Java HtmlParse标签值 Java HtmlParse提取标签中的值操作

package cas;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.StringFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.tags.ImageTag;
import org.htmlparser.util.NodeList;

/**
 * Html 中的body体中提取出Img标签中的src值
 *
 * @author XY
 *
 */
public class CASHtmlImgConvert {

  public static void main(String[] args) {
//演示
    String[] oldSrcPath=changeImgSrc("<img alt=\"\" src=\"http://www.czb8688.com/attached/image/20160116/20160116141455_775.jpg\" />");
    if(oldSrcPath!=null){
      for(String str:oldSrcPath){
        System.out.println(str);
      }
    }
  }

  public static boolean isEmpty(String str){
    if(str!=null&&(!str.equals("")))
      return false;
    else
      return true;
  }

  /**
   * 
   * @param htmlPath 本地的html路径 或者body
   */ 
  private static String[] changeImgSrc(String htmlPath) 
  {  StringBuilder oldSrcPath = new StringBuilder();  
    try { 
      Parser parser = new Parser(htmlPath); 
    //标签名过滤器
      NodeFilter filter = new TagNameFilter ("img"); 
      NodeList nodes = parser.extractAllNodesThatMatch(filter); 
      Node eachNode = null; 
      ImageTag imageTag = null; 

      if (nodes != null) 
      { 
//       遍历所有的img节点 
        for (int i = 0; i < nodes.size(); i++)  
        { 
          eachNode = (Node)nodes.elementAt(i); 
          if (eachNode instanceof ImageTag)  
          { 
            imageTag = (ImageTag)eachNode;              
//           获得html文本的原来的src属性 
            String path=imageTag.getAttribute("src");
            if(path.startsWith(""))
              path="http://www.czb8688.com"+path;
            oldSrcPath .append(path+","); 
          } 
        } 
      } 
    } catch (Exception e) { 
      e.printStackTrace(); 
    } 
    String str=oldSrcPath.toString();
    //返回图片数组
    return str.substring(0,str.length()-1).split(",");
  } 
}

package com.zhirui.oa.modules.notice.utils;

import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class TemplateUtil {

  public static List<Map<String, Object>> getImgSrc(String htmlContent) {
    List<Map<String, Object>> srcList = new ArrayList<>(); //用来存储获取到的地址
    Map<String, Object> map = null;
    Pattern p = Pattern.compile("<(img|IMG)(.*?)(>|></img>|/>)");//匹配字符串中的img标签
    Matcher matcher = p.matcher(htmlContent);
    boolean hasPic = matcher.find();
    if (hasPic == true)//判断是否含有图片
    {
      while (hasPic) //如果含有图片，那么持续进行查找，直到匹配不到
      {
        String group = matcher.group(2);//获取第二个分组的内容，也就是 (.*?)匹配到的
        Pattern srcText = Pattern.compile("(src|SRC)=(\"|\')(.*?)(\"|\')");//匹配图片的地址
        Matcher matcher2 = srcText.matcher(group);
        if (matcher2.find()) {
          map = new HashMap<>();
          map.put("imgResourcePath", matcher2.group(3));
          srcList.add(map);//把获取到的图片地址添加到列表中
          map = null;
        }
        hasPic = matcher.find();//判断是否还有img标签
      }
    }
    return srcList;
  }

  public static List<Map<String, Object>> getVideoSrc(String htmlContent) {
    List<Map<String, Object>> srcList = new ArrayList<>(); //用来存储获取到的视频地址
    Map<String, Object> map = null;
    Pattern p = Pattern.compile("<(video|VIDEO)(.*?)(>|></video>|/>)");//匹配字符串中的video标签
    Matcher matcher = p.matcher(htmlContent);
    boolean hasPic = matcher.find();
    if (hasPic == true)//判断是否含有视频
    {
      while (hasPic) //如果含有视频，那么持续进行查找，直到匹配不到
      {
        String group = matcher.group(2);//获取第二个分组的内容，也就是 (.*?)匹配到的
        Pattern srcText = Pattern.compile("(src|SRC)=(\"|\')(.*?)(\"|\')");//匹配视频的地址
        Matcher matcher2 = srcText.matcher(group);
        if (matcher2.find()) {
          map = new HashMap<>();
          map.put("videoResourcePath", matcher2.group(3));
          srcList.add(map);//把获取到的视频地址添加到列表中
          map = null;
        }
        hasPic = matcher.find();//判断是否还有video标签
      }
    }
    return srcList;
  }

  public static List<Map<String, Object>> getAhref(String htmlContent) {
    List<Map<String, Object>> srcList = new ArrayList<>(); //用来存储获取到的超链接地址
    Map<String, Object> map = null;
    Pattern p = Pattern.compile("<(a|A)(.*?)(>|></a>|/>)");//匹配字符串中的a标签
    Matcher matcher = p.matcher(htmlContent);
    boolean hasPic = matcher.find();
    if (hasPic == true)//判断是否含有超链接
    {
      while (hasPic) //如果含有超链接，那么持续进行查找，直到匹配不到
      {
        String group = matcher.group(2);//获取第二个分组的内容，也就是 (.*?)匹配到的
        Pattern srcText = Pattern.compile("(href|HREF)=(\"|\')(.*?)(\"|\')");//匹配超链接的地址
        Matcher matcher2 = srcText.matcher(group);
        if (matcher2.find()) {
          map = new HashMap<>();
          map.put("aResourcePath", matcher2.group(3));
          srcList.add(map);//把获取到的超链接地址添加到列表中
          map = null;
        }
        hasPic = matcher.find();//判断是否还有a标签
      }
    }
    return srcList;
  }
}