StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("htmlExtractor", HtmlExtractor.class);
        htmlExtractor = container.getComponent("htmlExtractor");
        htmlExtractor.addMetadata("title", "//TITLE");
    }

    public void test_getHtml_utf8() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_utf8.html");

     *
     * @param name the name of the metadata field
     * @param xpath the XPath expression to extract the metadata value
     */
    public void addMetadata(final String name, final String xpath) {
        metadataXpathMap.put(name, xpath);
    }

    /*
     * (non-Javadoc)
     *
     * @see