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
Log exception on PuppeteerCrawler failed request
Ondra Urban3644e1998087
diff --git a/src/crawlers/puppeteer_crawler.js b/src/crawlers/puppeteer_crawler.jsindex 61034c34a..8068fea8a 100644--- a/src/crawlers/puppeteer_crawler.js+++ b/src/crawlers/puppeteer_crawler.js@@ -371,13 +371,14 @@ class PuppeteerCrawler {/*** @param {Object} options+ * @param {Error} options.error* @param {Request} options.request* @return {Promise<void>}* @ignore*/- async _defaultHandleFailedRequestFunction({ request }) { // eslint-disable-line class-methods-use-this+ async _defaultHandleFailedRequestFunction({ error, request }) { // eslint-disable-line class-methods-use-thisconst details = _.pick(request, 'id', 'url', 'method', 'uniqueKey');- log.error('PuppeteerCrawler: Request failed and reached maximum retries', details);+ log.exception(error, 'PuppeteerCrawler: Request failed and reached maximum retries', details);}}