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
feat: add `utils.downloadListOfUrls` to crawlee metapackage
Martin Adámek7b33b0a582a7
diff --git a/packages/crawlee/src/index.ts b/packages/crawlee/src/index.tsindex e31d10a8b..599d3a855 100644--- a/packages/crawlee/src/index.ts+++ b/packages/crawlee/src/index.ts@@ -1,7 +1,7 @@/* eslint-disable import/export */import { log, enqueueLinks } from '@crawlee/core';-import { social, sleep } from '@crawlee/utils';+import { social, sleep, downloadListOfUrls } from '@crawlee/utils';import { puppeteerUtils } from '@crawlee/puppeteer';import { playwrightUtils } from '@crawlee/playwright';@@ -22,4 +22,5 @@ export const utils = {enqueueLinks,social,sleep,+ downloadListOfUrls,};