|
package com.jscud.test;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.nodes.TextNode;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.HtmlPage;
import org.htmlparser.visitors.TextExtractingVisitor;
import com.jscud.util.LogMan; //涓涓棩蹇楄褰曠被
/**
* 婕旂ず浜咹tml Parse鐨勫簲鐢?
*
* @author scud http://www.jscud.com
*/
public class ParseHtmlTest
{
public static void main(String[] args) throws Exception
{
String aFile = "e:/jscud/temp/test.htm";
String content = readTextFile(aFile, "GBK");
test1(content);
System.out.println("====================================");
test2(content);
System.out.println("====================================");
test3(content);
System.out.println("====================================");
test4(content);
System.out.println("====================================");
test5(aFile);
System.out.println("====================================");
//璁塊棶澶栭儴璧勬簮,鐩稿鎱?br />
test5("
System.out.println("====================================");
}
/**
* 璇誨彇鏂囦歡鐨勬柟寮忔潵鍒嗘瀽鍐呭.
* filePath涔熷彲浠ユ槸涓涓猆rl.
*
* @param resource 鏂囦歡/Url
*/
public static void test5(String resource) throws Exception
{
Parser myParser = new Parser(resource);
//璁劇疆緙栫爜
myParser.setEncoding("GBK");
HtmlPage visitor = new HtmlPage(myParser);
myParser.visitAllNodesWith(visitor);
String textInPage = visitor.getTitle();
System.out.println(textInPage);
}
/**
* 鎸夐〉闈㈡柟寮忓鐞?瀵逛竴涓爣鍑嗙殑Html欏甸潰,鎺ㄨ崘浣跨敤姝ょ鏂瑰紡.
*/
public static void test4(String content) throws Exception
{
Parser myParser;
myParser = Parser.createParser(content, "GBK");
HtmlPage visitor = new HtmlPage(myParser);
myParser.visitAllNodesWith(visitor);
String textInPage = visitor.getTitle();
System.out.println(textInPage);
}
/**
* 鍒╃敤Visitor妯″紡瑙ｆ瀽html欏甸潰.
*
* 灝忎紭鐐?緲昏瘧浜?lt;>絳夌鍙?
* 緙虹偣:濂藉絀烘牸,鏃犳硶鎻愬彇link
*
*/
public static void test3(String content) throws Exception
{
Parser myParser;
myParser = Parser.createParser(content, "GBK");
TextExtractingVisitor visitor = new TextExtractingVisitor();
myParser.visitAllNodesWith(visitor);
String textInPage = visitor.getExtractedText();
System.out.println(textInPage);
}
/**
* 寰楀埌鏅氭枃鏈拰閾炬帴鐨勫唴瀹?
*
* 浣跨敤浜嗚繃婊ゆ潯浠?
*/
public static void test2(String content) throws ParserException
{
Parser myParser;
NodeList nodeList = null;
myParser = Parser.createParser(content, "GBK");
NodeFilter textFilter = new NodeClassFilter(TextNode.class);
NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);
//鏆傛椂涓嶅鐞?meta
//NodeFilter metaFilter = new NodeClassFilter(MetaTag.class);
OrFilter lastFilter = new OrFilter();
lastFilter.setPredicates(new NodeFilter[] { textFilter, linkFilter });
nodeList = myParser.parse(lastFilter);
Node[] nodes = nodeList.toNodeArray();
for (int i = 0; i < nodes.length; i++)
{
Node anode = (Node) nodes[i];
String line = "";
if (anode instanceof TextNode)
{
TextNode textnode = (TextNode) anode;
//line = textnode.toPlainTextString().trim();
line = textnode.getText();
}
else if (anode instanceof LinkTag)
{
LinkTag linknode = (LinkTag) anode;
line = linknode.getLink();
//@todo 榪囨護(hù)jsp鏍囩:鍙互鑷繁瀹炵幇榪欎釜鍑芥暟
//line = StringFunc.replace(line, "<%.*%>", "");
}
if (isTrimEmpty(line))
continue;
System.out.println(line);
}
}
/**
* 瑙ｆ瀽鏅氭枃鏈妭鐐?
*
* @param content
* @throws ParserException
*/
public static void test1(String content) throws ParserException
{
Parser myParser;
Node[] nodes = null;
myParser = Parser.createParser(content, null);
nodes = myParser.extractAllNodesThatAre(TextNode.class); //exception could be thrown here
for (int i = 0; i < nodes.length; i++)
{
TextNode textnode = (TextNode) nodes[i];
String line = textnode.toPlainTextString().trim();
if (line.equals(""))
continue;
System.out.println(line);
}
}
/**
* 璇誨彇涓涓枃浠跺埌瀛楃涓查噷.
*
* @param sFileName 鏂囦歡鍚?br />
* @param sEncode String
* @return 鏂囦歡鍐呭
*/
public static String readTextFile(String sFileName, String sEncode)
{
StringBuffer sbStr = new StringBuffer();
try
{
File ff = new File(sFileName);
InputStreamReader read = new InputStreamReader(new FileInputStream(ff),
sEncode);
BufferedReader ins = new BufferedReader(read);
String dataLine = "";
while (null != (dataLine = ins.readLine()))
{
sbStr.append(dataLine);
sbStr.append("\r\n");
}
ins.close();
}
catch (Exception e)
{
LogMan.error("read Text File Error", e);
}
return sbStr.toString();
}
/**
* 鍘繪帀宸﹀彸絀烘牸鍚庡瓧絎︿覆鏄惁涓虹┖
* @param astr String
* @return boolean
*/
public static boolean isTrimEmpty(String astr)
{
if ((null == astr) || (astr.length() == 0))
{
return true;
}
if (isBlank(astr.trim()))
{
return true;
}
return false;
}
/**
* 瀛楃涓叉槸鍚︿負(fù)絀?null鎴栬呴暱搴︿負(fù)0.
* @param astr 婧愬瓧絎︿覆.
* @return boolean
*/
public static boolean isBlank(String astr)
{
if ((null == astr) || (astr.length() == 0))
{
return true;
}
else
{
return false;
}
}
}
|