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
chore: add logging to a flaky test
Ondra Urban9fbda1f15d8d
diff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex 1f07305f3..ad09da60c 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -77,13 +77,8 @@ jobs:node-version: 14registry-url: https://registry.npmjs.org/-- name: Load Cache- uses: actions/cache@v2- with:- path: |- node_modules- build- key: cache-${{ github.run_id }}-v14+ name: Install Dependencies+ run: npm install-# Determine if this is a beta or latest releasename: Set Release Tagdiff --git a/test/crawlers/cheerio_crawler.test.js b/test/crawlers/cheerio_crawler.test.jsindex 59a00f907..b09321ffd 100644--- a/test/crawlers/cheerio_crawler.test.js+++ b/test/crawlers/cheerio_crawler.test.js@@ -702,8 +702,15 @@ describe('CheerioCrawler', () => {const { sessions } = cheerioCrawler.sessionPool;expect(sessions.length).toBe(4);sessions.forEach((session) => {+ // TODO this test is flaky in CI and we need some more info to debug why.+ if (session.errorScore !== 1) {+ console.log('SESSIONS:');+ console.dir(sessions);+ }+expect(session.errorScore).toEqual(1);});+log.setLevel(log.LEVELS.ERROR);});