如何从网页上获取城市天气信息？

编写一段Java代码，从如下网站http://www.weather.com.cn/ 获得西安的天气信息：
 
 

  
  

   
   

    
    Java代码  
    
    
   
   
  
  
  
  
package com.url;  
  
import java.io.BufferedReader;  
import java.io.IOException;  
import java.io.InputStreamReader;  
import java.net.URL;  
import java.util.ArrayList;  
import java.util.List;  
import java.util.regex.Matcher;  
import java.util.regex.Pattern;  
  
public class Weather {  
  
    public static void main(String[] args) {  
  
        String weatherReturn = getWeatherInfo();  
  
        //获得层div  
        Pattern pattern = Pattern  
                .compile("<div class=\"weatherYubaoBox\">.*?</div>");  
  
        Matcher matcher = pattern.matcher(weatherReturn);  
  
        String weatherTable = "";  
  
        if (matcher.find()) {  
            weatherTable = matcher.group();  
        }  
  
        //找表  
        String weatherToday = "";  
          
        if (!weatherTable.equals("") && weatherTable.length() > 0) {  
              
            pattern = Pattern  
                    .compile("<table class=\"yuBaoTable\".*?>.*?</table>");  
            matcher = pattern.matcher(weatherTable);  
              
            if (matcher.find()) {  
                weatherToday = matcher.group();  
            }  
        }  
  
        pattern = Pattern.compile("<a.*?</a>");  
          
        matcher = pattern.matcher(weatherToday);  
          
        List<String> weatherList = new ArrayList<String>();  
        while (matcher.find()) {  
              
            weatherList.add(matcher.group());  
            System.out.println(replaceTagA(matcher.group()));  
              
        }  
    }  
  
    // 获取网页上的内容  
    public static String getWeatherInfo() {  
  
        URL url = null;  
        InputStreamReader inReader = null;  
        BufferedReader reader = null;  
          
        try {  
  
            // 建立一个url  
            url = new URL("http://www.weather.com.cn/weather/101110101.shtml");  
  
            // 打开一个流,并设置编码格式  
            inReader = new InputStreamReader(url.openStream(), "utf-8");  
            reader = new BufferedReader(inReader);  
  
            StringBuffer sb = new StringBuffer();  
  
            String inputLine;  
  
            while ((inputLine = reader.readLine()) != null) {  
                sb.append(inputLine);  
            }  
              
            return sb.toString();  
        } catch (Exception e) {  
  
            e.printStackTrace();  
              
        } finally {  
            // 关闭流  
            if (reader != null) {  
                try {  
                    reader.close();  
                } catch (IOException e) {  
                    e.printStackTrace();  
                }  
            }  
            if (inReader != null) {  
                try {  
                    inReader.close();  
                } catch (IOException e) {  
                    e.printStackTrace();  
                }  
            }  
        }  
        return null;  
    }  
  
    //从超连接中取数据  
    public static String replaceTagA(String orginal) {  
          
        List<String> resultList = new ArrayList<String>();  
          
        if (orginal != null && !"".equals(orginal)) {  
  
            Pattern pattern = Pattern.compile(">.*?<");  
            Matcher matcher = pattern.matcher(orginal);  
            while (matcher.find()) {  
                String temp = matcher.group();  
                temp = temp.replace('>', ' ');  
                temp = temp.replace('<', ' ');  
                resultList.add(temp.trim());  
            }  
        }  
        StringBuffer result = new StringBuffer();  
        for (String temp : resultList) {  
            result.append(temp);  
        }  
        return result.toString().trim();  
    }  
}  





public class WeatherJob implements Job
{
    // 代表自动获取天气预报
    private static final String AUTOMATIC = "0";
    
    private IWeatherService weatherService;
    
    public WeatherJob()
    {
        weatherService = (IWeatherService)PortalMSBeanFactory.getInstance()
                .getBean("portalWeatherService");
    }
    
    private static final DebugLogHelper logger = new DebugLogHelper(WeatherJob.class);
    private  List<Weather> WeatherLists = new ArrayList<Weather>();
    
    /**
     * 执行定时任务
     */
    @SuppressWarnings("unchecked")
    public void execute(JobExecutionContext context)
    {
        logger.enterFuncDebugLog();

        String type = XMLFactory.getValueString("weather.type");
        if (AUTOMATIC.equals(type))
        {
            logger.enterFuncDebugLog("======================Begin WeatherTaskManager.execute()======================");
            List<WeatherImage> imageList = new ArrayList<WeatherImage>();
            
            DefaultHttpClient httpclient = new DefaultHttpClient();
            String url = XMLFactory.getValueString("weather.weatherUrl");
            HttpGet httpget = new HttpGet(url);
            try
            {
                logger.atFuncDebugLog();
                HttpResponse response = httpclient.execute(httpget);
                
