:path'
+import { parseAmazonHtml } from '@/lib/scrapers/amazon'
+
+const fixture = readFileSync(join(__dirname, '../fixtures/amazon-ps5.html'), 'utf-8')
+
+describe('parseAmazonHtml', () => {
+  it('extracts price, name, image', () => {
+    const r = parseAmazonHtml(fixture)
+    expect(r.price).toBeGreaterThan(0)
+    expect(r.currency).toBe('EUR')
+    expect(r.name).toBeTruthy()
+    expect(r.imageUrl).toMatch(/^https?:\/\//)
+  })
+
+  it('detects captcha page', () => {
+    const captchaHtml = '<html><body><form action="/errors/validateCaptcha"></form></body></html>'
+    const r = parseAmazonHtml(captchaHtml)
+    expect(r.price).toBeNull()
+    expect(r.error).toBe('captcha')
+  })
+})