Cleanup modified & misisng files
Run Tests on Branches / Backend Tests (push) Successful in 3m29s
Run Tests on Branches / Frontend Tests (push) Successful in 3m25s

This commit is contained in:
Antoni Nuñez Romeu
2026-07-02 20:41:50 +02:00
parent 3f5f88bbf5
commit 5114c0bc57
15 changed files with 385 additions and 3737 deletions
+36 -53
View File
@@ -1,7 +1,3 @@
// OpenTelemetry SDK — must be required first to instrument http, dns, etc.
require('./tracing');
const { trace } = require('@opentelemetry/api');
const puppeteer = require('puppeteer-extra');
const StealthPlugin = require('puppeteer-extra-plugin-stealth');
const fs = require('fs');
@@ -20,56 +16,43 @@ const QUERIES = [
];
async function run() {
const tracer = trace.getTracer('farmaclic-scraper');
return tracer.startActiveSpan('scraper.run', { attributes: { 'scraper.queries': QUERIES.length } }, async (span) => {
try {
console.log('🚀 Starting Parapharmacy Scraper...');
const browser = await puppeteer.launch({
headless: 'new',
args: ['--no-sandbox', '--disable-setuid-sandbox']
});
const allResults = {};
for (const query of QUERIES) {
const querySpan = tracer.startSpan('scraper.query', { attributes: { 'scraper.query': query } });
console.log(`\n🔍 Searching for: "${query}"`);
const promofarmaResults = await scrapePromofarma(query, browser);
console.log(` ✅ Promofarma: found ${promofarmaResults.length} items`);
const amazonResults = await scrapeAmazon(query, browser);
console.log(` ✅ Amazon: found ${amazonResults.length} items`);
const googleShoppingResults = await scrapeGoogleShopping(query, browser);
console.log(` ✅ Google Shopping: found ${googleShoppingResults.length} items`);
const ofFactsResults = await scrapeOpenFoodFacts(query, browser);
console.log(` ✅ OpenFoodFacts: found ${ofFactsResults.length} items`);
allResults[query] = {
promofarma: promofarmaResults,
amazon: amazonResults,
googleshopping: googleShoppingResults,
openfoodfacts: ofFactsResults
};
querySpan.setAttribute('scraper.results.total', promofarmaResults.length + amazonResults.length + googleShoppingResults.length + ofFactsResults.length);
querySpan.end();
}
await browser.close();
fs.writeFileSync('results.json', JSON.stringify(allResults, null, 2));
console.log('\n💾 Scraping finished. Results saved to results.json');
span.setStatus({ code: 1 }); // OK
} catch (err) {
span.recordException(err);
span.setStatus({ code: 2, message: err.message }); // ERROR
throw err;
} finally {
span.end();
}
console.log('🚀 Starting Parapharmacy Scraper...');
// Launching browser
const browser = await puppeteer.launch({
headless: 'new',
args: ['--no-sandbox', '--disable-setuid-sandbox']
});
const allResults = {};
for (const query of QUERIES) {
console.log(`\n🔍 Searching for: "${query}"`);
// We run sequentially to be gentle on CPU and anti-bot systems
const promofarmaResults = await scrapePromofarma(query, browser);
console.log(` ✅ Promofarma: found ${promofarmaResults.length} items`);
const amazonResults = await scrapeAmazon(query, browser);
console.log(` ✅ Amazon: found ${amazonResults.length} items`);
const googleShoppingResults = await scrapeGoogleShopping(query, browser);
console.log(` ✅ Google Shopping: found ${googleShoppingResults.length} items`);
const ofFactsResults = await scrapeOpenFoodFacts(query, browser);
console.log(` ✅ OpenFoodFacts: found ${ofFactsResults.length} items`);
allResults[query] = {
promofarma: promofarmaResults,
amazon: amazonResults,
googleshopping: googleShoppingResults,
openfoodfacts: ofFactsResults
};
}
await browser.close();
fs.writeFileSync('results.json', JSON.stringify(allResults, null, 2));
console.log('\n💾 Scraping finished. Results saved to results.json');
}
run().catch(err => {
+3 -2417
View File
File diff suppressed because it is too large Load Diff
-6
View File
@@ -11,12 +11,6 @@
"license": "ISC",
"type": "commonjs",
"dependencies": {
"@opentelemetry/api": "^1.9.0",
"@opentelemetry/auto-instrumentations-node": "^0.52.0",
"@opentelemetry/exporter-trace-otlp-grpc": "^0.55.0",
"@opentelemetry/resources": "^1.28.0",
"@opentelemetry/sdk-node": "^0.55.0",
"@opentelemetry/semantic-conventions": "^1.28.0",
"puppeteer": "^24.40.0",
"puppeteer-extra": "^3.3.6",
"puppeteer-extra-plugin-stealth": "^2.11.2"
-46
View File
@@ -1,46 +0,0 @@
// OpenTelemetry Node SDK bootstrap for the FarmaClic scraper.
// Started as a side-effect require from index.js (CommonJS).
//
// Env vars:
// OTEL_SERVICE_NAME — default: farmaclic-scraper
// OTEL_EXPORTER_OTLP_ENDPOINT — OTLP gRPC endpoint (e.g. http://alloy:4317)
const { NodeSDK } = require('@opentelemetry/sdk-node');
const { getNodeAutoInstrumentations } = require('@opentelemetry/auto-instrumentations-node');
const { OTLPTraceExporter } = require('@opentelemetry/exporter-trace-otlp-grpc');
const { resourceFromAttributes } = require('@opentelemetry/resources');
const {
ATTR_SERVICE_NAME,
ATTR_SERVICE_NAMESPACE,
} = require('@opentelemetry/semantic-conventions');
const serviceName = process.env.OTEL_SERVICE_NAME || 'farmaclic-scraper';
const otlpEndpoint = process.env.OTEL_EXPORTER_OTLP_ENDPOINT || 'http://localhost:4317';
const sdk = new NodeSDK({
resource: resourceFromAttributes({
[ATTR_SERVICE_NAME]: serviceName,
[ATTR_SERVICE_NAMESPACE]: 'farmaclic',
}),
traceExporter: new OTLPTraceExporter({ url: otlpEndpoint }),
instrumentations: [
getNodeAutoInstrumentations({
'@opentelemetry/instrumentation-fs': { enabled: false },
'@opentelemetry/instrumentation-dns': { enabled: false },
}),
],
});
sdk.start();
const shutdown = async () => {
try {
await sdk.shutdown();
} catch (err) {
// eslint-disable-next-line no-console
console.error('OpenTelemetry shutdown failed', err);
}
};
process.on('SIGTERM', shutdown);
process.on('SIGINT', shutdown);