SAX 解析Google Weather API的问题

     这几天在研究使用SAX方式来解析XML文件，在这个期间还没有遇到什么阻塞性的问题，也看到大家在使用Google Weather API来实现天气预报数据显示的功能，所以我也写了一个，总体来说没有大的问题，但是遇到一个很奇怪的问题，如果直接使用URL.openStream()方法获得的InputStream解析老是出问题，问题的提示很奇怪，如果把文件保存起来，再解析就没有什么问题，不知道什么问题，希望大家热心帮助，初步感觉是字符编码问题。

com.sun.org.apache.xerces.internal.impl.io.MalformedByteSequenceException: Invalid byte 2 of 2-byte UTF-8 sequence.
	at com.sun.org.apache.xerces.internal.impl.io.UTF8Reader.invalidByte(UTF8Reader.java:684)
	at com.sun.org.apache.xerces.internal.impl.io.UTF8Reader.read(UTF8Reader.java:369)
	at com.sun.org.apache.xerces.internal.impl.XMLEntityScanner.load(XMLEntityScanner.java:1742)
	at com.sun.org.apache.xerces.internal.impl.XMLEntityScanner.scanLiteral(XMLEntityScanner.java:1064)
	at com.sun.org.apache.xerces.internal.impl.XMLScanner.scanAttributeValue(XMLScanner.java:813)
	at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanAttribute(XMLDocumentFragmentScannerImpl.java:1539)
	at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanStartElement(XMLDocumentFragmentScannerImpl.java:1316)
	at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl$FragmentContentDriver.next(XMLDocumentFragmentScannerImpl.java:2747)
	at com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl.next(XMLDocumentScannerImpl.java:648)
	at com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanDocument(XMLDocumentFragmentScannerImpl.java:510)
	at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:807)
	at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:737)
	at com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(XMLParser.java:107)
	at com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(AbstractSAXParser.java:1205)
	at com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl$JAXPSAXParser.parse(SAXParserImpl.java:522)
	at WeatherForecast.parse(WeatherForecast.java:51)
	at WeatherForecast.parse(WeatherForecast.java:30)
	at WeatherForecast.main(WeatherForecast.java:65)
null

import java.io.IOException;
import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URL;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;

public class WeatherForecast {
    public final static String WEATHER_URL =
        "http://www.google.com/ig/api?weather=%s&hl=zh_CN";

    public static WeatherSet parse(String city) {
        city = city.replace(" ", "%20");
        String weatherURL = String.format(WEATHER_URL, city);
        InputStream in = null;
        try {
            URL url = new URL(weatherURL);
            in = url.openStream();
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return parse(in);
    }

    public static WeatherSet parse(String fileName, String city) {
        InputStream in = WeatherForecast.class.getResourceAsStream(fileName);
        return parse(in);
    }

    public static WeatherSet parse(InputStream in) {
        if(in == null){
            return null;
        }
        SAXParserFactory spf = SAXParserFactory.newInstance();

        try {
            SAXParser parser = spf.newSAXParser();

            XMLReader reader = parser.getXMLReader();
            GoogleWeatherHandler handler = new GoogleWeatherHandler();
            reader.setContentHandler(handler);

            reader.parse(new InputSource(in));
            return handler.getWeatherSet();
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    public static void main(String[] args) {
        WeatherForecast weather = new WeatherForecast();
        WeatherSet weatherSet = weather.parse("api.xml","beijing,china");
        System.out.println(weatherSet);
    }
}

public class WeatherForecastCondition extends WeatherCondition {
    private String low;

    private String high;

    private String dayOfWeek;

    public String getLow() {
        return low;
    }

    public void setLow(String low) {
        this.low = low;
    }

    public String getHigh() {
        return high;
    }

    public void setHigh(String high) {
        this.high = high;
    }


    public String getDayOfWeek() {
        return dayOfWeek;
    }

    public void setDayOfWeek(String dayOfWeek) {
        this.dayOfWeek = dayOfWeek;
    }

    @Override
    public String toString() {
        StringBuffer sb = new StringBuffer();
        sb.append("\t<day_of_week data=" + this.dayOfWeek +"/>\n");
        sb.append("\t<low data=" + this.low+"/>\n");
        sb.append("\t<high data=" + this.high+"/>\n");
        sb.append("\t<icon data=" +super.getIcon()+"/>\n");
        sb.append("\t<condition data=" +super.getCondition()+"/>\n");
        return sb.toString();
    }
}

import java.util.ArrayList;
import java.util.List;

public class WeatherSet {
    private String city;

    private String postalCode;

    private String latitude;

    private String longitude;

    private String forecastDate;

    private String currentDate;

    private String unitSystem;

    private WeatherCurrentCondition currentCondition;

    private List<WeatherForecastCondition> forecastConditions;

    public WeatherSet() {
        forecastConditions = new ArrayList<WeatherForecastCondition>();
    }

    public WeatherForecastCondition getLastForecastCondition() {
        return forecastConditions.get(forecastConditions.size() - 1);
    }

    public String getCity() {
        return city;
    }

    public void setCity(String city) {
        this.city = city;
    }

    public String getPostalCode() {
        return postalCode;
    }

    public void setPostalCode(String postalCode) {
        this.postalCode = postalCode;
    }

    public String getLatitude() {
        return latitude;
    }

    public void setLatitude(String latitude) {
        this.latitude = latitude;
    }

