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
Merge branch 'master' into feature/request_as_browser_update
Petr Patek466ed64e5962
diff --cc package.jsonindex b44bf6082,de501d1a1..3cce7942d--- a/package.json+++ b/package.json@@@ -49,11 -50,9 +50,10 @@@"lint:fix": "./node_modules/.bin/eslint ./src ./test --ext .js,.jsx --fix"},"dependencies": {+ "@apify/http-request": "^1.0.0","@apify/ps-tree": "^1.1.3",- "apify-client": "^0.5.13",- "apify-shared": "^0.1.41",- "bluebird": "^3.5.3",+ "apify-client": "^0.5.22",+ "apify-shared": "^0.1.51","cheerio": "^1.0.0-rc.2","content-type": "^1.0.4","express": "^4.16.4",diff --cc src/index.jsindex 3a77fe14f,451deba45..8630dbbf6--- a/src/index.js+++ b/src/index.js@@@ -16,13 -16,11 +16,12 @@@ import { RequestList, openRequestListimport { openRequestQueue } from './request_queue';import SettingsRotator from './settings_rotator';import { apifyClient, getMemoryInfo, isAtHome, publicUtils, logSystemInfo } from './utils';- import { browse, launchWebDriver } from './webdriver';import { puppeteerUtils } from './puppeteer_utils';import { socialUtils } from './utils_social';- import { enqueueLinks } from './enqueue_links';+ import { enqueueLinks } from './enqueue_links/enqueue_links';import PseudoUrl from './pseudo_url';import LiveViewServer from './live_view/live_view_server';+import { requestAsBrowser } from './utils_request';/* globals module */