How to use

BoilerpipeHTMLParser

in

de.l3s.boilerpipe.sax

/**
 * Retrieves the {@link TextDocument} using a default HTML parser.
 */
public TextDocument getTextDocument() throws BoilerpipeProcessingException {
  return getTextDocument(new BoilerpipeHTMLParser());
}

/**
 * Constructs a {@link BoilerpipeHTMLParser} using the given {@link BoilerpipeHTMLContentHandler}.
 *
 * @param contentHandler
 */
public BoilerpipeHTMLParser(BoilerpipeHTMLContentHandler contentHandler) {
  super(new HTMLConfiguration());
  setContentHandler(contentHandler);
}

/**
 * Retrieves the {@link TextDocument} using the given HTML parser.
 * 
 * @param parser The parser used to transform the input into boilerpipe's internal representation.
 * @return The retrieved {@link TextDocument}
 * @throws BoilerpipeProcessingException
 */
public TextDocument getTextDocument(final BoilerpipeHTMLParser parser) throws BoilerpipeProcessingException {
  try {
    parser.parse(is);
  } catch (IOException e) {
    throw new BoilerpipeProcessingException(e);
  } catch (SAXException e) {
    throw new BoilerpipeProcessingException(e);
  }
  
  return parser.toTextDocument();
}

/**
 * Retrieves the {@link TextDocument} using the given HTML parser.
 * 
 * @param parser The parser used to transform the input into boilerpipe's internal representation.
 * @return The retrieved {@link TextDocument}
 * @throws BoilerpipeProcessingException
 */
public TextDocument getTextDocument(final BoilerpipeHTMLParser parser) throws BoilerpipeProcessingException {
  try {
    parser.parse(is);
  } catch (IOException e) {
    throw new BoilerpipeProcessingException(e);
  } catch (SAXException e) {
    throw new BoilerpipeProcessingException(e);
  }
  
  return parser.toTextDocument();
}

/**
 * Retrieves the {@link TextDocument} using the given HTML parser.
 * 
 * @param parser The parser used to transform the input into boilerpipe's internal representation.
 * @return The retrieved {@link TextDocument}
 * @throws BoilerpipeProcessingException
 */
public TextDocument getTextDocument(final BoilerpipeHTMLParser parser) throws BoilerpipeProcessingException {
  try {
    parser.parse(is);
  } catch (IOException e) {
    throw new BoilerpipeProcessingException(e);
  } catch (SAXException e) {
    throw new BoilerpipeProcessingException(e);
  }
  
  return parser.toTextDocument();
}

/**
 * Retrieves the {@link TextDocument} using a default HTML parser.
 */
public TextDocument getTextDocument() throws BoilerpipeProcessingException {
  return getTextDocument(new BoilerpipeHTMLParser());
}

/**
 * Constructs a {@link BoilerpipeHTMLParser} using the given {@link BoilerpipeHTMLContentHandler}.
 *
 * @param contentHandler
 */
public BoilerpipeHTMLParser(BoilerpipeHTMLContentHandler contentHandler) {
  super(new HTMLConfiguration());
  setContentHandler(contentHandler);
}

/**
 * Retrieves the {@link TextDocument} using the given HTML parser.
 * 
 * @param parser The parser used to transform the input into boilerpipe's internal representation.
 * @return The retrieved {@link TextDocument}
 * @throws BoilerpipeProcessingException
 */
public TextDocument getTextDocument(final BoilerpipeHTMLParser parser) throws BoilerpipeProcessingException {
  try {
    parser.parse(is);
  } catch (IOException e) {
    throw new BoilerpipeProcessingException(e);
  } catch (SAXException e) {
    throw new BoilerpipeProcessingException(e);
  }
  
  return parser.toTextDocument();
}

/**
 * Retrieves the {@link TextDocument} using a default HTML parser.
 */
public TextDocument getTextDocument() throws BoilerpipeProcessingException {
  return getTextDocument(new BoilerpipeHTMLParser());
}

/**
 * Constructs a {@link BoilerpipeHTMLParser} using the given {@link BoilerpipeHTMLContentHandler}.
 *
 * @param contentHandler
 */
public BoilerpipeHTMLParser(BoilerpipeHTMLContentHandler contentHandler) {
  super(new HTMLConfiguration());
  this.contentHandler = contentHandler;
  setContentHandler(contentHandler);
}

/**
 * Retrieves the {@link TextDocument} using a default HTML parser.
 */
public TextDocument getTextDocument() throws BoilerpipeProcessingException {
  return getTextDocument(new BoilerpipeHTMLParser());
}

/**
 * Constructs a {@link BoilerpipeHTMLParser} using the given {@link BoilerpipeHTMLContentHandler}.
 *
 * @param contentHandler
 */
public BoilerpipeHTMLParser(BoilerpipeHTMLContentHandler contentHandler) {
  super(new HTMLConfiguration());
  setContentHandler(contentHandler);
}