|
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; //一個日志記錄類
/**
* 演示了Html Parse的應(yīng)用.
*
* @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("====================================");
//訪問外部資源,相對慢
test5("
System.out.println("====================================");
}
/**
* 讀取文件的方式來分析內(nèi)容.
* filePath也可以是一個Url.
*
* @param resource 文件/Url
*/
public static void test5(String resource) throws Exception
{
Parser myParser = new Parser(resource);
//設(shè)置編碼
myParser.setEncoding("GBK");
HtmlPage visitor = new HtmlPage(myParser);
myParser.visitAllNodesWith(visitor);
String textInPage = visitor.getTitle();
System.out.println(textInPage);
}
/**
* 按頁面方式處理.對一個標準的Html頁面,推薦使用此種方式.
*/
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);
}
/**
* 利用Visitor模式解析html頁面.
*
* 小優(yōu)點:翻譯了<>等符號
* 缺點:好多空格,無法提取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);
}
/**
* 得到普通文本和鏈接的內(nèi)容.
*
* 使用了過濾條件.
*/
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);
//暫時不處理 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 過濾jsp標簽:可以自己實現(xiàn)這個函數(shù)
//line = StringFunc.replace(line, "<%.*%>", "");
}
if (isTrimEmpty(line))
continue;
System.out.println(line);
}
}
/**
* 解析普通文本節(jié)點.
*
* @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);
}
}
/**
* 讀取一個文件到字符串里.
*
* @param sFileName 文件名
* @param sEncode String
* @return 文件內(nèi)容
*/
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();
}
/**
* 去掉左右空格后字符串是否為空
* @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;
}
/**
* 字符串是否為空:null或者長度為0.
* @param astr 源字符串.
* @return boolean
*/
public static boolean isBlank(String astr)
{
if ((null == astr) || (astr.length() == 0))
{
return true;
}
else
{
return false;
}
}
}
|