How to use

HTMLHighlighter

in

de.l3s.boilerpipe.sax

/**
 * Creates a new {@link HTMLHighlighter}, which is set-up to return the full
 * HTML text, with the extracted text portion <b>highlighted</b>.
 */
public static HTMLHighlighter newHighlightingInstance() {
  return new HTMLHighlighter(false);
}

private HTMLHighlighter(final boolean extractHTML) {
  if (extractHTML) {
    setOutputHighlightOnly(true);
    setExtraStyleSheet("");
    setPreHighlight("");
    setPostHighlight("");
  }
}

/**
 * returns the article from an document with its basic html structure. 
 * 
 * @param HTMLDocument
 * @param URI the uri from the document for resolving the relative anchors in the document to absolute anchors
 * @return String
 */
public String process(HTMLDocument htmlDoc, URI docUri, final BoilerpipeExtractor extractor) {
  final HTMLHighlighter hh = HTMLHighlighter.newExtractingInstance();
  hh.setOutputHighlightOnly(true);
  TextDocument doc;
  String text = "";
  try {
    doc = new BoilerpipeSAXInput(htmlDoc.toInputSource()).getTextDocument();
    extractor.process(doc);
    final InputSource is = htmlDoc.toInputSource();
    text = hh.process(doc, is);
  } catch (Exception ex) {
    return null;
  }
  return removeNotAllowedTags(text, docUri);
}

/**
 * Processes the given {@link TextDocument} and the original HTML text (as a
 * String).
 * 
 * @param doc
 *            The processed {@link TextDocument}.
 * @param origHTML
 *            The original HTML document.
 * @throws BoilerpipeProcessingException
 */
public String process(final TextDocument doc, final String origHTML)
    throws BoilerpipeProcessingException {
  return process(doc, new InputSource(new StringReader(origHTML)));
}

/**
 * Processes the given {@link TextDocument} and the original HTML text (as a
 * String).
 * 
 * @param doc
 *            The processed {@link TextDocument}.
 * @param origHTML
 *            The original HTML document.
 * @return The highlighted HTML.
 * @throws BoilerpipeProcessingException
 */
public String process(final TextDocument doc, final String origHTML)
    throws BoilerpipeProcessingException {
  return process(doc, new InputSource(new StringReader(origHTML)));
}

private HTMLHighlighter(final boolean extractHTML) {
  if (extractHTML) {
    setOutputHighlightOnly(true);
    setExtraStyleSheet("\n<style type=\"text/css\">\n"
        + "A:before { content:' '; } \n" //
        + "A:after { content:' '; } \n" //
        + "SPAN:before { content:' '; } \n" //
        + "SPAN:after { content:' '; } \n" //
        + "</style>\n");
    setPreHighlight("");
    setPostHighlight("");
  }
}

/**
 * Creates a new {@link HTMLHighlighter}, which is set-up to return only the
 * extracted HTML text, including enclosed markup.
 */
public static HTMLHighlighter newExtractingInstance() {
  return new HTMLHighlighter(true);
}

/**
 * Processes the given {@link TextDocument} and the original HTML text (as a
 * String).
 * 
 * @param doc
 *            The processed {@link TextDocument}.
 * @param origHTML
 *            The original HTML document.
 * @return The highlighted HTML.
 * @throws BoilerpipeProcessingException
 */
public String process(final TextDocument doc, final String origHTML)
    throws BoilerpipeProcessingException {
  return process(doc, new InputSource(new StringReader(origHTML)));
}

private HTMLHighlighter(final boolean extractHTML) {
  if (extractHTML) {
    setOutputHighlightOnly(true);
    setExtraStyleSheet("\n<style type=\"text/css\">\n"
        + "A:before { content:' '; } \n" //
        + "A:after { content:' '; } \n" //
        + "SPAN:before { content:' '; } \n" //
        + "SPAN:after { content:' '; } \n" //
        + "</style>\n");
    setPreHighlight("");
    setPostHighlight("");
  }
}

/**
 * Creates a new {@link HTMLHighlighter}, which is set-up to return the full
 * HTML text, with the extracted text portion <b>highlighted</b>.
 */
public static HTMLHighlighter newHighlightingInstance() {
  return new HTMLHighlighter(false);
}

