Method parse

src/java/org/apache/nutch/parse/ParseUtil.java:138–156

Performs a parse by iterating through a List of preferred Parsers until a successful parse is performed and a Parse object is returned. If the parse is unsuccessful, a message is logged to the WARNING level, and an empty parse is returned. @throws ParserNotFound

(String url, WebPage page)

   *           If there is an error parsing.
   */
  public Parse parse(String url, WebPage page) throws ParseException {
    Parser[] parsers = null;
    Parse parse = null;

    String contentType = TableUtil.toString(page.getContentType());
    parsers = this.parserFactory.getParsers(contentType, url);

    for (int i = 0; i < parsers.length; i++) {
      parse = parse(url, page, parsers[i]);
      if (parse != null && ParseStatusUtils.isSuccess(parse.getParseStatus())) {
        return parse;
      }
    }

    LOG.warn("Unable to successfully parse content " + url + " of type "
        + contentType);
    return ParseStatusUtils.getEmptyParse(new ParseException(
        "Unable to successfully parse content"), null);
  }

  private Parse parse(String url, WebPage page, Parser parser) {
    if (LOG.isDebugEnabled()) {