HtmlContentExtractor.java

package com.qwant;

import org.ccil.cowan.tagsoup.jaxp.SAXParserImpl;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;

public class HtmlContentExtractor extends DefaultHandler {
    final static SAXParserImpl parser;

    static {
        try {
            parser = SAXParserImpl.newInstance(null);
        } catch (SAXException | IOException e) {
            throw new Error(e);
        }
    }

    StringBuilder contents = new StringBuilder();

    public static CharSequence parseText(String s) {
        try {
            InputStream stream = new ByteArrayInputStream(s.getBytes(StandardCharsets.UTF_8));
            HtmlContentExtractor myHandler = new HtmlContentExtractor();
            synchronized (parser) {
                parser.parse(stream, myHandler);
            }
            return myHandler.getContents();
        } catch (SAXException | IOException e) {
            return s;
        }
    }

    @Override
    public void startElement(String uri, String localName, String qName, Attributes attributes) {
        if (localName.equals("br")) contents.append(' ');
    }

    @Override
    public void ignorableWhitespace(char[] ch, int start, int length) {
        contents.append(ch[start]);
    }


    @Override
    public void characters(char[] ch, int start, int length) {
        contents.append(ch, start, length);
    }

    CharSequence getContents() {
        return contents;
    }
}