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
Update examples
Ondra Urbanb384c5ea52c3
diff --git a/examples/hello_world.js b/examples/hello_world.jsindex c20c3920d..9901b84c8 100644--- a/examples/hello_world.js+++ b/examples/hello_world.js@@ -17,7 +17,7 @@ Apify.main(async () => {handlePageFunction: async ({ request, page }) => {const title = await page.title();console.log(`Title of ${request.url}: ${title}`);- await Apify.utils.puppeteer.enqueueLinks({ page, selector: 'a', pseudoUrls, requestQueue });+ await Apify.utils.enqueueLinks({ page, selector: 'a', pseudoUrls, requestQueue });},maxRequestsPerCrawl: 100,maxConcurrency: 10,diff --git a/examples/puppeteer_crawler.js b/examples/puppeteer_crawler.jsindex 6e0c83176..2cab403ad 100644--- a/examples/puppeteer_crawler.js+++ b/examples/puppeteer_crawler.js@@ -70,7 +70,7 @@ Apify.main(async () => {await Apify.pushData(data);// Find a link to the next page and enqueue it if it exists.- const infos = await Apify.utils.puppeteer.enqueueLinks({+ const infos = await Apify.utils.enqueueLinks({page,requestQueue,selector: '.morelink',