百度mp3下载地址抓取^_^

     那天朋友发我一个txt文件，里面是他喜欢的歌曲名称，让我帮忙写个程序把上面歌曲的下载地址找来。 我想到了HtmlUnit, 于是ＹＹ几分钟后写了个hello world. 如下

public static void main(String[] args)
            throws FailingHttpStatusCodeException, MalformedURLException,
            IOException {

        File writeFile = new File("/Users/jferson/Desktop/rs.txt");
        if (writeFile.isFile())
            writeFile.mkdirs();

        List<String> songInfos = FileUtils.readLines(new File(
                "/Users/jferson/Desktop/500.txt"));

        String mp3UrlPrefix = "";
        String mp3UrlSuffix = "&lm=-1&f=ms&tn=baidump3&ct=134217728&lf=&rn=";
        if (songInfos != null && songInfos.size() > 0) {
            String song = null;
            String singer = null;
            StringBuffer sb = new StringBuffer();
            for (String songInfo : songInfos) {
                String[] splits = songInfo.split("_");
                if (splits != null && splits.length == 2) {
                    song = splits[0];
                    singer = splits[1];

                    String ma3UrlPath = mp3UrlPrefix
                            + song.replaceAll(" ", "+") + mp3UrlSuffix;

                    WebClient webClient = new WebClient();

                    webClient.setThrowExceptionOnScriptError(false);

                    webClient.setThrowExceptionOnFailingStatusCode(false);

                    HtmlPage gamePage = webClient.getPage(ma3UrlPath);

                    if (gamePage == null
                            || gamePage.getElementById("songResults") == null)
                        continue;

                    DomNodeList<HtmlElement> trElements = gamePage
                            .getElementById("songResults")
                            .getElementsByTagName("tr");
                    int i = 1;
                    sb.append("歌曲：").append(song).append("rn");
                    for (HtmlElement htmlElement : trElements) {
                        DomNodeList<HtmlElement> tdElements = htmlElement
                                .getElementsByTagName("td");
                        if (tdElements == null || tdElements.size() == 0)
                            continue;
                        boolean bingo = false;
                        if (i > 2) {
                            break;
                        }
                        HtmlElement thridElement = tdElements.get(2);
                        if (thridElement.getAttribute("class")
                                .equalsIgnoreCase("third")) {

                            if (thridElement
                                    .asText()
                                    .toLowerCase()
                                    .trim()
                                    .equalsIgnoreCase(
                                            singer.toLowerCase().trim())) {

                                bingo = true;
                            } else {
                                continue;
                            }
                        }
                        HtmlElement downElement = tdElements.get(6);
                        if (downElement.getAttribute("class").equalsIgnoreCase(
                                "down")
                                && bingo) {
                            HtmlPage p = downElement.getElementsByTagName("a")
                                    .get(0).click();
                            String pageHtml = p.getWebResponse()
                                    .getContentAsString();
                            if (pageHtml.lastIndexOf("/j?j=2&url=") != -1) {
                                String downloadPath = null;
                                pageHtml = StringUtils
                                        .substring(
                                                pageHtml,
                                                pageHtml.lastIndexOf("/j?j=2&url=") + 11,
                                                pageHtml.indexOf("return startDownLoad()") - 11);
                                downloadPath = pageHtml.replaceAll("%2F", "/")
                                        .replaceAll("%3A", ":")
                                        .replaceAll("%3F", "?")
                                        .replaceAll("%3D", "=");

                                sb.append("下载地址" + i + ": ")
                                        .append(downloadPath).append("rn");
                                i++;
                            }

                        }
                    }
                    if (i == 1) {
                        sb.append("找不到匹配的下载地址！rn");
                    }
                }
            }
            FileUtils.writeStringToFile(writeFile, sb.toString());
        }

    }