                HttpEntity entity = response.getEntity();
                if (entity != null)
                {
                    WeatherInfo weather = new WeatherInfo();
                    
                    InputStream in = entity.getContent();
                    
                    int count = 0;
                    while (count == 0)
                    {
                        count = Integer.parseInt("" + entity.getContentLength());
                    }
                    byte[] bytes = new byte[count];
                    
                    // 已经成功读取的字节的个数
                    int readCount = 0;
                    while (readCount <= count)
                    {
                        if (readCount == count)
                            break;
                        readCount += in.read(bytes, readCount, count
                                - readCount);
                    }
                    
                    // 转换成字符串
                    String readContent = new String(bytes, 0, readCount,
                            "UTF-8");
                    
                    Document document = DocumentHelper.parseText(readContent);
                    
                    Element root = document.getRootElement();
                    
                    // 获取根节点下的子节点active
                    Element data = root.element("data");
                    
                    // 天气信息
                    String report = data.elementText("report");
                    
                    String weatherInfo[] = report.split("；");
                    
                    weather.setWeatherDesc(weatherInfo[0]);
                    weather.setTemperature(weatherInfo[1].replace(ChineseCharacter.WEATHERJOB_TEMPERATURE,
                            ""));
                    weather.setType(0);
                    weather.setUpdater(1L);
                    
                    // 天气信息
                    String dateStr = data.elementText("date");
                    weather.setWeatherDate(dateStr);
                    
                    List<?> fieldList = root.selectNodes("/root/data/weathericons/icon");
                    
                    String suffix = Constants.SPLIT_DOT.getStringValue()
                            + XMLFactory.getValueString("weather.imageSuffix");
                    for (int i = 0; i < fieldList.size(); i++)
                    {
                        WeatherImage image = new WeatherImage();
                        Element fieldEle = (Element)fieldList.get(i);
                        image.setImage(fieldEle.getStringValue() + suffix);
                        imageList.add(image);
                    }
                    
                    weather.setWeatherImageList(imageList);
                    
                    try
                    {
                        weatherService.saveEntity(weather);
                    }
                    catch (PortalMSException e)
                    {
                        logger.excepFuncDebugLog("insert the weather is failed:", e);
                    }
                }
            }
            catch (ClientProtocolException e1)
            {
                logger.excepFuncDebugLog("query the weather is failed:", e1);
            }
            catch (IOException e1)
            {
                logger.excepFuncDebugLog("query the weather is failed:", e1);
            }
            catch (Exception e1)
            {
                logger.excepFuncDebugLog("query the weather is failed:", e1);
            }
            
            logger.exitFuncDebugLog("======================WeatherTaskManager execute() Task End!======================");
        }
        
 
        
//                   WeatherLists = XMLFactory.getValueList("weathers.weather");
                List<WeatherInfo> WeatherList = new ArrayList<WeatherInfo>();
                try {
                    WeatherList = weatherService.findWeatherConfig();
                } catch (PortalMSException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
                

                for (int j = 0; j < WeatherList.size(); j++) 
                {
                    WeatherInfo weatherinfo = new WeatherInfo();
                    weatherinfo = WeatherList.get(j);
                    

                    String weatherReturn = getWeatherInfo(weatherinfo.getWeatherUrl());

                    // 获得table
                    Pattern pattern = Pattern.compile("<table class=\"FcstBoxTable01\".*?>.*?</table>");

                    Matcher matcher = pattern.matcher(weatherReturn);

                    String weatherTable = "";

                    if (matcher.find()) 
                    {
                        weatherTable = matcher.group();
                    }

                    // 找表
                    String weatherToday = "";

                    if (!weatherTable.equals("") && weatherTable.length() > 0) 
                    {

                        pattern = Pattern.compile("<tbody>.*?</tbody>");
                        matcher = pattern.matcher(weatherTable);

                        if (matcher.find()) 
                        {
                            weatherToday = matcher.group();
                        }
                    }
                    /**                     
                     * weather_id NUMBER(13) not null, city_code VARCHAR2(50), city_name
                     * VARCHAR2(50) not null, weather_code VARCHAR2(50), weather_desc
                     * VARCHAR2(100), temperature VARCHAR2(10), weather_date
                     * VARCHAR2(20) not null, image VARCHAR2(512), update_date DATE,
                     * type VARCHAR2(10)
                     */

                    // 获取今天的数据
                    String str = weatherToday.substring(
                            weatherToday.indexOf("<tr>", 1), weatherToday.indexOf(
                                    "</tr>", 1));
                    String temperature = str.substring(str.indexOf("<td>", 1) + 4, str
                            .indexOf("</td>", 1))+"℃";
                    // 天气情况
                    pattern = Pattern.compile("alt=\".*?\"");
                    matcher = pattern.matcher(str);

