1 package com.zjm.www.test;
  2 
  3 import java.io.BufferedReader;
  4 import java.io.IOException;
  5 import java.io.InputStream;
  6 import java.io.InputStreamReader;
  7 import java.net.HttpURLConnection;
  8 import java.net.URL;
  9 import java.util.regex.Matcher;
 10 import java.util.regex.Pattern;
 11 
 12 /**
 13  * 描述：趴取网页上的今天的天气
 14  * @author     zjm    
 15  * @time     2014/8/6
 16  */
 17 public class TodayTemperatureService {
 18     
 19      /** 
 20      * 发起http get请求获取网页源代码 
 21      * @param requestUrl     String    请求地址
 22      * @return                 String    该地址返回的html字符串
 23      */  
 24     private static String httpRequest(String requestUrl) {  
 25         
 26         StringBuffer buffer = null;  
 27         BufferedReader bufferedReader = null;
 28         InputStreamReader inputStreamReader = null;
 29         InputStream inputStream = null;
 30         HttpURLConnection httpUrlConn = null;
 31   
 32         try {  
 33             // 建立get请求
 34             URL url = new URL(requestUrl);  
 35             httpUrlConn = (HttpURLConnection) url.openConnection();  
 36             httpUrlConn.setDoInput(true);  
 37             httpUrlConn.setRequestMethod("GET");  
 38   
 39             // 获取输入流  
 40             inputStream = httpUrlConn.getInputStream();  
 41             inputStreamReader = new InputStreamReader(inputStream, "utf-8");  
 42             bufferedReader = new BufferedReader(inputStreamReader);  
 43   
 44             // 从输入流读取结果
 45             buffer = new StringBuffer();  
 46             String str = null;  
 47             while ((str = bufferedReader.readLine()) != null) {  
 48                 buffer.append(str);  
 49             }  
 50   
 51         } catch (Exception e) {  
 52             e.printStackTrace();  
 53         }  finally {
 54             // 释放资源
 55             if(bufferedReader != null) {
 56                 try {
 57                     bufferedReader.close();
 58                 } catch (IOException e) {
 59                     e.printStackTrace();
 60                 }
 61             }
 62             if(inputStreamReader != null){
 63                 try {
 64                     inputStreamReader.close();
 65                 } catch (IOException e) {
 66                     e.printStackTrace();
 67                 }
 68             }
 69             if(inputStream != null){
 70                 try {
 71                     inputStream.close();
 72                 } catch (IOException e) {
 73                     e.printStackTrace();
 74                 }
 75             }
 76             if(httpUrlConn != null){
 77                 httpUrlConn.disconnect();  
 78             }
 79         }
 80         return buffer.toString();  
 81     }  
 82   
 83     /** 
 84      * 过滤掉html字符串中无用的信息
 85      * @param html    String    html字符串
 86      * @return         String    有用的数据
 87      */ 
 88     private static String htmlFiter(String html) {  
 89         
 90         StringBuffer buffer = new StringBuffer();  
 91         String str1 = "";
 92         String str2 = "";
 93         buffer.append("今天:");
 94         
 95         // 取出有用的范围
 96         Pattern p = Pattern.compile("(.*)(<li class=\'dn on\' data-dn=\'7d1\'>)(.*?)(</li>)(.*)");  
 97         Matcher m = p.matcher(html);  
 98         if (m.matches()) {  
 99             str1 = m.group(3);
100             // 匹配日期，注：日期被包含在<h2> 和 </h2>中
101             p = Pattern.compile("(.*)(<h2>)(.*?)(</h2>)(.*)");
102             m = p.matcher(str1);
103             if(m.matches()){
104                 str2 = m.group(3);
105                 buffer.append(str2);
106                 buffer.append("\n天气：");
107             }
108             // 匹配天气，注：天气被包含在<p class="wea" title="..."> 和 </p>中
109             p = Pattern.compile("(.*)(<p class=\"wea\" title=)(.*?)(>)(.*?)(</p>)(.*)");
110             m = p.matcher(str1);
111             if(m.matches()){
112                 str2 = m.group(5);
113                 buffer.append(str2);
114                 buffer.append("\n温度：");
115             }
116             // 匹配温度，注：温度被包含在<p class=\"tem tem2\"> <span> 和 </span><i>中
117             p = Pattern.compile("(.*)(<p class=\"tem tem2\"> <span>)(.*?)(</span><i>)(.*)");
118             m = p.matcher(str1);
119             if(m.matches()){
120                 str2 = m.group(3);
121                 buffer.append(str2);
122                 buffer.append("°~");
123             }
124             p = Pattern.compile("(.*)(<p class=\"tem tem1\"> <span>)(.*?)(</span><i>)(.*)");
125             m = p.matcher(str1);
126             if(m.matches()){
127                 str2 = m.group(3);
128                 buffer.append(str2);
129                 buffer.append("°\n风力：");
130             }
131             // 匹配风，注：<i> 和 </i> 中
132             p = Pattern.compile("(.*)(<i>)(.*?)(</i>)(.*)");
133             m = p.matcher(str1);
134             if(m.matches()){
135                 str2 = m.group(3);
136                 buffer.append(str2);
137             }
138         }  
139         return buffer.toString();
140     }
141     
142     /** 
143      *  对以上两个方法进行封装。
144      * @return 
145      */  
146     public static String getTodayTemperatureInfo() {  
147         // 调用第一个方法，获取html字符串
148         String html = httpRequest("http://www.weather.com.cn/html/weather/101280101.shtml");  
149         // 调用第二个方法，过滤掉无用的信息
150         String result = htmlFiter(html);  
151         
152         return result;  
153     }  
154   
155     /**
156      * 测试
157      * @param args
158      */
159     public static void main(String[] args) {  
160         String info = getTodayTemperatureInfo();
161         System.out.println(info);
162     }  
163 }