public Configuration getConf() 
{
    return this.conf;
}

 public ParseResult getParse(Content content) 
{
    HTMLMetaTags metaTags = new HTMLMetaTags();
    URL base;
    try {
      base = new URL(content.getBaseUrl());
    } catch (MalformedURLException e) {
      return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    }
    String text = "";
    String title = "";
    Outlink[] outlinks = new Outlink[0];
    Metadata metadata = new Metadata();
    // parse the content
    DocumentFragment root;
    try {
      byte[] contentInOctets = content.getContent();
      InputSource input = new InputSource(new ByteArrayInputStream(contentInOctets));
      EncodingDetector detector = new EncodingDetector(conf);
      detector.autoDetectClues(content, true);
      detector.addClue(sniffCharacterEncoding(contentInOctets), "sniffed");
      String encoding = detector.guessEncoding(content, defaultCharEncoding);
      metadata.set(Metadata.ORIGINAL_CHAR_ENCODING, encoding);
      metadata.set(Metadata.CHAR_ENCODING_FOR_CONVERSION, encoding);
      input.setEncoding(encoding);
      if (LOG.isTraceEnabled()) { LOG.trace("Parsing..."); }
      root = parse(input);
    } catch (IOException e) {
      return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    } catch (DOMException e) {
      return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    } catch (SAXException e) {
      return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    } catch (Exception e) {
      e.printStackTrace(LogUtil.getWarnStream(LOG));
      return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    }
    // get meta directives
    HTMLMetaProcessor.getMetaTags(metaTags, root, base);
    if (LOG.isTraceEnabled()) {
      LOG.trace("Meta tags for " + base + ": " + metaTags.toString());
    }
    // check meta directives
    if (!metaTags.getNoIndex()) {               // okay to index
      StringBuffer sb = new StringBuffer();
      if (LOG.isTraceEnabled()) { LOG.trace("Getting text..."); }
      utils.getText(sb, root);          // extract text
      text = sb.toString();
      sb.setLength(0);
      if (LOG.isTraceEnabled()) { LOG.trace("Getting title..."); }
      utils.getTitle(sb, root);         // extract title
      title = sb.toString().trim();
    }
    if (!metaTags.getNoFollow()) {              // okay to follow links
      ArrayList< Outlink > l = new ArrayList< Outlink >();   // extract outlinks
      URL baseTag = utils.getBase(root);
      if (LOG.isTraceEnabled()) { LOG.trace("Getting links..."); }
      utils.getOutlinks(baseTag!=null?baseTag:base, l, root);
      outlinks = l.toArray(new Outlink[l.size()]);
      if (LOG.isTraceEnabled()) {
        LOG.trace("found "+outlinks.length+" outlinks in "+content.getUrl());
      }
    }
    ParseStatus status = new ParseStatus(ParseStatus.SUCCESS);
    if (metaTags.getRefresh()) {
      status.setMinorCode(ParseStatus.SUCCESS_REDIRECT);
      status.setArgs(new String[] {metaTags.getRefreshHref().toString(),
        Integer.toString(metaTags.getRefreshTime())});      
    }
    ParseData parseData = new ParseData(status, title, outlinks,
                                        content.getMetadata(), metadata);
    ParseResult parseResult = ParseResult.createParseResult(content.getUrl(), 
                                                 new ParseImpl(text, parseData));
    // run filters on parse
    ParseResult filteredParse = this.htmlParseFilters.filter(content, parseResult, 
                                                             metaTags, root);
    if (metaTags.getNoCache()) {             // not okay to cache
      for (Map.Entry< org.apache.hadoop.io.Text, Parse > entry : filteredParse) 
        entry.getValue().getData().getParseMeta().set(Nutch.CACHING_FORBIDDEN_KEY, 
                                                      cachingPolicy);
    }
    return filteredParse;
}

 public static  void main(String[] args) throws Exception 
{
    //LOG.setLevel(Level.FINE);
    String name = args[0];
    String url = "file:"+name;
    File file = new File(name);
    byte[] bytes = new byte[(int)file.length()];
    DataInputStream in = new DataInputStream(new FileInputStream(file));
    in.readFully(bytes);
    Configuration conf = NutchConfiguration.create();
    HtmlParser parser = new HtmlParser();
    parser.setConf(conf);
    Parse parse = parser.getParse(
            new Content(url, url, bytes, "text/html", new Metadata(), conf)).get(url);
    System.out.println("data: "+parse.getData());
    System.out.println("text: "+parse.getText());
}

 public  void setConf(Configuration conf) 
{
    this.conf = conf;
    this.htmlParseFilters = new HtmlParseFilters(getConf());
    this.parserImpl = getConf().get("parser.html.impl", "neko");
    this.defaultCharEncoding = getConf().get(
        "parser.character.encoding.default", "windows-1252");
    this.utils = new DOMContentUtils(conf);
    this.cachingPolicy = getConf().get("parser.caching.forbidden.policy",
        Nutch.CACHING_FORBIDDEN_CONTENT);
}