java从网页中提取图片地址

import java.util.regex.Matcher;
import java.util.regex.Pattern;

//1：这个是拿到一个字符取得里面的图像地址返回一个List 

public static List<String> getImgStr(String htmlStr){      
         String img="";      
         Pattern p_image;      
         Matcher m_image;      
         List<String> pics = new ArrayList<String>();   
      
         String regEx_img = "<img.*src=(.*?)[^>]*?>"; //图片链接地址      
         p_image = Pattern.compile    
                 (regEx_img,Pattern.CASE_INSENSITIVE);      
        m_image = p_image.matcher(htmlStr);    
        while(m_image.find()){      
             img = img + "," + m_image.group();      
             Matcher m  = Pattern.compile("src=\"?(.*?)(\"|>|\\s+)").matcher(img); //匹配src   
             while(m.find()){   
                pics.add(m.group(1));   
             }   
         }      
            return pics;      
     }     

//2：下面是获得第一个地址存入到数据库

    public String saveOrUpdate() 
    { 
     try{
      if(infoId !=null){
      infoTpicnew = infoTpicnewService.getInfoTpicnew(infoId);
      }else{
       
       infoTpicnew.setInfoDatetime(new Date());
      }
      infoTpicnew.setInfoContent(infoContent);
      List list =getImgStr(infoContent);
      infoTpicnew.setInfoPicname((String) list.get(0));
         infoTpicnewService.saveOrUpdateInfoTpicnew(infoTpicnew);
            return SUCCESS;
        } catch (Exception e) {
            e.printStackTrace();
            return INPUT;
        }
    }


本文来自CSDN博客，转载请标明出处：http://blog.csdn.net/lancijk/archive/2010/03/17/5389394.aspx