正则表达式获取网页中链接和内容解决办法

        /**     * 文件中读取 目标文件     * @return     * @author wangjikuan     */    private static StringBuffer getSb(){        StringBuffer sb = new StringBuffer();        File f = new File("c:/xx.txt");        try {            BufferedReader reader = new BufferedReader( new InputStreamReader(new FileInputStream(f), "gbk"));            String s = "";            while((s = reader.readLine()) != null){                sb.append(s);            }                    } catch (FileNotFoundException e) {            // TODO Auto-generated catch block            e.printStackTrace();        } catch (IOException e) {            // TODO Auto-generated catch block            e.printStackTrace();        }        return sb;    }        /**     * 解析 字符串，得到目标     * @param sb     * @author wangjikuan     */    private static void parse(StringBuffer sb){        String regx = "<a.*?</a>";        Pattern p = Pattern.compile(regx);        Matcher m = p.matcher(sb.toString());                String regx1 = "(?<=href=\").*(?=\")";        Pattern p1 = Pattern.compile(regx1);            String regx2 = "(?<=>).*(?=<)";        Pattern p2 = Pattern.compile(regx2);                        while(m.find()){            String child = m.group();            Matcher m1 = p1.matcher(child);                        if(m1.find()){                System.out.print(m1.group());            }                        Matcher m2 = p2.matcher(child);                        if(m2.find()){                System.out.println(m2.group());            }                    }            }        public static void main(String[] args) {        parse(getSb());    }
------解决方案--------------------
Java code
    public static void main(String args[]) {        String str = "<img src=\"http://www.baidu.com/icon.png\" /><a href=\"http://guide.sina.cn/?pos=1&amp;vt=1\">导航</a><a href=\"http://sina.cn/nc.php?pos=1&amp;vt=1\">新闻</a><a href=\"http://mil.sina.cn/?pos=1&amp;vt=1\">军事</a><a href=\"http://weibo.cn/?gotoreg=1&amp;from=index&amp;s2w=index&amp;wm=ig_0001_index&amp;pos=1&amp;vt=1\">微博</a><a href=\"http://finance.sina.cn/?sa=t60d13v512&amp;pos=1&amp;vt=1\">股票</a><br/>";        String regex = "href=\"(.*?)\">(.*?)<";        Pattern p = Pattern.compile(regex);        Matcher m = p.matcher(str);        while (m.find()) {            System.out.println(m.group(1));            System.out.println(m.group(2));            System.out.println("-------------");        }    }    private static String converse(String str, int pos) {        String result = "";        for (int i = 0; i < str.length(); i++) {            int index = pos;            if (i > pos)                index = str.length() - i + pos;            else if (i < pos)                index = pos - i - 1;            result += str.charAt(index);        }        return result;    }