import org.ccil.cowan.tagsoup.Parser;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import java.io.IOException;
import java.io.StringReader;
public class TagSoupExample {
public static void main(String[] args) {
String html = "<html><body><h1>Title</h1><p>Paragraph</p></body></html>";
try {
XMLReader reader = new Parser();
reader.setContentHandler(new ContentHandler() {
private StringBuilder stringBuilder = new StringBuilder();
@Override
public void startElement(String uri, String localName, String qName, Attributes atts) throws SAXException { }
@Override
public void endElement(String uri, String localName, String qName) throws SAXException { }
@Override
public void characters(char[] ch, int start, int length) throws SAXException {
stringBuilder.append(ch, start, length);
}
@Override
public void skippedEntity(String name) throws SAXException { }
@Override
public void startDocument() throws SAXException { }
@Override
public void endDocument() throws SAXException {
System.out.println("Parsed HTML: " + stringBuilder.toString());
}
});
reader.parse(new InputSource(new StringReader(html)));
e.printStackTrace();
}
}
}
<dependency>
<groupId>org.ccil.cowan.tagsoup</groupId>
<artifactId>tagsoup</artifactId>
<version>1.2.1</version>
</dependency>
