How to use

toTextDocument

method

in

de.l3s.boilerpipe.sax.BoilerpipeHTMLParser

/**
 * 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 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();
}