doc-to-readable
Version:
Universal document-to-markdown and section splitter for HTML, URLs, and PDFs.
72 lines (71 loc) • 1.93 kB
JSON
{
"type": "module",
"name": "doc-to-readable",
"version": "1.5.3",
"description": "Universal document-to-markdown and section splitter for HTML, URLs, and PDFs.",
"main": "src/index.js",
"types": "src/index.d.ts",
"files": [
"src/"
],
"homepage": "https://ilyashusterman.github.io/doc-to-readable/",
"repository": {
"type": "git",
"url": "https://github.com/ilyashusterman/doc-to-readable.git"
},
"keywords": [
"markdown",
"markdown-converter",
"html-to-markdown",
"pdf-to-markdown",
"url-to-markdown",
"document-parser",
"content-extraction",
"readability",
"article-extractor",
"text-processing",
"document-processing",
"content-splitter",
"section-splitter",
"rag",
"retrieval-augmented-generation",
"ai-preprocessing",
"web-scraping",
"content-cleanup",
"universal-parser",
"cross-platform",
"browser-compatible",
"nodejs",
"typescript",
"javascript",
"turndown",
"readability-parser",
"pdfjs",
"dompurify"
],
"author": "",
"license": "MIT",
"scripts": {
"test": "node --experimental-vm-modules ./node_modules/.bin/jest src/__tests__/",
"test:watch": "node --experimental-vm-modules ./node_modules/.bin/jest src/__tests__/ --watch",
"test:standalone": "node src/__tests__/fetch-html-standalone-test.js",
"test:benchmark": "node --experimental-vm-modules ./node_modules/.bin/jest src/__tests__/benchmark.test.js"
},
"dependencies": {
"@mozilla/readability": "^0.6.0",
"dompurify": "^3.2.6",
"jsdom": "^26.1.0",
"marked": "^16.0.0",
"pdfjs-dist": "^5.3.93",
"turndown": "^7.2.0",
"turndown-plugin-gfm": "^1.0.2"
},
"devDependencies": {
"@babel/preset-env": "^7.28.0",
"@types/jest": "^30.0.0",
"@types/node": "^24.0.12",
"babel-jest": "^30.0.4",
"jest": "^30.0.4",
"ts-jest": "^29.4.0"
}
}