content/_data/references/pdfbox-reference-apache-nutch.json - pdfbox-docs - Git at Google

 {
     "name": "Apache Nutch",
     "url": "https://nutch.apache.org/",
     "license": "Apache License v2",
     "description": "Apache Nutch is open source web-search software. It builds on Apache Lucene, adding web-specifics, such as a crawler, a link-graph database, parsers for HTML and other document formats, etc."
 }
	{
	"name": "Apache Nutch",
	"url": "https://nutch.apache.org/",
	"license": "Apache License v2",
	"description": "Apache Nutch is open source web-search software. It builds on Apache Lucene, adding web-specifics, such as a crawler, a link-graph database, parsers for HTML and other document formats, etc."
	}