Tengo una idea para matar y lanzar titiritero automáticamente cada 20 minutos. El navegador de titiriteros (cromo) se cerrará automáticamente cuando finalice el trabajo de extracción/análisis, y luego, después de 20 minutos, se reiniciará el nuevo navegador, por lo que no consumirá más recursos. Estoy usando el grupo de navegadores (clúster) para este método.

 import cluster from 'cluster' import * as os from 'os' import * as process from 'process' import * as puppeteer from 'puppeteer' const launchOptions = { args: [ '--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage', '--disable-accelerated-2d-canvas', '--no-first-run', '--no-zygote', '--single-process', '--disable-gpu' ], headless: true } let lastProcessUptime = [] let userAgentString = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36' let viewportSize = { width: 1920, height: 1080 } let CPUsNum = os.cpus().length CPUsNum = 1 // Set this number as how many browser page do you want to launch simultaneously const runThis = async (processID) => { const browser = await puppeteer.launch(launchOptions) const page = await browser.newPage() await page.setUserAgent(userAgentString) await page.setViewport(viewportSize) await page.setRequestInterception(true) page.on('request', (request) => { let blockedResources = ['stylesheet', 'font', 'image'] if (blockedResources.includes(request.resourceType())) { await request.abort() } else { await request.continue() } }); await page.goto(url, { waitUntil: 'networkidle0' }) // ... and do stuff // ... then close the page and browser and also kill the process await page.close() await browser.close() lastProcessUptime.push({ pid: process.pid, uptime: Math.round(process.uptime() * 1000) }) process.kill(processID) process.exit(0) } if (!cluster.isWorker) { console.log(`Primary ${process.pid} is running`) // Fork workers. for (let i = 0; i < CPUsNum; i++) { cluster.fork() } cluster.on('exit', (worker, code, signal) => { console.log(`worker ${worker.process.pid} died`) /*with code: ${code} and signal ${signal}*/ setTimeout(() => cluster.fork(), (20 * 60 * 1000) - lastProcessUptime[lastProcessUptime.findIndex(process => process.pid === worker.process.pid)].uptime) //lets recreate the worker that died }) } else { let processID = process.pid console.log(`Worker ${processID} started`) ;(async (processID: number) => { await runThis(processID) })(processID) }