clean-web-scraper
Version:
A powerful Node.js web scraper that extracts clean, readable content from websites while keeping everything nicely organized. Perfect for creating AI training datasets! 🤖
33 lines • 685 B
JSON
{
"name": "clean-web-scraper",
"version": "4.3.5",
"main": "main.js",
"scripts": {
"start": "node main.js",
"test": "node --max-old-space-size=8192 example-usage.js"
},
"keywords": [
"clean-web-scraper",
"web-scraper",
"scraper",
"scraper-js",
"scraper-js-library",
"web-scraper-js",
"ai-ready-web-scraper",
"ai",
"fine-tune",
"data-processing",
"dataset"
],
"author": "",
"license": "ISC",
"description": "",
"dependencies": {
"@mozilla/readability": "^0.6.0",
"axios": "^1.8.4",
"eslint": "^9.23.0",
"jsdom": "^26.0.0",
"puppeteer": "^24.1.1",
"puppeteer-real-browser": "^1.3.22"
}
}