本文介绍的就是把雅虎心香一脉（http://soul.cn.yahoo.com/）每天的那4篇文章全文发到指定邮箱，没有广告，没有其他内容，就文章本身。用到的东西：jmail、jsoup、httpclient。我的本意其实就是想要个那4篇文章的feed，可是搜了一下雅虎没有提供，只好自己想办法解决了。这个感觉是比较笨的方法，还有个简单的方法来制作feed，这个在下篇博文中会介绍。

上面3个东西分别是用来干什么的呢？jmail就是用来发送邮件的了，jsoup是用来解析html，httpclient是用来发送请求的。想更进一步的了解请自行google。

项目结构：
          XinXiangYiMai
                    --lib
                    --src
                        --com.xx.yahoo
                        --com.xx.util

项目代码

package com.xx.yahoo;/*** Created with IntelliJ IDEA.* User: xx* Date: 13-3-27* Time: 上午11:39* DoWhat:文章*/
public class Article {private String title;private String author;private String createTime;private String content;public String getTitle() {return title;}public void setTitle(String title) {this.title = title;}public String getAuthor() {return author;}public void setAuthor(String author) {this.author = author;}public String getCreateTime() {return createTime;}public void setCreateTime(String createTime) {this.createTime = createTime;}public String getContent() {return content;}public void setContent(String content) {this.content = content;}
}

package com.xx.yahoo;import com.xx.util.MyTimeUtil;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.HttpStatus;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.util.EntityUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;/*** Created with IntelliJ IDEA.* User: xx* Date: 13-3-26* Time: 下午5:55* DoWhat:获取url的返回的网页源码*/public class ResourceHtml {/*** 根据url获得页面源码* @param url* @return*/public static String getHtmlByUrl(String url) {String html = null;HttpClient httpClient = new DefaultHttpClient();HttpGet httpGet = new HttpGet(url);try {HttpResponse httpResponse = httpClient.execute(httpGet);int state = httpResponse.getStatusLine().getStatusCode();if (state == HttpStatus.SC_OK) {HttpEntity entity = httpResponse.getEntity();html = EntityUtils.toString(entity);}} catch (IOException e) {e.printStackTrace();} finally {httpClient.getConnectionManager().shutdown();}return html;}/*** 获取页面源码中的链接** @param html* @return*/public static List<String> getArticleLinks(String html, String css) {List<String> list = getArticleLinks(html, css, null);return list;}/*** 获取页面源码中的链接* @param html* @param css1* @param css2* @return*/public static List<String> getArticleLinks(String html, String css1, String css2) {List<String> list = new ArrayList<String>();Document doc = getDocument(html);Elements elements1 = doc.select(css1);for (Element e : elements1) {String href = e.attr("href");list.add(href);}if (css2 != null && !css2.isEmpty()) {Elements elements2 = doc.select(css2);for (Element e : elements2) {String href = e.attr("href");list.add(href);}}return list;}/*** 获取一篇文章，纯文本** @param url*/public static Article doArticle(String url) {String html = getHtmlByUrl(url);Document doc = getDocument(html);Element title = doc.select("div.title > h2").first();Element author = doc.select("div.title > p").first();String createTime = MyTimeUtil.getNowStr("yyyyMMdd");Element div = doc.select("div.article_p").first();String temp = div.html();String content = temp.replaceAll("<[^>]*>","");Article article = new Article();article.setTitle(title.text());article.setAuthor(author.text());article.setCreateTime(createTime);article.setContent(content);return article;}/*** 获取一篇文章，带html标签的* @param url* @return*/public static Article doHtmlArticle(String url) {String html = getHtmlByUrl(url);Document doc = getDocument(html);Element title = doc.select("div.title > h2").first();Element author = doc.select("div.title > p").first();String createTime = MyTimeUtil.getNowStr("yyyyMMdd");Element div = doc.select("div.article_p").first();String temp = div.html();Article article = new Article();article.setTitle(title.text());article.setAuthor(author.text());article.setCreateTime(createTime);article.setContent(temp);return article;}public static void doTXT(Article article,String path) {File txt = new File(path);if(!txt.exists()) {txt.mkdir();}System.out.println(txt.getAbsolutePath());File timeFile = new File(txt.getAbsolutePath()+"/"+article.getCreateTime());if(!timeFile.exists()) {timeFile.mkdir();}File articleFile = new File(timeFile.getAbsolutePath()+"/"+article.getTitle());try {articleFile.createNewFile();BufferedWriter bw = new BufferedWriter(new FileWriter(articleFile));bw.write(article.getAuthor());bw.newLine();bw.write(article.getCreateTime());bw.newLine();bw.write(article.getContent());bw.flush();} catch (IOException e) {System.out.println("创建文件失败");e.printStackTrace();}}/*** 解析html，获得Document* @param html* @return*/private static Document getDocument(String html) {Document document = Jsoup.parse(html);return document;}}

