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 assertion in the failing linkedom e2e test (#1972)
Martin Adámek5826f7562a17
diff --git a/test/e2e/linkedom-default-ts/actor/main.ts b/test/e2e/linkedom-default-ts/actor/main.tsindex 7ade2f017..5b91558f9 100644--- a/test/e2e/linkedom-default-ts/actor/main.ts+++ b/test/e2e/linkedom-default-ts/actor/main.ts@@ -11,15 +11,14 @@ if (process.env.STORAGE_IMPLEMENTATION === 'LOCAL') {const crawler = new LinkeDOMCrawler();-crawler.router.addDefaultHandler(async ({ window, document, enqueueLinks, request, log }) => {+crawler.router.addDefaultHandler(async ({ document, enqueueLinks, request, log }) => {const { url } = request;await enqueueLinks({globs: ['https://crawlee.dev/docs/**'],});- const pageTitle = window.document.title;- const { title } = document;- assert.strictEqual(pageTitle, title);+ const pageTitle = document.title;+ assert.notEqual(pageTitle, '');log.info(`URL: ${url} TITLE: ${pageTitle}`);await Dataset.pushData({ url, pageTitle });