<rt id="bn8ez"></rt>
<label id="bn8ez"></label>

  • <span id="bn8ez"></span>

    <label id="bn8ez"><meter id="bn8ez"></meter></label>

    posts - 120,  comments - 19,  trackbacks - 0
    import ?org.htmlparser.Node;
    import ?org.htmlparser.NodeFilter;
    import ?org.htmlparser.Parser;
    import ?org.htmlparser.filters.TagNameFilter;
    import ?org.htmlparser.tags.TableTag;
    import ?org.htmlparser.util.NodeList;

    /**
    ?*?<br>
    ?*?標題:?<br>
    ?*?功能概要:?<br>
    ?*?版權:?cityyouth.cn?(c)?2005?<br>
    ?*?公司:上海城市青年網?<br>
    ?*?創建時間:2005-12-21?<br>
    ?*?修改時間:?<br>
    ?*?修改原因:
    ?*?
    ?*?
    @author ?張偉
    ?*?
    @version ?1.0
    ?
    */
    public ? class ?TestYahoo?{
    ????
    public ? static ? void ?testHtml()?{
    ????????
    try ?{
    ????????????String?sCurrentLine;
    ????????????String?sTotalString;
    ????????????sCurrentLine?
    = ? "" ;
    ????????????sTotalString?
    = ? "" ;
    ????????????java.io.InputStream?l_urlStream;
    ????????????java.net.URL?l_url?
    = ? new ?java.net.URL(
    ????????????????????
    " http://sports.sina.com.cn/iframe/nba/live/ " );
    ????????????java.net.HttpURLConnection?l_connection?
    = ?(java.net.HttpURLConnection)?l_url
    ????????????????????.openConnection();
    ????????????l_connection.connect();
    ????????????l_urlStream?
    = ?l_connection.getInputStream();
    ????????????java.io.BufferedReader?l_reader?
    = ? new ?java.io.BufferedReader(
    ????????????????????
    new ?java.io.InputStreamReader(l_urlStream));
    ????????????
    while ?((sCurrentLine? = ?l_reader.readLine())? != ? null )?{
    ????????????????sTotalString?
    += ?sCurrentLine;
    ????????????}
    ????????????System.out.println(sTotalString);

    ????????????System.out.println(
    " ==================== " );
    ????????????String?testText?
    = ?extractText(sTotalString);
    ????????????System.out.println(testText);
    ????????}?
    catch ?(Exception?e)?{
    ????????????e.printStackTrace();
    ????????}

    ????}

    ????
    /**
    ?????*?抽取純文本信息
    ?????*?
    ?????*?
    @param ?inputHtml
    ?????*?
    @return
    ?????
    */
    ????
    public ? static ?String?extractText(String?inputHtml)? throws ?Exception?{
    ????????StringBuffer?text?
    = ? new ?StringBuffer();

    ????????Parser?parser?
    = ?Parser.createParser( new ?String(inputHtml.getBytes(),
    ????????????????
    " 8859_1 " ),? " 8859-1 " );
    ????????
    // ?遍歷所有的節點
    ????????NodeList?nodes? = ?parser.extractAllNodesThatMatch( new ?NodeFilter()?{
    ????????????
    public ? boolean ?accept(Node?node)?{
    ????????????????
    return ? true ;
    ????????????}
    ????????});
    ????????Node?node?
    = ?nodes.elementAt( 0 );
    ????????text.append(
    new ?String(node.toPlainTextString().getBytes( " 8859_1 " )));
    ????????
    return ?text.toString();
    ????}

    ????
    /**
    ?????*?讀取文件的方式來分析內容.?filePath也可以是一個Url.
    ?????*?
    ?????*?
    @param ?resource
    ?????*????????????文件/Url
    ?????
    */
    ????
    public ? static ? void ?test5(String?resource)? throws ?Exception?{
    ????????Parser?myParser?
    = ? new ?Parser(resource);

    ????????
    // ?設置編碼
    ????????myParser.setEncoding( " GBK " );
    ????????String?filterStr?
    = ? " table " ;
    ????????NodeFilter?filter?
    = ? new ?TagNameFilter(filterStr);
    ????????NodeList?nodeList?
    = ?myParser.extractAllNodesThatMatch(filter);
    ????????TableTag?tabletag?
    = ?(TableTag)?nodeList.elementAt( 11 );
    ????????????
    ????????????System.out.println(tabletag.toHtml());
    ????????????
    ????????????System.out.println(
    " ============== " );

    ????}

    ????
    /*
    ?????*?public?static?void?main(String[]?args)?{?TestYahoo?testYahoo?=?new
    ?????*?TestYahoo();?testYahoo.testHtml();?}
    ?????
    */
    ????
    public ? static ? void ?main(String[]?args)? throws ?Exception?{
    ????????test5(
    " http://sports.yahoo.com/nba/scoreboard " );
    ????}
    }


    posted on 2006-09-15 10:04 阿成 閱讀(3957) 評論(0)  編輯  收藏 所屬分類: Open source
    主站蜘蛛池模板: 亚洲av网址在线观看| 亚洲日本一区二区三区在线不卡| 亚洲AV无码专区国产乱码4SE| 免费大片av手机看片高清| 国产jizzjizz免费看jizz| 久久亚洲色WWW成人欧美| 四虎免费影院4hu永久免费| 国产亚洲精品91| 国产成人亚洲影院在线观看| 91精品成人免费国产| 久久亚洲精品视频| 日本xxxx色视频在线观看免费| 亚洲AV成人无码久久精品老人| 120秒男女动态视频免费| 亚洲videos| 国产成人免费手机在线观看视频| 美女一级毛片免费观看| 亚洲人成网亚洲欧洲无码久久| 久久精品成人免费网站| 亚洲高清无在码在线无弹窗| 在线a毛片免费视频观看| 污视频网站在线免费看| 精品亚洲永久免费精品| 91免费在线播放| 亚洲AV成人片无码网站| 国产成人A亚洲精V品无码| 日韩精品久久久久久免费| 亚洲午夜福利在线视频| 亚洲日韩国产精品乱| 777爽死你无码免费看一二区| 亚洲性色精品一区二区在线| 亚洲综合区小说区激情区| 一级成人a毛片免费播放| 亚洲youwu永久无码精品| 亚洲熟妇中文字幕五十中出| 日韩在线免费视频| 一级毛片大全免费播放| 亚洲乱亚洲乱淫久久| 国产小视频在线免费| 一级毛片免费视频| 美女裸免费观看网站|