fix: harden price scraping (findings 1, 2, 6)

Finding 1: parsePriceValue mishandled thousands separators — "1.299,00"
and "1,299.00" both parsed to 1.3. Both the meta-tag path and the
text-regex path now funnel through a single normalizeAmount() helper
that picks the last separator as the decimal one, and the text regex
also matches thousands-grouped amounts.

Finding 2: the text fallback read <script>/<style> contents via
$('body').text(); those elements are now stripped from a clone first.

Finding 6: the default fetch now uses a 15s AbortSignal.timeout and a
browser-like User-Agent, so one unresponsive host cannot stall the
whole sequential run. The fetchImpl injection point is unchanged.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013gwc3aCiyQxmCWQke8RvEz
This commit is contained in:
Sjoerd de Vries
2026-09-05 15:49:56 +02:00
parent 862699d35b
commit 52c9947267
5 changed files with 92 additions and 7 deletions
+39 -1
View File
@@ -2,7 +2,7 @@ const test = require('node:test');
const assert = require('node:assert/strict');
const fs = require('node:fs');
const path = require('node:path');
const { extractPrice, fetchAndExtractPrice } = require('../src/scraper');
const { extractPrice, fetchAndExtractPrice, parsePriceValue } = require('../src/scraper');
function loadFixture(name) {
return fs.readFileSync(path.join(__dirname, 'fixtures', name), 'utf8');
@@ -28,6 +28,31 @@ test('extractPrice returns null price when nothing matches', () => {
assert.deepEqual(result, { price: null, method: null });
});
test('parsePriceValue handles both thousands-separator conventions', () => {
assert.equal(parsePriceValue('1.299,00'), 1299.00);
assert.equal(parsePriceValue('1,299.00'), 1299.00);
assert.equal(parsePriceValue('19,99'), 19.99);
assert.equal(parsePriceValue('19.99'), 19.99);
assert.equal(parsePriceValue('1.234.567,89'), 1234567.89);
assert.equal(parsePriceValue(null), null);
assert.equal(parsePriceValue('geen prijs'), null);
});
test('extractPrice reads a thousands-grouped price from a meta tag', () => {
const result = extractPrice(loadFixture('thousands-meta.html'));
assert.deepEqual(result, { price: 1299.00, method: 'meta' });
});
test('extractPrice reads a thousands-grouped price from page text', () => {
const result = extractPrice(loadFixture('thousands-regex.html'));
assert.deepEqual(result, { price: 1299.00, method: 'regex' });
});
test('extractPrice ignores euro amounts inside script and style tags', () => {
const result = extractPrice(loadFixture('script-decoy.html'));
assert.deepEqual(result, { price: 49.95, method: 'regex' });
});
test('fetchAndExtractPrice returns error when fetch rejects', async () => {
const fetchImpl = async () => { throw new Error('network down'); };
const result = await fetchAndExtractPrice('https://example.invalid', { fetchImpl });
@@ -42,6 +67,19 @@ test('fetchAndExtractPrice returns error on non-OK response', async () => {
assert.ok(result.error instanceof Error);
});
test('fetchAndExtractPrice returns error when the request times out', async () => {
const fetchImpl = async () => {
const err = new Error('The operation was aborted due to timeout');
err.name = 'TimeoutError';
throw err;
};
const result = await fetchAndExtractPrice('https://example.invalid', { fetchImpl });
assert.deepEqual(result.price, null);
assert.equal(result.method, null);
assert.ok(result.error instanceof Error);
assert.equal(result.error.name, 'TimeoutError');
});
test('fetchAndExtractPrice extracts price from fetched HTML', async () => {
const html = loadFixture('meta-tag.html');
const fetchImpl = async () => ({ ok: true, status: 200, text: async () => html });