htmlparser的一个入门使用实例，公做感觉。

来源：互联网发布：apache顶级开源项目编辑：程序博客网时间：2024/05/19 14:39

package org.htmlparser;

import java.net.URL;

import org.htmlparser.beans.LinkBean;
import org.htmlparser.visitors.NodeVisitor;

public class ParserTest {

public static void main(String[] args) {

// ParserTest.printAllTag();
ParserTest.printAllLink();
}

public static void printAllTag() {
try {
Parser parser = new Parser();

parser.setURL("http://www.baidu.com/");
parser.setEncoding(parser.getEncoding());

   NodeVisitor visitor = new NodeVisitor() {
    public void visitTag(Tag tag) {
     System.out.println("tag name is: " + tag.getTagName());
     System.out.println("    n class is: " + tag.getClass());
    }
   };
   parser.visitAllNodesWith(visitor);
  } catch (Exception e) {
  }
}

private static void printAllLink() {
  Parser parser = new Parser();
  LinkBean linkBean = new LinkBean();
  linkBean
    .setURL("http://www.tianya.cn/publicforum/articleslist/0/no20.shtml");
  URL[] urls = linkBean.getLinks();
  for (int i = 0; i < urls.length; i++) {
   URL url = urls[i];
   System.out.println(url);
  }
}
// http://www.cjol.com/main/jobseeker/SearchResult_new.asp?JobLocation_CODE=2008&JobFunction_CODE=220&JobPostingPeriod=30&KeyWord=java&x=28&y=6
}