用HttpClient导出人人日志

这两天想把自己在人人的日志导出来，想自己偷个懒，去网上搜个工具，结果在JavaEye找到了一篇，但是下载下来发现已经不适用现在的情况，查了半天原因，原来是人人的blog地址做了改变，现在将新的类贴出来，大家可以看看！这个比原来JavaEye上的老兄发的那篇有以下几个方面改进：rss格式；准确判断用户是否登录成功。好了，代码贴出来，大家看看吧。有不明白的Email给我：zzcwfp@gmail.com

 

奥：之所以将打印信息弄成英文，是因为ant编译后不支持UTF-8编码，根源于windows下cmd不支持UTF-8的原因，大家可以自己去网上google一下！jar文件包请参考JavaEye老兄列出的那些，我没有增加啥，呵呵！

 

package com.soffon.tools; import java.io.BufferedReader; import java.io.File; import java.io.IOException; import java.io.InputStreamReader; import java.io.StringReader; import java.util.ArrayList; import java.util.Iterator; import java.util.List; import java.util.regex.Matcher; import java.util.regex.Pattern; import org.apache.commons.io.FileUtils; import org.apache.commons.lang.StringUtils; import org.apache.http.Header; import org.apache.http.HttpResponse; import org.apache.http.NameValuePair; import org.apache.http.client.HttpClient; import org.apache.http.client.ResponseHandler; import org.apache.http.client.entity.UrlEncodedFormEntity; import org.apache.http.client.methods.HttpGet; import org.apache.http.client.methods.HttpPost; import org.apache.http.client.params.CookiePolicy; import org.apache.http.cookie.Cookie; import org.apache.http.impl.client.BasicResponseHandler; import org.apache.http.impl.client.DefaultHttpClient; import org.apache.http.message.BasicNameValuePair; import org.apache.http.protocol.HTTP; public class BlogExport { private static final String Encoding = "UTF-8"; private String uid;//登录后通过查询uid看看是否登录成功 private final Pattern uidReg = Pattern.compile("http://www//.renren//.com///profile//.do//?id//=(//d+)"); // The configuration items private static String userName; private static String password; private static String redirectURL = "http://www.renren.com/Home.do"; private static String blogURL = "http://blog.renren.com/blog/0?from=homeleft&__view=async-html"; // private static String blogURL = "http://www.renren.com/home#//blog/blog/0?from=homeleft"; private static String renRenLoginURL = "http://www.renren.com/PLogin.do"; private String index = "index.html"; private String blogIndex = "blogIndex.html"; private String blogContent = "blogContent.html"; private String xmlFile = "D:/nginx/html/airtles.xml"; // The HttpClient is used in one session private HttpResponse response; private DefaultHttpClient httpclient; private final Pattern pageReg = Pattern.compile("当前显示1-(//d*)篇/共(//d*)篇"); private final Pattern articleUrlReg = Pattern.compile("http://blog.renren.com/blog///d{2,}/(//d+)"); private final Pattern articleUrlNxtReg = Pattern .compile("http://blog.renren.com/blog///d+/(//d+)//?from=fanyeOld"); private final Pattern articleContent = Pattern.compile("<div//sid=/"blogContent/"//sclass=/"text-article/">"); private final Pattern articleTitle = Pattern .compile("<input//stype=/"hidden/"//sname=/"itemName/"//sid=/"itemName/"//svalue=/""); private final Pattern articleTimestamp = Pattern .compile("<span//sclass=/"timestamp/">([//d|//s|//-//:]+)<span//sclass=/"group/">"); private String xmlHeader = "<?xml version=/"1.0/" encoding=/"UTF-8/"?>/n"; private String xmlFooter = "/t</channel>/n</rss>"; public BlogExport(){ httpclient = new DefaultHttpClient(); xmlHeader += " <rss version=/"1.0/"> /n"; xmlHeader += " <channel> /n"; xmlHeader += "/t<title>soffon.com Latest Articles</title> /n" +"/t<link>www.soffon.com</link> /n" +"/t<description>soffon.com Latest Articles</description> /n" +"/t<language>zh-cn</language> /n" +"/t<copyright>Copyright (C) soffon.com. All rights reserved.</copyright> /n" +"/t<generator>Balder,Home</generator> /n"; } private boolean login() { HttpPost httpost = new HttpPost(renRenLoginURL); // All the parameters post to the web site List<NameValuePair> nvps = new ArrayList<NameValuePair>(); nvps.add(new BasicNameValuePair("origURL", redirectURL)); nvps.add(new BasicNameValuePair("domain", "renren.com")); nvps.add(new BasicNameValuePair("isplogin", "true")); nvps.add(new BasicNameValuePair("formName", "")); nvps.add(new BasicNameValuePair("method", "")); nvps.add(new BasicNameValuePair("submit", "登录")); nvps.add(new BasicNameValuePair("email", userName)); nvps.add(new BasicNameValuePair("password", password)); nvps.add(new BasicNameValuePair("User-Agent", "Firefox Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.3) Gecko/20090824 Firefox/3.5.3")); try { httpost.setEntity(new UrlEncodedFormEntity(nvps, HTTP.UTF_8)); response = httpclient.execute(httpost); } catch (Exception e) { e.printStackTrace(); return false; } finally { httpost.abort(); } return true; } private String getRedirectLocation() { Header locationHeader = response.getFirstHeader("Location"); if (locationHeader == null) { return null; } return locationHeader.getValue(); } //来自：http://www.docin.com/p-89049017.html private void setCookie(DefaultHttpClient httpclient,List<Cookie> cookies){ if(cookies.isEmpty()){ System.out.println("cookies is empty"); return; }else{ for(Cookie cookie:cookies){ httpclient.getCookieStore().addCookie(cookie); } } } private String getHtml(String redirectLocation) { HttpGet httpget = new HttpGet(redirectLocation); // Create a response handler ResponseHandler<String> responseHandler = new BasicResponseHandler(); String responseBody = ""; try { responseBody = httpclient.execute(httpget, responseHandler); } catch (Exception e) { e.printStackTrace(); responseBody = ""; } finally { httpget.abort(); } return responseBody; } public void closeConnect() { httpclient.getConnectionManager().shutdown(); } public void export() { if (!login()) { System.out.println("Exception：Login failed!"); return; } //读取首页信息 readHomeInfo(); 读取日志首页信息 readBlogIndexInfo(); //读取日志总数 int articleNum = parseArticleNum(); System.out.println("total " + articleNum + " blogs!"); //导出所有日志 exportAllArticle(articleNum); closeConnect(); System.out.println("finish!"); } private void exportAllArticle(int articleNum) { //获得最新一篇日志的地址 String newestArticleUrl = getNewestArticleUrl(); if (StringUtils.isNotBlank(newestArticleUrl)) { String blogUrl = newestArticleUrl; // String[] articles = new String[articleNum]; List<String> articles = new ArrayList<String>(); articles.add(xmlHeader); // int i = 1; for (int i = 1; i <= articleNum; i++) { System.out.println("export the " + i + " blog(total " + articleNum + ")"); File blogContentFile = new File(blogContent); String blogHtml = getHtml(blogUrl); try { FileUtils.writeStringToFile(blogContentFile, blogHtml, Encoding); } catch (IOException e) { e.printStackTrace(); } articles.add(toRss(blogContentFile)); Matcher matcher = articleUrlNxtReg.matcher(blogHtml); if (matcher.find()) { blogUrl = matcher.group(); } try { Thread.sleep(500); } catch (InterruptedException e) { e.printStackTrace(); } } writeArticleXmlFile(articles); } } private void writeArticleXmlFile(List<String> articles) { try { articles.add(xmlFooter); FileUtils.writeLines(new File(xmlFile), Encoding, articles); } catch (IOException e) { e.printStackTrace(); } } private String getNewestArticleUrl() { String url = ""; try { File blogIndexFile = new File(blogIndex); for (Iterator<String> lineIterator = FileUtils.lineIterator(blogIndexFile, Encoding); lineIterator .hasNext();) { String lineStr = lineIterator.next(); Matcher matcher = articleUrlReg.matcher(lineStr); if (matcher.find()) { url = matcher.group(); break; } } } catch (IOException e) { e.printStackTrace(); } return url; } private int parseArticleNum() { int articleNum = 0; try { File blogIndexFile = new File(blogIndex); for (Iterator<String> lineIterator = FileUtils.lineIterator(blogIndexFile, Encoding); lineIterator .hasNext();) { String lineStr = lineIterator.next(); Matcher matcher = pageReg.matcher(lineStr); if (matcher.find()) { String num = matcher.group(2); articleNum = Integer.parseInt(num); break; } } } catch (IOException e) { e.printStackTrace(); } return articleNum; } private void readBlogIndexInfo() { //读取日志首页 String blogIndexHtml = getHtml(blogURL); File blogIndexFile = new File(blogIndex); try { FileUtils.writeStringToFile(blogIndexFile, blogIndexHtml, Encoding); } catch (IOException e) { e.printStackTrace(); } } public void readHomeInfo() { //读取首页 String redirectLocation = getRedirectLocation(); if (redirectLocation != null) { String homeIndexHtml = getHtml(redirectLocation); Matcher matcher = uidReg.matcher(homeIndexHtml); if (matcher.find()) { uid = matcher.group(1); System.out.println(uid); } if(uid != null && !uid.trim().equals("")){//登录成功 System.out.println("Login succes!"); File homeIndexFile = new File(index); try { FileUtils.writeStringToFile(homeIndexFile, homeIndexHtml, Encoding); } catch (IOException e) { e.printStackTrace(); } } }else{ System.err.println("Login failed!"); // System.exit(-1); } } public String toRss(File file) { String title = null; String timeStamp = null; String content = null; try { for (Iterator<String> lineIterator = FileUtils.lineIterator(file, Encoding); lineIterator .hasNext();) { String lineStr = lineIterator.next(); Matcher contentMatcher = articleContent.matcher(lineStr); if (contentMatcher.find()) { lineIterator.next(); content = lineIterator.next(); continue; } Matcher titleMatcher = articleTitle.matcher(lineStr); if (titleMatcher.find()) { title = StringUtils.substring(lineStr, 58, lineStr.length() - 4); continue; } Matcher timeStampMatcher = articleTimestamp.matcher(lineStr); if (timeStampMatcher.find()) { timeStamp = timeStampMatcher.group(1); continue; } } } catch (IOException e) { e.printStackTrace(); } return toRss(title, timeStamp, content); } private String toRss(String title, String timeStamp, String content) { StringBuffer xmlStr = new StringBuffer(10000).append("/t<item>/n"); xmlStr.append("/t/t<title>").append(title).append("</title>/n"); xmlStr.append("/t/t<pubdate>").append(timeStamp).append("</pubdate>/n"); xmlStr.append("/t/t<description><!--[CDATA[").append(content).append("]]--></description>/n"); xmlStr.append("/t</item>/n"); return xmlStr.toString(); } public static void main(String[] args) throws Exception { userName = "你的用户名"; password = "你的密码"; BlogExport export = new BlogExport(); export.export(); } }

 

 

【推广】正正博客：http://www.2009fly.com/