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
test: fix cheerio test and remove logs
Martin Adámekbae07cdafa6f
diff --git a/test/core/crawlers/cheerio_crawler.test.ts b/test/core/crawlers/cheerio_crawler.test.tsindex 55c47f734..fc8635bb1 100644--- a/test/core/crawlers/cheerio_crawler.test.ts+++ b/test/core/crawlers/cheerio_crawler.test.ts@@ -252,7 +252,6 @@ describe('CheerioCrawler', () => {});test('should serialize body and html', async () => {- expect.assertions(3);const sources = [`${serverAddress}/special/html-type`];const requestList = await RequestList.open(null, sources);const tmp: any[] = [];@@ -263,9 +262,6 @@ describe('CheerioCrawler', () => {maxConcurrency: 1,requestHandler: ({ $, body, request }) => {tmp.push(body, $.html(), request.loadedUrl);- console.log(request.loadedUrl.length, sources[0].length);- console.log(body);- console.log($.html());},});