java用正则表达式分析读取网页内容(2)

/** */ /** */ /** */ /**
     * 
     * @param s
     * @return 获取雅虎知识堂文章标题及内容
     */
     public  HashMap < String, String >  getFromYahoo(String s) ... ... {
        HashMap<String, String> hm = new HashMap<String, String>();
        StringBuffer sb = new StringBuffer();
        String html="";
        System.out.println(" ------------------开始读取网页(" + s
                + ")--------------------");
        try......{
             html= getOneHtml(s);
        }catch(Exception e)......{
            e.getMessage();
        }
        // System.out.println(html);
        System.out.println("------------------读取网页(" + s
                + ")结束-------------------- ");
        System.out.println("------------------分析(" + s
                + ")结果如下-------------------- ");
        String title = outTag(getTitle(html));
        title = title.replaceAll("_雅虎知识堂", "");
        // Pattern pa=Pattern.compile("<div
        // class="original">(.*?)(( )*)(.*?)(( )*)(.*?)</div>",Pattern.DOTALL);
        Pattern pa = Pattern.compile("<div class="original">(.*?)</p></div>",
                Pattern.DOTALL);
        Matcher ma = pa.matcher(html);
        while (ma.find()) ......{
            sb.append(ma.group());
        }
        String temp = sb.toString();
        temp = temp.replaceAll("(<br>)+?", " ");// 转化换行
        temp = temp.replaceAll("<p><em>.*?</em></p>", "");// 去图片注释
        hm.put("title", title);
        hm.put("original", outTag(temp));
        return hm;

    }

     /** */ /** */ /** */ /**
     * 
     * @param args
     *            测试一组网页，针对雅虎知识堂
     */
     public   static   void  main(String args[]) ... ... {
        String url="";
        List<String> list = new ArrayList<String>();
        System.out.print("输入URL，一行一个，输入结束后输入 go 程序开始运行:    ");
        /** *//**//*
http://ks.cn.yahoo.com/question/1307121201133.html
http://ks.cn.yahoo.com/question/1307121101907.html
http://ks.cn.yahoo.com/question/1307121101907_2.html
http://ks.cn.yahoo.com/question/1307121101907_3.html
http://ks.cn.yahoo.com/question/1307121101907_4.html
http://ks.cn.yahoo.com/question/1307121101907_5.html
http://ks.cn.yahoo.com/question/1307121101907_6.html
http://ks.cn.yahoo.com/question/1307121101907_7.html
http://ks.cn.yahoo.com/question/1307121101907_8.html
         */
        BufferedReader br = new BufferedReader(new InputStreamReader(System.in));
        try ......{
            while(!(url=br.readLine()).equals("go"))......{
                list.add(url);
            }
        } catch (Exception e) ......{
            e.getMessage();
        }
        WebContent wc = new WebContent();
        HashMap<String, String> hm = new HashMap<String, String>();
        for (int i = 0; i < list.size(); i++) ......{
            hm = wc.getFromYahoo(list.get(i));
            System.out.println("标题： " + hm.get("title"));
            System.out.println("内容：  " + hm.get("original"));
        }
    /** *//**//*
        String htmlurl[] = {
                "http://ks.cn.yahoo.com/question/1307121201133.html",
                "http://ks.cn.yahoo.com/question/1307121101907.html",
                "http://ks.cn.yahoo.com/question/1307121101907_2.html",
                "http://ks.cn.yahoo.com/question/1307121101907_3.html",
                "http://ks.cn.yahoo.com/question/1307121101907_4.html",
                "http://ks.cn.yahoo.com/question/1307121101907_5.html",
                "http://ks.cn.yahoo.com/question/1307121101907_6.html",
                "http://ks.cn.yahoo.com/question/1307121101907_7.html",
                "http://ks.cn.yahoo.com/question/1307121101907_8.html" };
        WebContent wc = new WebContent();
        HashMap<String, String> hm = new HashMap<String, String>();
        for (int i = 0; i < htmlurl.length; i++) {
            hm = wc.getFromYahoo(htmlurl[i]);
            System.out.println("标题： " + hm.get("title"));
            System.out.println("内容：  " + hm.get("original"));
        }
    */
        /** *//**//*
         * String html=""; String link=""; String sscript=""; String content="";
         * System.out.println(htmlurl+" 开始读取网页内容：");
         * html=wc.getOneHtml(htmlurl); System.out.println(htmlurl+"
         * 读取完毕开始分析……"); html=html.replaceAll("(<script.*?)(( )*)(.*?)(( )*)(.*?)(</script>)","
         * ");//去除脚本 html=html.replaceAll("(<style.*?)(( )*)(.*?)(( )*)(.*?)(</style>)","
         * ");//去掉CSS html=html.replaceAll("<title>.*?</title>"," ");//除去页面标题
         * html=html.replaceAll("<a[^>]*href=("([^"]*)"|'([^']*)'|([^s>]*))[^>]*>(.*?)</a>","
         * ");//去掉链接 html=html.replaceAll("(s){2,}?"," ");//除去多余空格
         * html=wc.outTag(html);//多余标记 System.out.println(html);
         */

        /** *//**//*
         * String s[]=html.split(" +"); for(int i=0;i<s.length;i++){
         * content=(content.length()>s[i].length())?content:s[i]; }
         * System.out.println(content);
         */

        // System.out.println(htmlurl+"网页内容结束");
        /** *//**//*
         * System.out.println(htmlurl+"网页脚本开始："); List
         * script=wc.getScript(html); for(int i=0;i<script.size();i++){
         * System.out.println(script.get(i)); }
         * System.out.println(htmlurl+"网页脚本结束：");
         * 
         * System.out.println(htmlurl+"CSS开始："); List css=wc.getCSS(html);
         * for(int i=0;i<css.size();i++){ System.out.println(css.get(i)); }
         * System.out.println(htmlurl+"CSS结束：");
         * 
         * System.out.println(htmlurl+"全部链接内容开始："); List list=wc.getLink(html);
         * for(int i=0;i<list.size();i++){ link=list.get(i).toString(); }
         * System.out.println(htmlurl+"全部链接内容结束：");
         * 
         * System.out.println("内容"); System.out.println(wc.outTag(html));
         */
    }
}