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
Update docs
Ondra Urbanf23f0cf23c62
diff --git a/src/enqueue_links.js b/src/enqueue_links.jsindex 0facaab2d..703ccdeb9 100644--- a/src/enqueue_links.js+++ b/src/enqueue_links.js@@ -47,6 +47,7 @@ export const constructPseudoUrlInstances = (pseudoUrls) => {* @param {Page} page* @param {string} selector* @returns {string[]}+ * @ignore*/export const extractUrlsFromPage = async (page, selector) => {/* istanbul ignore next */@@ -59,6 +60,7 @@ export const extractUrlsFromPage = async (page, selector) => {* @param {Function} $* @param {string} selector* @returns {string[]}+ * @ignore*/export const extraxtUrlsFromCheerio = ($, selector) => {return $(selector).map((i, el) => $(el).attr('href')).get().filter(href => !!href);@@ -149,7 +151,7 @@ let logDeprecationWarning = true;* ```* @return {Promise<QueueOperationInfo[]>}* Promise that resolves to an array of {@link QueueOperationInfo} objects.- * @memberOf puppeteer+ * @memberOf utils*/export const enqueueLinks = async (...args) => {// TODO: Remove after v1.0.0 gets released.