Skip to content

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.

1.5 KB
Raw Blame
{
    "name": "@crawlee/utils",
    "version": "4.0.0",
    "description": "A set of shared utilities that can be used by crawlers",
    "engines": {
        "node": ">=22.13.0"
    },
    "type": "module",
    "exports": {
        ".": "./dist/index.js",
        "./internal": "./dist/internal.js",
        "./package.json": "./package.json"
    },
    "keywords": [
        "apify",
        "crawlers",
        "crawling",
        "utilities",
        "utils"
    ],
    "author": {
        "name": "Apify",
        "email": "[email protected]",
        "url": "https://apify.com"
    },
    "contributors": [
        "Ondra Urban <[email protected]>"
    ],
    "license": "Apache-2.0",
    "repository": {
        "type": "git",
        "url": "git+https://github.com/apify/crawlee"
    },
    "bugs": {
        "url": "https://github.com/apify/crawlee/issues"
    },
    "homepage": "https://crawlee.dev",
    "scripts": {
        "build": "pnpm clean && pnpm compile && pnpm copy",
        "clean": "rimraf ./dist",
        "compile": "tsc -p tsconfig.build.json",
        "copy": "tsx ../../scripts/copy.ts"
    },
    "dependencies": {
        "@apify/validations": "^1.1.4",
        "@crawlee/http-client": "workspace:*",
        "@crawlee/types": "workspace:*",
        "@types/sax": "^1.2.7",
        "cheerio": "^1.2.0",
        "domhandler": "^6.0.1",
        "file-type": "^21.3.4",
        "robots-parser": "^3.0.1",
        "sax": "^1.6.1",
        "tldts": "^7.4.22",
        "tslib": "^2.9.1",
        "whatwg-mimetype": "^5.0.0",
        "zod": "catalog:"
    }
}