HtmlCleaner is an HTML parser written in Java. It transforms dirty HTML to well-formed XML following the same rules that most web-browsers use.
'net.sourceforge.htmlcleaner:htmlcleaner:2.12'
<dependency>
<groupId>net.sourceforge.htmlcleaner</groupId>
<artifactId>htmlcleaner</artifactId>
<version>2.12</version>
</dependency>
<dependency org="net.sourceforge.htmlcleaner" name="htmlcleaner" rev="2.12"/>
"net.sourceforge.htmlcleaner", "htmlcleaner", "2.12"