sjoerd/korting
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files
src/scraper.js
+44 -6
View File
@@ -4,10 +4,32 @@ function roundMoney(n) {
return Math.round(n * 100) / 100; return Math.round(n * 100) / 100;
} }
function parsePriceValue(raw) { // Turns a human-written amount into a plain JS-parsable number string.
// When both separators occur, the last one is the decimal separator
// ("1.299,00" and "1,299.00" both mean 1299.00); a lone comma is decimal
// only when exactly two digits follow it, otherwise it groups thousands.
function normalizeAmount(raw) {
if (raw == null) return null; if (raw == null) return null;
const cleaned = String(raw).trim().replace(',', '.'); const match = String(raw).trim().match(/-?\d[\d.,]*/);
const value = parseFloat(cleaned); if (!match) return null;
const str = match[0].replace(/[.,]+$/, '');
const lastDot = str.lastIndexOf('.');
const lastComma = str.lastIndexOf(',');
if (lastDot !== -1 && lastComma !== -1) {
return lastComma > lastDot
? str.replace(/\./g, '').replace(',', '.')
: str.replace(/,/g, '');
}
if (lastComma !== -1) {
return /,\d{2}$/.test(str) ? str.replace(',', '.') : str.replace(/,/g, '');
}
return str;
}
function parsePriceValue(raw) {
const normalized = normalizeAmount(raw);
if (normalized == null) return null;
const value = parseFloat(normalized);
return Number.isFinite(value) ? roundMoney(value) : null; return Number.isFinite(value) ? roundMoney(value) : null;
} }
@@ -59,9 +81,14 @@ function findPriceInMeta($) {
return null; return null;
} }
// Thousands-grouped amounts first, then a plain amount, so "€1.299,00"
// is not truncated to "€1.29".
const TEXT_PRICE_RE = /€\s?(\d{1,3}(?:[.,]\d{3})+[.,]\d{2}|\d+[.,]\d{2})/;
function findPriceInText($) { function findPriceInText($) {
const text = $('body').text(); const text = $('body').clone().find('script, style, noscript').remove().end()
const match = text.match(/€\s?(\d+[.,]\d{2})/); .text();
const match = text.match(TEXT_PRICE_RE);
return match ? parsePriceValue(match[1]) : null; return match ? parsePriceValue(match[1]) : null;
} }
@@ -76,7 +103,18 @@ function extractPrice(html) {
return { price: null, method: null }; return { price: null, method: null };
} }
async function fetchAndExtractPrice(url, { fetchImpl = fetch } = {}) { const FETCH_TIMEOUT_MS = 15000;
const USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 '
+ '(KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36';
function defaultFetch(url) {
return fetch(url, {
signal: AbortSignal.timeout(FETCH_TIMEOUT_MS),
headers: { 'User-Agent': USER_AGENT },
});
}
async function fetchAndExtractPrice(url, { fetchImpl = defaultFetch } = {}) {
let response; let response;
try { try {
response = await fetchImpl(url); response = await fetchImpl(url);
test/fixtures/script-decoy.html
Vendored
+5
View File
@@ -0,0 +1,5 @@
<html><body>
<script>var config = {"fallbackPrice": "€9,99"};</script>
<style>.price:after { content: "€1,11"; }</style>
<p>Onze prijs: &euro;49,95 vandaag</p>
</body></html>
test/fixtures/thousands-meta.html
Vendored
+3
View File
@@ -0,0 +1,3 @@
<html><head>
<meta property="product:price:amount" content="1.299,00" />
</head><body><p>Duur product</p></body></html>
test/fixtures/thousands-regex.html
Vendored
+1
View File
@@ -0,0 +1 @@
<html><body><p>Nu voor &euro;1.299,00 incl. btw</p></body></html>
test/scraper.test.js
+39 -1
View File
@@ -2,7 +2,7 @@ const test = require('node:test');
const assert = require('node:assert/strict'); const assert = require('node:assert/strict');
const fs = require('node:fs'); const fs = require('node:fs');
const path = require('node:path'); const path = require('node:path');
const { extractPrice, fetchAndExtractPrice } = require('../src/scraper'); const { extractPrice, fetchAndExtractPrice, parsePriceValue } = require('../src/scraper');
function loadFixture(name) { function loadFixture(name) {
return fs.readFileSync(path.join(__dirname, 'fixtures', name), 'utf8'); 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 }); 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 () => { test('fetchAndExtractPrice returns error when fetch rejects', async () => {
const fetchImpl = async () => { throw new Error('network down'); }; const fetchImpl = async () => { throw new Error('network down'); };
const result = await fetchAndExtractPrice('https://example.invalid', { fetchImpl }); 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); 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 () => { test('fetchAndExtractPrice extracts price from fetched HTML', async () => {
const html = loadFixture('meta-tag.html'); const html = loadFixture('meta-tag.html');
const fetchImpl = async () => ({ ok: true, status: 200, text: async () => html }); const fetchImpl = async () => ({ ok: true, status: 200, text: async () => html });