Posted on 2009-05-22 14:11
landor 閱讀(1130)
評(píng)論(0) 編輯 收藏 所屬分類:
java
下載地址 http://sourceforge.net/projects/nekohtml
比如我想獲取
http://topic.csdn.net/u/20090521/11/db336c07-2dbc-4732-8229-cb99fcb9d10e.html網(wǎng)頁中kokobox的回復(fù)
package test;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import org.cyberneko.html.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;
public class Test {
public static void main(String[] argv) throws Exception {
//指定rul
URL url = new URL(
"http://topic.csdn.net/u/20090521/11/db336c07-2dbc-4732-8229-cb99fcb9d10e.html");
HttpURLConnection connection = (java.net.HttpURLConnection)url.openConnection();
connection.connect();
InputStream stream = connection.getInputStream();
DOMParser parser = new DOMParser();
//這行代碼等同于html頁面中的<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
parser.setProperty("http://cyberneko.org/html/properties/default-encoding","utf-8");
parser.parse(new InputSource(stream));
Document doc = parser.getDocument();
Node myNode= doc.getElementById("reply57194353_body");
print(myNode, "");
}
public static void print(Node node, String indent) {
System.out.println(node.getTextContent());
}
}