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 logging in a test
Ondra Urban50522a28d08f
diff --git a/test/cheerio_crawler.js b/test/cheerio_crawler.jsindex 7649a9c9d..6e5ef6e99 100644--- a/test/cheerio_crawler.js+++ b/test/cheerio_crawler.js@@ -283,6 +283,7 @@ describe('CheerioCrawler', () => {});it('by throwing on unsupported Content-Encoding', async () => {+ log.setLevel(log.LEVELS.OFF);const sourceFilePath = path.join(__dirname, 'data', 'sample.html');let handlePageInvocationCount = 0;let allErrors = [];@@ -300,7 +301,7 @@ describe('CheerioCrawler', () => {const response = fs.createReadStream(sourceFilePath);response.headers = {'content-type': 'text/html', // to avoid throwing- 'content-encoding': 'compress',+ 'content-encoding': 'bad-encoding',};Object.assign(response, responseMock);@@ -319,8 +320,9 @@ describe('CheerioCrawler', () => {expect(handlePageInvocationCount).to.be.eql(0);allErrors.forEach((err) => {expect(err).to.include('Invalid Content-Encoding header');- expect(err).to.include('compress');+ expect(err).to.include('bad-encoding');});+ log.setLevel(log.LEVELS.ERROR);});});