feat: add Playwright-based fallback scraper

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013gwc3aCiyQxmCWQke8RvEz
2026-09-05 17:30:18 +02:00
parent dac7893cd2
commit df3d3250e5
4 changed files with 126 additions and 2 deletions
@@ -0,0 +1,70 @@
+const test = require('node:test');
+const assert = require('node:assert/strict');
+const { fetchAndExtractPriceViaBrowser } = require('../src/browserScraper');
+
+test('fetchAndExtractPriceViaBrowser extracts a price from the rendered page', async () => {
+  let closed = false;
+  const html = '<html><head><meta property="og:price:amount" content="42.00" /></head><body></body></html>';
+  const page = {
+    goto: async () => {},
+    content: async () => html,
+    close: async () => { closed = true; },
+  };
+  const browser = { newPage: async () => page };
+  const result = await fetchAndExtractPriceViaBrowser(browser, 'https://example.com');
+  assert.deepEqual(result, { price: 42, method: 'meta', error: null });
+  assert.equal(closed, true);
+});
+
+test('fetchAndExtractPriceViaBrowser returns an error when navigation fails, and still closes the page', async () => {
+  let closed = false;
+  const page = {
+    goto: async () => { throw new Error('Timeout 20000ms exceeded'); },
+    content: async () => '',
+    close: async () => { closed = true; },
+  };
+  const browser = { newPage: async () => page };
+  const result = await fetchAndExtractPriceViaBrowser(browser, 'https://example.com');
+  assert.equal(result.price, null);
+  assert.equal(result.method, null);
+  assert.ok(result.error instanceof Error);
+  assert.equal(closed, true);
+});
+
+test('fetchAndExtractPriceViaBrowser returns null price when nothing matches, and still closes the page', async () => {
+  let closed = false;
+  const page = {
+    goto: async () => {},
+    content: async () => '<html><body><p>Geen prijs</p></body></html>',
+    close: async () => { closed = true; },
+  };
+  const browser = { newPage: async () => page };
+  const result = await fetchAndExtractPriceViaBrowser(browser, 'https://example.com');
+  assert.deepEqual(result, { price: null, method: null, error: null });
+  assert.equal(closed, true);
+});
+
+test('fetchAndExtractPriceViaBrowser closes the page even if reading its content throws', async () => {
+  let closed = false;
+  const page = {
+    goto: async () => {},
+    content: async () => { throw new Error('content failed'); },
+    close: async () => { closed = true; },
+  };
+  const browser = { newPage: async () => page };
+  const result = await fetchAndExtractPriceViaBrowser(browser, 'https://example.com');
+  assert.ok(result.error instanceof Error);
+  assert.equal(closed, true);
+});
+
+test('fetchAndExtractPriceViaBrowser passes the timeout option through to page.goto', async () => {
+  let receivedOptions;
+  const page = {
+    goto: async (url, options) => { receivedOptions = options; },
+    content: async () => '<html><body></body></html>',
+    close: async () => {},
+  };
+  const browser = { newPage: async () => page };
+  await fetchAndExtractPriceViaBrowser(browser, 'https://example.com', { timeoutMs: 5000 });
+  assert.equal(receivedOptions.timeout, 5000);
+});