主程序

package com.xx.yahoo;import com.xx.util.MyJMailUtil;import java.util.List;/*** Created with IntelliJ IDEA.* User: xx* Date: 13-3-26* Time: 下午6:16* DoWhat:*/
public class MyPaiRunner {public static void main(String[] args) {String url = "http://soul.cn.yahoo.com/";String css1 = "div.i_right > ul > li > a";String css2 = "div.i_right > ul > a";String html = ResourceHtml.getHtmlByUrl(url);List<String> links = ResourceHtml.getArticleLinks(html, css1, css2);for (String link : links) {System.out.println(link);Article article = ResourceHtml.doHtmlArticle(link);System.out.println(article.getTitle());MyJMailUtil.sendMail(article);}}}

util工具包

package com.xx.util;import java.text.SimpleDateFormat;
import java.util.Date;/*** Created with IntelliJ IDEA.* User: xx* Date: 13-3-27* Time: 上午11:32* DoWhat:根据一定格式获得一定格式的时间字符串*/
public class MyTimeUtil {public static String getNowStr(String pattern) {return getNowStr(pattern, null);}public static String getNowStr(String pattern, Date date) {SimpleDateFormat df = new SimpleDateFormat(pattern);if (date == null) {date = new Date();}String now = df.format(date);return now;}}

package com.xx.util;import com.xx.yahoo.Article;import javax.mail.*;
import javax.mail.internet.InternetAddress;
import javax.mail.internet.MimeMessage;
import java.util.Properties;/*** Created with IntelliJ IDEA.* User: xx* Date: 13-3-28* Time: 下午2:58* DoWhat:将获取的文章发送到制定邮箱*/public class MyJMailUtil {private static String host = "smtp.163.com";//163邮箱服务器private static String to = "xx";//接受邮件的邮箱private static String from = "xx";//发送邮件的邮箱private static String username = "xx";//发送邮件的邮箱的用户名private static String password = "xx";//发送邮件的邮箱的密码/*** 发送邮件* @param article*/public static void sendMail(Article article){//获取Properties对象Properties properties = System.getProperties();//添加smtp服务器属性properties.put("mail.smtp.host",host);properties.put("mail.smtp.auth", true);//创建邮件会话Session session = Session.getDefaultInstance(properties,new Authenticator() {@Overrideprotected PasswordAuthentication getPasswordAuthentication() {//验证账号return new PasswordAuthentication(username, password);}});//是否在控制台显示debug信息
//        session.setDebug(true);try {//定义邮件信息MimeMessage message = new MimeMessage(session);message.setFrom(new InternetAddress(from));message.addRecipient(Message.RecipientType.TO,new InternetAddress(to));message.setSubject(article.getTitle());message.setContent(article.getAuthor()+"\n"+article.getCreateTime()+"\n"+article.getContent(),"text/html;charset=utf-8");//            message.setText(article.getAuthor()+"\n"+article.getCreateTime()+"\n"+article.getContent());//发送Transport.send(message);} catch (MessagingException e) {e.printStackTrace();}}}

内容都在代码中了，有不清楚的，可以留言，我也是个练习级别的，呵呵