从网页中提取图片地址(java 正则表达式)

   /**
    * 得到网页中图片的地址
     */
   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;   
    }  
     //重点在于正则表达式 <img.*src=(.*?)[^>]*?>   
     //               src=\"?(.*?)(\"|>|\\s+)                     

评论

1 楼 zhuchao_ko 2012-06-27