lucene-使用htmlparser提取网页特定链接

1、以EMAIL为例：(以这个网页为例http://www.qunar.com/site/zh/Cooperate_4.shtml)

package extract;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

public class extracthtmllinkemail {

/**
* @param args
*/
public static String getText(String f){
StringBuffer sb=new StringBuffer();
try {
Parser parser=new Parser(f);
parser.setEncoding("UTF-8");
NodeFilter filter=new NodeClassFilter(){
public boolean accept(Node node){
return (LinkTag.class.isAssignableFrom(node.getClass())&&((LinkTag)node).isMailLink());
}
};
NodeList links=new NodeList();
for (NodeIterator e=parser.elements();e.hasMoreNodes();){
e.nextNode().collectInto(links, filter);
}
for (int i=0;i<links.size();i++){
LinkTag linktag=(LinkTag)links.elementAt(i);
sb.append("\n|"+linktag.getLinkText()+"|=>"+linktag.getLink());
}

} catch (ParserException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return sb.toString();
}
public static void main(String[] args) {
// TODO Auto-generated method stub
String s=getText("./htmls/Qunar_com.htm");
System.out.print(s);
}
}
效果如下：

|[e-mail]|=>[e-mail]
|[e-mail]|=>[e-mail]

2、以(www.hao123.com)为例，提取js链接

代码

package extract;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

public class extracthtmllinkemail {

/**
* @param args
*/
public static String getText(String f){
StringBuffer sb=new StringBuffer();
try {
Parser parser=new Parser(f);
parser.setEncoding("GB2312");
NodeFilter filter=new NodeClassFilter(){
public boolean accept(Node node){
return (LinkTag.class.isAssignableFrom(node.getClass())&&((LinkTag)node).isJavascriptLink());
}
};
NodeList links=new NodeList();
for (NodeIterator e=parser.elements();e.hasMoreNodes();){
e.nextNode().collectInto(links, filter);
}
for (int i=0;i<links.size();i++){
LinkTag linktag=(LinkTag)links.elementAt(i);
sb.append("\n|"+linktag.getLinkText()+"|=>"+linktag.getLink());
}

} catch (ParserException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return sb.toString();
}
public static void main(String[] args) {
// TODO Auto-generated method stub
String s=getText("./htmls/hao123.htm");
System.out.print(s);
}
}
效果如下：

|我的hao123|=>void(0);
|我喜欢的网站：|=>void(0)
|我定制的网站：|=>void(0)