                    String weather_desc = "";

                    if (matcher.find()) 
                    {
                        weather_desc = matcher.group();
                    }
                    weather_desc = weather_desc.substring(5, weather_desc.indexOf("\"",5));
                    // 天气预报图片
                    
                    if(str.indexOf("day")>0)
                    {
                        pattern = Pattern.compile("day/.*?\"");
                    }
                    else pattern = Pattern.compile("night/.*?\"");
                    
                    matcher = pattern.matcher(str);

                    String weather_pic = "";

                    if (matcher.find()) {
                        weather_pic = matcher.group();
                    }
                    if(str.indexOf("day")>0)
                    {
                        weather_pic = weather_pic.substring(4, weather_pic.indexOf("\"", 4));
                    }
                    else
                    {
                        weather_pic = weather_pic.substring(6, weather_pic.indexOf("\"", 4));
                    }

                    weatherinfo.setTemperature(temperature);
                    String day = DateUtil.fmtDate(new Date());
                    weatherinfo.setWeatherDate(day);
                    weatherinfo.setWeatherDesc(weather_desc);
                    weatherinfo.setImageUrl(weather_pic);
                    weatherinfo.setWeatherId(System.currentTimeMillis());

                     
                    
                    //新增天气情况同步给portal
                   syncWeatherInformation(Constants.SYNC_WEATHERINFO.getStringValue(), weatherinfo);
                    
                    
                    
                }
           
            
    }

    //获取网页上的内容
    public static String getWeatherInfo(String weatherUrl) 
    {
    
        URL url = null;
        InputStreamReader inReader = null;
        BufferedReader reader = null;
    
        try {
    
            // 建立一个url
            url = new URL(weatherUrl);
    //                "http://www.cwb.gov.tw/V7/forecast/taiwan/New_Taipei_City.htm");
            // URL("http://www.weather.com.cn/weather/101110101.shtml");
    
            // 打开一个流,并设置编码格式
            inReader = new InputStreamReader(url.openStream(), "utf-8");
            reader = new BufferedReader(inReader);
    
            StringBuffer sb = new StringBuffer();
    
            String inputLine;
    
            while ((inputLine = reader.readLine()) != null) 
            {
                sb.append(inputLine);
            }
    
            return sb.toString();
        } catch (Exception e) 
        {
    
            e.printStackTrace();
    
        } finally 
        {
            // 关闭流
            if (reader != null) 
            {
                try {
                    reader.close();
                } catch (IOException e) 
                {
                    e.printStackTrace();
                }
            }
            if (inReader != null) 
            {
                try {
                    inReader.close();
                } catch (IOException e) 
                {
                    e.printStackTrace();
                }
            }
        }
        return null;
    }

    // 从超连接中取数据
    public static String replaceTagA(String orginal) {
    
        List<String> resultList = new ArrayList<String>();
    
        if (orginal != null && !"".equals(orginal)) {
    
            Pattern pattern = Pattern.compile(">.*?<");
            Matcher matcher = pattern.matcher(orginal);
            while (matcher.find()) {
                String temp = matcher.group();
                temp = temp.replace('>', ' ');
                temp = temp.replace('<', ' ');
                resultList.add(temp.trim());
            }
        }
        StringBuffer result = new StringBuffer();
        for (String temp : resultList) {
            result.append(temp);
        }
        return result.toString().trim();
    }
    
    public IWeatherService getWeatherService()
    {
        return weatherService;
    }
    
    public void setWeatherService(IWeatherService weatherService)
    {
        this.weatherService = weatherService;
    }
    
    
    public void syncWeatherInformation(String opCode, WeatherInfo weather)
    {

        logger.enterFuncDebugLog();
        SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
        String updateDate = "";
        if (weather.getWeatherDate() != null)
        {
            updateDate = weather.getWeatherDate();
        }
        IMessageSync messageSync = new MessageSync();
        SyncWeatherInfoReqBody body = new SyncWeatherInfoReqBody();
        WeatherInfoReqMsg weatherInfoReqMsg = new WeatherInfoReqMsg();
        weatherInfoReqMsg.setCityCode(weather.getCityCode() == null ? "" : weather.getCityCode());
        weatherInfoReqMsg.setCityName(weather.getCityName());
        weatherInfoReqMsg.setImage(weather.getImageUrl()== null ? "" : weather.getImageUrl());
        weatherInfoReqMsg.setTemperature(weather.getTemperature() == null ? "" : weather.getTemperature());
        weatherInfoReqMsg.setUpdateDate(updateDate);
        weatherInfoReqMsg.setWeatherID(String.valueOf(weather.getWeatherId()));
        body.setWeatherInfo(weatherInfoReqMsg);
        messageSync.syncMessage(body, opCode);
        logger.exitFuncDebugLog();
    }
} 

  
  
http://www.szmb.gov.cn/data_cache/szWeather/szweather2.1.xml