Java DOMFragmentParser类代码示例

import org.cyberneko.html.parsers.DOMFragmentParser; //导入依赖的package包/类
/**
 * @param html
 * @return text from HTML
 */
public static String htmlToText(String html) {

	DOMFragmentParser parser = new DOMFragmentParser();
	StringBuffer buffer = new StringBuffer();
	
	try {
		ByteArrayInputStream fin = new ByteArrayInputStream(html.getBytes("UTF-8"));
		InputSource inSource = new InputSource(fin);
		CoreDocumentImpl codeDoc = new CoreDocumentImpl();
		DocumentFragment doc = codeDoc.createDocumentFragment();
		parser.parse(inSource, doc);
		processNode(buffer, doc);
		fin.close();
	} catch (Exception e) {
		return null;
	}

	return buffer.toString();
}
 

import org.cyberneko.html.parsers.DOMFragmentParser; //导入依赖的package包/类
protected Node stringToNode(String str) {
	try {
		final DOMFragmentParser parser = new DOMFragmentParser();
		final DocumentFragment fragment = document.createDocumentFragment();
		parser.parse(new InputSource(new StringReader(str)), fragment);
		return fragment;

		// try and return the element itself if possible...
		// NodeList nl = fragment.getChildNodes();
		// for (int i=0; i<nl.getLength(); i++) if (nl.item(i).getNodeType()
		// == Node.ELEMENT_NODE) return nl.item(i);
		// return fragment;

	} catch (final Exception e) {
		throw new RuntimeException(e);
	}
}
 

import org.cyberneko.html.parsers.DOMFragmentParser; //导入依赖的package包/类
/**
 * 将 html 格式的文本过滤掉标签.
 * @param html
 *            html 格式的字符串
 * @return String
 * 			  过滤掉 html 标签后的文本。如果 html 为空，返回空串""
 */
private String htmlToText(String html) {
	if (html == null) {
		return "";
	}
	DOMFragmentParser parser = new DOMFragmentParser();
	CoreDocumentImpl codeDoc = new CoreDocumentImpl();
	InputSource inSource = new InputSource(new ByteArrayInputStream(html.getBytes()));
	inSource.setEncoding(textCharset);
	DocumentFragment doc = codeDoc.createDocumentFragment();

	try {
		parser.parse(inSource, doc);
	} catch (Exception e) {
		return "";
	}

	textBuffer = new StringBuffer();
	processNode(doc);
	return textBuffer.toString();
}
 

import org.cyberneko.html.parsers.DOMFragmentParser; //导入依赖的package包/类
public static Node parse(String content) throws SAXException, IOException {
  DOMFragmentParser parser = new DOMFragmentParser();
  HTMLDocument document = new HTMLDocumentImpl();
  DocumentFragment fragment = document.createDocumentFragment();

  InputSource is = new InputSource(new StringReader(content));
  parser.parse(is, fragment);
  return fragment;
}
 

import org.cyberneko.html.parsers.DOMFragmentParser; //导入依赖的package包/类
public static Node parse( String content ) throws SAXException, IOException {
  DOMFragmentParser parser = new DOMFragmentParser();
  HTMLDocument document = new HTMLDocumentImpl();
  DocumentFragment fragment = document.createDocumentFragment();

  InputSource is = new InputSource( new StringReader( content ) );
  parser.parse( is, fragment );
  return fragment;
}
 

import org.cyberneko.html.parsers.DOMFragmentParser; //导入依赖的package包/类
@Before
public void setup() throws Exception {
  conf = NutchConfiguration.create();
  conf.setBoolean("parser.html.form.use_action", true);
  utils = new DOMContentUtils(conf);
  DOMFragmentParser parser = new DOMFragmentParser();
  parser.setFeature(
      "http://cyberneko.org/html/features/scanner/allow-selfclosing-iframe",
      true);
  for (int i = 0; i < testPages.length; i++) {
    DocumentFragment node = new HTMLDocumentImpl().createDocumentFragment();
    try {
      parser.parse(
          new InputSource(new ByteArrayInputStream(testPages[i].getBytes())),
          node);
      testBaseHrefURLs[i] = new URL(testBaseHrefs[i]);
    } catch (Exception e) {
      Assert.assertTrue("caught exception: " + e, false);
    }
    testDOMs[i] = node;
  }
  answerOutlinks = new Outlink[][] {
      { new Outlink("http://www.nutch.org", "anchor"), },
      { new Outlink("http://www.nutch.org/", "home"),
          new Outlink("http://www.nutch.org/docs/bot.html", "bots"), },
      { new Outlink("http://www.nutch.org/", "separate this"),
          new Outlink("http://www.nutch.org/docs/ok", "from this"), },
      { new Outlink("http://www.nutch.org/", "home"),
          new Outlink("http://www.nutch.org/docs/1", "1"),
          new Outlink("http://www.nutch.org/docs/2", "2"), },
      { new Outlink("http://www.nutch.org/frames/top.html", ""),
          new Outlink("http://www.nutch.org/frames/left.html", ""),
          new Outlink("http://www.nutch.org/frames/invalid.html", ""),
          new Outlink("http://www.nutch.org/frames/right.html", ""), },
      { new Outlink("http://www.nutch.org/maps/logo.gif", ""),
          new Outlink("http://www.nutch.org/index.html", ""),
          new Outlink("http://www.nutch.org/maps/#bottom", ""),
          new Outlink("http://www.nutch.org/bot.html", ""),
          new Outlink("http://www.nutch.org/docs/index.html", ""), },
      { new Outlink("http://www.nutch.org/index.html", "whitespace test"), },
      {},
      { new Outlink("http://www.nutch.org/dummy.jsp", "test2"), },
      {},
      { new Outlink("http://www.nutch.org/;x", "anchor1"),
          new Outlink("http://www.nutch.org/g;x", "anchor2"),
          new Outlink("http://www.nutch.org/g;x?y#s", "anchor3") },
      {
          // this is tricky - see RFC3986 section 5.4.1 example 7
          new Outlink("http://www.nutch.org/g", "anchor1"),
          new Outlink("http://www.nutch.org/g?y#s", "anchor2"),
          new Outlink("http://www.nutch.org/;something?y=1", "anchor3"),
          new Outlink("http://www.nutch.org/;something?y=1#s", "anchor4"),
          new Outlink("http://www.nutch.org/;something?y=1;somethingelse",
              "anchor5") } };

}