{
  "name": "markdown-crawler",
  "version": "1.0.17",
  "description": "A powerful web crawler that extracts content from web pages and converts them to clean Markdown format, with support for code blocks and GitHub Flavored Markdown",
  "main": "dist/index.js",
  "bin": {
    "markdown-crawler": "dist/cli.js"
  },
  "scripts": {
    "build": "tsc && chmod +x ./dist/cli.js",
    "dev": "tsc --watch",
    "clean": "rm -rf dist",
    "prebuild": "npm run clean",
    "test": "node dist/cli.js -- https://sample.site/docs/ sample.docs.yaml",
    "lint": "tsc --noEmit",
    "prepub": "npm version patch",
    "pub": "npm publish --access public"
  },
  "files": [
    "dist",
    "README.md",
    "README-*.md",
    "LICENSE"
  ],
  "keywords": [
    "web-crawler",
    "markdown",
    "html-to-markdown",
    "readability",
    "content-extraction",
    "playwright",
    "cli-tool",
    "web-scraping",
    "gfm",
    "turndown",
    "ai",
    "llm",
    "ai-content",
    "ai-processing",
    "machine-learning",
    "nlp",
    "text-extraction",
    "semantic-content",
    "structured-data",
    "clean-text"
  ],
  "author": "gkctou@gmail.com",
  "license": "MIT",
  "repository": {
    "type": "git",
    "url": "git+https://github.com/gkctou/md-crawler.git"
  },
  "bugs": {
    "url": "https://github.com/gkctou/md-crawler/issues"
  },
  "homepage": "https://github.com/gkctou/md-crawler#readme",
  "engines": {
    "node": ">=16.0.0"
  },
  "devDependencies": {
    "@types/node": "^22.13.14",
    "typescript": "^5.8.2"
  },
  "dependencies": {
    "@mozilla/readability": "^0.6.0",
    "@types/minimatch": "^5.1.2",
    "cheerio": "^1.0.0",
    "commander": "^13.1.0",
    "jsdom": "^26.0.0",
    "minimatch": "^10.0.1",
    "remark-parse": "^11.0.0",
    "remark-stringify": "^11.0.0",
    "turndown": "^7.2.0",
    "turndown-plugin-gfm": "^1.0.2",
    "unified": "^11.0.5",
    "unist-util-visit": "^5.0.0",
    "yaml": "^2.7.0"
  }
}