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
import ExecutionEnvironment from '@docusaurus/ExecutionEnvironment';
export default ExecutionEnvironment.canUseDOM ? {
onRouteUpdate() {
// this forces deferred execution that ensures `window.location` is in sync
setTimeout(() => {
// Don't track page views on development
if (process.env.NODE_ENV === 'production' && window.analytics) {
window.analytics.page({
app: 'crawlee',
path: window.location.pathname,
url: window.location.href,
search: window.location.search,
});
}
}, 0);
},
} : null;