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
Fixing Puppeteer pool - errors of page.goto() not catched
Marek Trunkat49085bb663c6
diff --git a/src/puppeteer_crawler.js b/src/puppeteer_crawler.jsindex 7c63d7a20..a8de1a81d 100644--- a/src/puppeteer_crawler.js+++ b/src/puppeteer_crawler.js@@ -247,8 +247,9 @@ export default class PuppeteerCrawler {const page = await this.puppeteerPool.newPage();try {- const gotoPromise = this.gotoFunction({ page, request, puppeteerPool: this.puppeteerPool });- const pageOperationsPromise = gotoPromise.then((response) => {+ const pageOperationsPromise = this+ .gotoFunction({ page, request, puppeteerPool: this.puppeteerPool })+ .then((response) => {return Promise.race([this.handlePageFunction({ page, request, puppeteerPool: this.puppeteerPool, response }),createTimeoutPromise(this.handlePageTimeoutSecs * 1000, 'PuppeteerCrawler: handlePageFunction timed out.'),