/**
 * Processes the given {@link TextDocument} and the original HTML text (as a
 * String).
 * 
 * @param doc
 *            The processed {@link TextDocument}.
 * @param origHTML
 *            The original HTML document.
 * @return The highlighted HTML.
 * @throws BoilerpipeProcessingException
 */
public String process(final TextDocument doc, final String origHTML)
    throws BoilerpipeProcessingException {
  return process(doc, new InputSource(new StringReader(origHTML)));
}

private HTMLHighlighter(final boolean extractHTML) {
  if (extractHTML) {
    setOutputHighlightOnly(true);
    setExtraStyleSheet("\n<style type=\"text/css\">\n"
        + "A:before { content:' '; } \n" //
        + "A:after { content:' '; } \n" //
        + "SPAN:before { content:' '; } \n" //
        + "SPAN:after { content:' '; } \n" //
        + "</style>\n");
    setPreHighlight("");
    setPostHighlight("");
  }
}

/**
 * Creates a new {@link HTMLHighlighter}, which is set-up to return the full
 * HTML text, with the extracted text portion <b>highlighted</b>.
 */
public static HTMLHighlighter newHighlightingInstance() {
  return new HTMLHighlighter(false);
}

public String process(final URL url, final BoilerpipeExtractor extractor)
    throws IOException, BoilerpipeProcessingException, SAXException {
  final HTMLDocument htmlDoc = HTMLFetcher.fetch(url);
  final TextDocument doc = new BoilerpipeSAXInput(htmlDoc.toInputSource())
      .getTextDocument();
  extractor.process(doc);
  final InputSource is = htmlDoc.toInputSource();
  return process(doc, is);
}

/**
 * Creates a new {@link HTMLHighlighter}, which is set-up to return only the
 * extracted HTML text, including enclosed markup.
 */
public static HTMLHighlighter newExtractingInstance() {
  return new HTMLHighlighter(true);
}

/**
 * Fetches the given {@link URL} using {@link HTMLFetcher} and processes the
 * retrieved HTML using the specified {@link BoilerpipeExtractor}.
 * 
 *            The processed {@link TextDocument}.
 *            The original HTML document.
 * @return The highlighted HTML.
 * @throws BoilerpipeProcessingException
 */
public String process(final URL url, final BoilerpipeExtractor extractor)
    throws IOException, BoilerpipeProcessingException, SAXException {
  final HTMLDocument htmlDoc = HTMLFetcher.fetch(url);
  final TextDocument doc = new BoilerpipeSAXInput(htmlDoc.toInputSource())
      .getTextDocument();
  extractor.process(doc);
  final InputSource is = htmlDoc.toInputSource();
  return process(doc, is);
}

/**
 * Creates a new {@link HTMLHighlighter}, which is set-up to return only the
 * extracted HTML text, including enclosed markup.
 */
public static HTMLHighlighter newExtractingInstance() {
  return new HTMLHighlighter(true);
}

/**
 * Fetches the given {@link URL} using {@link HTMLFetcher} and processes the
 * retrieved HTML using the specified {@link BoilerpipeExtractor}.
 * 
 *            The processed {@link TextDocument}.
 *            The original HTML document.
 * @return The highlighted HTML.
 * @throws BoilerpipeProcessingException
 */
public String process(final URL url, final BoilerpipeExtractor extractor)
    throws IOException, BoilerpipeProcessingException, SAXException {
  final HTMLDocument htmlDoc = HTMLFetcher.fetch(url);
  final TextDocument doc = new BoilerpipeSAXInput(htmlDoc.toInputSource())
      .getTextDocument();
  extractor.process(doc);
  final InputSource is = htmlDoc.toInputSource();
  return process(doc, is);
}

/**
 * Creates a new {@link HTMLHighlighter}, which is set-up to return the full
 * HTML text, with the extracted text portion <b>highlighted</b>.
 */
public static HTMLHighlighter newHighlightingInstance() {
  return new HTMLHighlighter(false);
}

/**
 * Fetches the given {@link URL} using {@link HTMLFetcher} and processes the
 * retrieved HTML using the specified {@link BoilerpipeExtractor}.
 * 
 * @param doc
 *            The processed {@link TextDocument}.
 * @param is
 *            The original HTML document.
 * @return The highlighted HTML.
 * @throws BoilerpipeProcessingException
 */
public String process(final URL url, final BoilerpipeExtractor extractor)
    throws IOException, BoilerpipeProcessingException, SAXException {
  final HTMLDocument htmlDoc = HTMLFetcher.fetch(url);
  final TextDocument doc = new BoilerpipeSAXInput(htmlDoc.toInputSource())
      .getTextDocument();
  extractor.process(doc);
  final InputSource is = htmlDoc.toInputSource();
  return process(doc, is);
}