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
Improve Statistics a bit
Ondra Urban4db41dc35cfd
diff --git a/src/crawlers/basic_crawler.js b/src/crawlers/basic_crawler.jsindex ab473a39c..b11984070 100644--- a/src/crawlers/basic_crawler.js+++ b/src/crawlers/basic_crawler.js@@ -263,6 +263,8 @@ class BasicCrawler {await this.isRunningPromise;} finally {this.stats.stopLogging();+ const finalStats = this.stats.getCurrent();+ log.info('Crawler final request statistics:', finalStats);}}diff --git a/src/crawlers/statistics.js b/src/crawlers/statistics.jsindex e83cfd09a..a29aef534 100644--- a/src/crawlers/statistics.js+++ b/src/crawlers/statistics.js@@ -91,7 +91,7 @@ export default class Statistics {const totalMinutes = totalMillis / 1000 / 60;return {- avgDurationMillis: (this.totalJobDurationMillis / this.finishedJobs) || Infinity,+ avgDurationMillis: Math.round(this.totalJobDurationMillis / this.finishedJobs) || Infinity,perMinute: Math.round(this.finishedJobs / totalMinutes),finished: this.finishedJobs,failed: this.failedJobs,