import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.tags.TableTag;
import org.htmlparser.util.NodeList;
/**
* <br>
* 標題: <br>
* 功能概要: <br>
* 版權: cityyouth.cn (c) 2005 <br>
* 公司:上海城市青年網(wǎng) <br>
* 創(chuàng )建時(shí)間:2005-12-21 <br>
* 修改時(shí)間: <br>
* 修改原因：
*
* @author 張偉
* @version 1.0
*/
public class TestYahoo {
public static void testHtml() {
try {
String sCurrentLine;
String sTotalString;
sCurrentLine = "";
sTotalString = "";
java.io.InputStream l_urlStream;
java.net.URL l_url = new java.net.URL(
"http://sports.sina.com.cn/iframe/nba/live/");
java.net.HttpURLConnection l_connection = (java.net.HttpURLConnection) l_url
.openConnection();
l_connection.connect();
l_urlStream = l_connection.getInputStream();
java.io.BufferedReader l_reader = new java.io.BufferedReader(
new java.io.InputStreamReader(l_urlStream));
while ((sCurrentLine = l_reader.readLine()) != null) {
sTotalString += sCurrentLine;
}
System.out.println(sTotalString);
System.out.println("====================");
String testText = extractText(sTotalString);
System.out.println(testText);
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 抽取純文本信息
*
* @param inputHtml
* @return
*/
public static String extractText(String inputHtml) throws Exception {
StringBuffer text = new StringBuffer();
Parser parser = Parser.createParser(new String(inputHtml.getBytes(),
"8859_1"), "8859-1");
// 遍歷所有的節點(diǎn)
NodeList nodes = parser.extractAllNodesThatMatch(new NodeFilter() {
public boolean accept(Node node) {
return true;
}
});
Node node = nodes.elementAt(0);
text.append(new String(node.toPlainTextString().getBytes("8859_1")));
return text.toString();
}
/**
* 讀取文件的方式來(lái)分析內容. filePath也可以是一個(gè)Url.
*
* @param resource
* 文件/Url
*/
public static void test5(String resource) throws Exception {
Parser myParser = new Parser(resource);
// 設置編碼
myParser.setEncoding("GBK");
String filterStr = "table";
NodeFilter filter = new TagNameFilter(filterStr);
NodeList nodeList = myParser.extractAllNodesThatMatch(filter);
TableTag tabletag = (TableTag) nodeList.elementAt(11);
System.out.println(tabletag.toHtml());
System.out.println("==============");
}
/*
* public static void main(String[] args) { TestYahoo testYahoo = new
* TestYahoo(); testYahoo.testHtml(); }
*/
public static void main(String[] args) throws Exception {
test5("http://sports.yahoo.com/nba/scoreboard");
}
}
本站僅提供存儲服務(wù)，所有內容均由用戶(hù)發(fā)布，如發(fā)現有害或侵權內容，請
點(diǎn)擊舉報。
