{"id":56691,"library":"htmlcleaner","title":"HtmlCleaner","description":"HtmlCleaner is an HTML parser written in Java that transforms dirty HTML to well-formed XML following the same rules that most web-browsers use.","status":"active","version":"2.6.1","language":"java","source_language":null,"source_url":"https://svn.code.sf.net/p/htmlcleaner/code/tags/htmlcleaner-2.29","tags":["html","parser","xml","cleaner","java"],"install":[{"cmd":"\n net.sourceforge.htmlcleaner\n htmlcleaner\n 2.6.1\n","lang":"xml","label":"Maven"},{"cmd":"implementation 'net.sourceforge.htmlcleaner:htmlcleaner:2.6.1'","lang":"groovy","label":"Gradle"}],"dependencies":[],"imports":[{"symbol":"HtmlCleaner","correct":"org.htmlcleaner.HtmlCleaner"}],"quickstart":{"code":"import org.htmlcleaner.HtmlCleaner;\nimport org.htmlcleaner.TagNode;\n\npublic class Example {\n public static void main(String[] args) throws Exception {\n HtmlCleaner cleaner = new HtmlCleaner();\n TagNode node = cleaner.clean(\"

Hello

\");\n System.out.println(node.getText());\n }\n}","lang":"java","description":"Parses dirty HTML into a clean TagNode tree."},"warnings":[],"env_vars":null,"search_vec":"'browser':27 'cleaner':32 'dirti':12 'follow':19 'form':17 'html':5,13,29 'htmlcleaner':1,2 'java':9,33 'parser':6,30 'rule':22 'transform':11 'use':28 'web':26 'web-brows':25 'well':16 'well-form':15 'written':7 'xml':18,31","created_at":"2026-06-15T10:46:32.667421+00:00","updated_at":"2026-06-15T10:46:32.667421+00:00","problems":[],"ecosystem":"maven","meta_description":null,"install_score":null,"quickstart_score":null,"quickstart_tag":null,"pypi_latest":null,"cli_name":null,"cli_version":null,"type":"library","homepage":"http://htmlcleaner.sourceforge.net/","github":null,"docs":"https://appdoc.app/artifact/net.sourceforge.htmlcleaner/htmlcleaner/","changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["utility"],"base_url":null,"auth_type":null,"provenance":{"verified_status":null,"verified_at":null,"last_verified":"2026-06-15","next_check":"2026-12-12","install_tag":null}}