MSN博客搬家工具

原创

xieyan0811 2022-09-16 14:12:18 ©著作权

文章标签 工具 string blog null file 文章分类 运维

©著作权归作者所有：来自51CTO博客作者xieyan0811的原创作品，请联系作者获取转载授权，否则将追究法律责任

1. 说明
最近MSN的博客即将关闭，而使用MSN上推荐的迁移到workpress，又总是不成功。在网上下了几个工具，都是各个blog开发的，只能搬到特定的blog中去。让人十分郁闷。
后来试写了一段代码，先把从MSN博客备份到本地，挑了些技术文档搬到了，下面是程序的实现和说明，大家举一反三吧。用此方法也可以搬到其它的blog。
编译好的程序可以下载，源码可以下载，大家可以直接使用或者修改加以完善。

2. 原理
使用XML-RPC协议，一个XML-RPC消息就是一个请求体为xml的http-post请求，被调用的方法在服务器端执行并将执行结果以xml格式编码后返回，可以通过此协议，读写blog上的文章，如，WORDPRESS，新浪等都支持，利用它可以方便地开发blog的客户端。

3. 程序说明

1) MSN网页解析

public class Fetcher {
         private String getPage(String file) {      // 读取日志文件                   BufferedReader reader = null;
                   StringBuilder sb = new StringBuilder();                   String line = null;
                   try {
                            reader = new BufferedReader(new InputStreamReader(
                                               new FileInputStream((file)), Charset.forName("utf-8")));
                            while ((line = reader.readLine()) != null) {
                                     sb.append(line);
                            }
                            reader.close();
                   } catch (MalformedURLException e) {
                            System.out.println("file:" + file);
                            System.out.println("error:" + e);
                   } catch (IOException e) {
                            System.out.println("file:" + file);
                            System.out.println("error:" + e);
                   }
                   return sb.toString();
         }

// 解析日志文件：标题，日期，正文         public void getDoc(String file, String server, String user, String passwd) {
                   String html = getPage(file);
                   String titleDivRegex = "<title>.+?</title>";
                   Pattern titleDivPattern = Pattern.compile(titleDivRegex);
                   Matcher titleDivMatcher = titleDivPattern.matcher(html);
                   String title = null;
                   if (titleDivMatcher.find()) { // 标题                            title = titleDivMatcher.group().replaceAll("<title>", "")
                                               .replaceAll("</title>", "");
                   }
                   String dateDivRegex = "<h5 id=/".+?/">.+?</h5>";
                   Pattern dateDivPattern = Pattern.compile(dateDivRegex);
                   Matcher dateMatcher = dateDivPattern.matcher(html);
                   String dateStr = null;
                   Date postDate = null;
                   if (dateMatcher.find()) {      //       日期                            dateStr = dateMatcher.group().replaceAll("<h5 id=/".+?/">", "")
                                              .replaceAll("</h5>", "").trim();
                            String tmp = dateStr.replace(":", ":");
                            postDate = new Date(tmp);
                   }
                   String textDivRegex = "<div id=/".*/" class=/"blogpost/">.+?</div>";
                   Pattern textDivPattern = Pattern.compile(textDivRegex);
                   Matcher textMatcher = textDivPattern.matcher(html);
                   String text = null;
                   if (textMatcher.find()) {       // 正文                            text = textMatcher.group().replaceAll(
                                               "<div id=/".*/" class=/"blogpost/">", "").replaceAll(
                                               "</div>", "").trim();
                   }
                   String[] categories = { "android", "linux" };
                   text = "<html><meta http-equiv=/"Content-Type/" content=/"text/html; charset=utf-8/">"
                                     + text + "</html>";

                   Post post = new Post(title, text, categories, postDate);
                   post.setServer(server, user, passwd);
                   post.publish();

                   System.out.println("title:" + title);
                   System.out.println("date" + postDate);
         }}
2)        上转到其它博客
public class Post {
         private Date dateCreated;
         private String description;
         private String title;
         private String[] categories;
         private String mServer;
         private String mUser;         private String mPasswd;
         static private XmlRpcClientConfigImpl config;
         static private XmlRpcClient client;

         public Post(String title, String description, String[] categories,
                            Date dateCreated) {
                   this.dateCreated = dateCreated;
                   this.description = description;
                   this.title = title;
                   this.categories = categories;
         }

         static {
                   config = new XmlRpcClientConfigImpl();
                   client = new XmlRpcClient();
         }

         private void writelog(String log) {
                   UI.getInstance().showLog(log);
         }

         public void setServer(String server, String user, String passwd) {
                   mServer = server;
                   mUser = user;
                   mPasswd = passwd;
                   try {
                            config.setServerURL(new URL(mServer));
                            client.setConfig(config);
                   } catch (MalformedURLException e) {
                            System.out.println("connect error");
                   }
         }

         public void publish() {
                   Map<String, Object> struct = new HashMap<String, Object>();
                   struct.put("dateCreated", dateCreated);
                   struct.put("description", description);
                   struct.put("title", title);
                   struct.put("categories", categories);
                   Object[] params = new Object[] { mUser, mUser, mPasswd, struct, true };
                   String blogid = null;
                   try {           // 发布日志                            blogid = (String) client.execute("metaWeblog.newPost", params);
                            writelog("OK:  title=" + title + " id=" + blogid + "/n");
                   } catch (XmlRpcException e) {
                            writelog("ERR: title=" + title + "/n");
                   }
                   struct.clear();
         }}