Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
TypeScript apifyautomationcrawlercrawlingheadlessheadless-chromejavascriptnodejsnpmplaywrightpuppeteerscraperscrapingtypescriptweb-crawlerweb-crawlingweb-scraping
Add focusing of oldest tabs in browser
Ondra Urban47a98617a15a
diff --git a/src/puppeteer_pool.js b/src/puppeteer_pool.jsindex 37847bb73..3188f01f8 100644--- a/src/puppeteer_pool.js+++ b/src/puppeteer_pool.js@@ -472,6 +472,7 @@ class PuppeteerPool {try {const browser = await instance.browserPromise;const page = await browser.newPage();+ this._focusOldestTab(browser).catch(() => log.debug('Could not focus oldest tab.'));this.pagesToInstancesMap.set(page, instance);return this._decoratePage(page);} catch (err) {@@ -507,6 +508,18 @@ class PuppeteerPool {return page;}+ /**+ * Tells Chromium to focus oldest tab. This is to work around Chromium+ * throttling CPU and network in inactive tabs.+ *+ * @param {Browser} browser+ * @ignore+ */+ async _focusOldestTab(browser) { // eslint-disable-line class-methods-use-this+ const pages = await browser.pages();+ if (pages.length > 1) return pages[1].bringToFront();+ }+/*** Closes all open browsers.* @return {Promise}