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
{
"name": "crawlee-docs",
"description": "Documentation and examples for Crawlee. This package is not published to npm, only used locally for TS build checks.",
"type": "module",
"scripts": {
"typecheck": "tsc --noEmit"
},
"devDependencies": {
"typescript": "^6.0.3"
},
"dependencies": {
"@crawlee/browser-pool": "workspace:*",
"@crawlee/core": "workspace:*",
"@crawlee/got-scraping-client": "workspace:*",
"@crawlee/http-client": "workspace:*",
"@crawlee/impit-client": "workspace:*",
"@crawlee/otel": "workspace:*",
"@crawlee/stagehand": "workspace:*",
"@opentelemetry/api": "^1.10.0",
"@opentelemetry/exporter-trace-otlp-grpc": "^0.223.1",
"@opentelemetry/resources": "^2.12.1",
"@opentelemetry/sdk-node": "^0.223.1",
"@opentelemetry/sdk-trace-base": "^2.12.1",
"@opentelemetry/semantic-conventions": "^1.45.0",
"apify": "*",
"crawlee": "workspace:*",
"impit": "^0.14.9",
"pino": "^10.4.0",
"playwright-extra": "^4.3.6",
"puppeteer-extra": "^3.3.6",
"puppeteer-extra-plugin-stealth": "^2.11.2",
"winston": "^3.19.0"
}
}