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
Changed the order of logged statistics (#795)
Jan Bártacf0120d2d51e
diff --git a/src/crawlers/basic_crawler.js b/src/crawlers/basic_crawler.jsindex fc2d9f1d9..2a0854918 100644--- a/src/crawlers/basic_crawler.js+++ b/src/crawlers/basic_crawler.js@@ -327,10 +327,10 @@ class BasicCrawler {const finalStats = this.stats.calculate();const { requestsFailed, requestsFinished } = this.stats.state;this.log.info('Final request statistics:', {- ...finalStats,requestsFinished,requestsFailed,retryHistogram: this.stats.requestRetryHistogram,+ ...finalStats,});}}