    public String getLongitude() {
        return longitude;
    }

    public void setLongitude(String longitude) {
        this.longitude = longitude;
    }

    public String getForecastDate() {
        return forecastDate;
    }

    public void setForecastDate(String forecastDate) {
        this.forecastDate = forecastDate;
    }

    public String getCurrentDate() {
        return currentDate;
    }

    public void setCurrentDate(String currentDate) {
        this.currentDate = currentDate;
    }

    public String getUnitSystem() {
        return unitSystem;
    }

    public void setUnitSystem(String unitSystem) {
        this.unitSystem = unitSystem;
    }

    public WeatherCurrentCondition getCurrentCondition() {
        return currentCondition;
    }

    public void setCurrentCondition(WeatherCurrentCondition currentCondition) {
        this.currentCondition = currentCondition;
    }

    public List<WeatherForecastCondition> getForeastConditions() {
        return forecastConditions;
    }

    public void setForeastConditions(
            List<WeatherForecastCondition> foreastConditions) {
        this.forecastConditions = foreastConditions;
    }

    @Override
    public String toString() {
        StringBuffer sb = new StringBuffer();
        sb.append("<city data=" +  this.city + "/>\n");

        sb.append("<postal_code data=" +this.postalCode+"/>\n");
        sb.append("<latitude_e6 data=" +this.latitude+"/>\n");
        sb.append("<longitude_e6 data="+this.longitude+"/>\n");
        sb.append("<forecast_date data="+this.forecastDate+"/>\n");
        sb.append("<current_date_time data="+this.currentDate+"/>\n");
        sb.append("<unit_system data="+this.unitSystem+"/>\n");

        sb.append("\n\n" + this.currentCondition + "\n\n");
        sb.append(this.forecastConditions);

        return sb.toString();
    }
}

public class WeatherCurrentCondition extends WeatherCondition {
    private String tempFahrenheit;

    private String tempCelcius;

    private String humidity;

    private String icon;

    private String windCondition;

    public String getTempFahrenheit() {
        return tempFahrenheit;
    }

    public void setTempFahrenheit(String tempFahrenheit) {
        this.tempFahrenheit = tempFahrenheit;
    }

    public String getTempCelcius() {
        return tempCelcius;
    }

    public void setTempCelcius(String tempCelcius) {
        this.tempCelcius = tempCelcius;
    }

    public String getHumidity() {
        return humidity;
    }

    public void setHumidity(String humidity) {
        this.humidity = humidity;
    }

    public String getIcon() {
        return icon;
    }

    public void setIcon(String icon) {
        this.icon = icon;
    }

    public String getWindCondition() {
        return windCondition;
    }

    public void setWindCondition(String windCondition) {
        this.windCondition = windCondition;
    }

    @Override
    public String toString() {
        StringBuffer sb = new StringBuffer();
        sb.append("<condition data=" + super.getCondition() + "/>\n");
        sb.append("<temp_f data=" + this.tempFahrenheit + "/>\n");
        sb.append("<temp_c data=" + this.tempFahrenheit + "/>\n");
        sb.append("<humidity data=humidity：" + this.humidity + "12%/>\n");
        sb.append("<icon data=" + super.getIcon() +"/>\n");
        sb.append("<wind_condition data=" + this.windCondition +"/>\n");
        return sb.toString();
    }
}

public class WeatherCondition {
    private String condition;


    private String icon;

    public String getCondition() {
        return condition;
    }

    public void setCondition(String condition) {
        this.condition = condition;
    }

    public String getIcon() {
        return icon;
    }

    public void setIcon(String icon) {
        this.icon = icon;
    }
}

import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

public class GoogleWeatherHandler extends DefaultHandler {
    private WeatherSet weatherSet = null;

    private boolean inForecastInformation = false;
    private boolean inCurrentConditions = false;
    private boolean inForecastConditions = false;

    public WeatherSet getWeatherSet() {
        return weatherSet;
    }

    public void startElement(String uri, String localName, String qName,
            Attributes attributes) throws SAXException {
        if(qName.equals("xml_api_reply") || qName.equals("weather")) {
            return;
        }
        if(qName.equals("forecast_information")){
            weatherSet = new WeatherSet();
            inForecastInformation = true;
            return;
        }

        if(qName.equals("current_conditions")){
            WeatherCurrentCondition todayCondition = new WeatherCurrentCondition();
            weatherSet.setCurrentCondition(todayCondition);
            inCurrentConditions = true;
            return;
        }

        if(qName.equals("forecast_conditions")){
            WeatherForecastCondition forecastCondition = new WeatherForecastCondition();
            weatherSet.getForeastConditions().add(forecastCondition);
            inForecastConditions = true;
            return;
        }

        String dataAttr = attributes.getValue("data");

        if(inForecastInformation) {
            if(qName.equals("city")){
                weatherSet.setCity(dataAttr);
            } else if(qName.equals("postal_code")){
                weatherSet.setPostalCode(dataAttr);
            } else if(qName.equals("latitude_e6")){
                weatherSet.setLatitude(dataAttr);
            } else if(qName.equals("longitude_e6")) {
                weatherSet.setLongitude(dataAttr);
            } else if(qName.equals("forecast_date")){
                weatherSet.setForecastDate(dataAttr);
            } else if(qName.equals("current_date_time")){
                weatherSet.setCurrentDate(dataAttr);
            } else if(qName.equals("unit_system")){
                weatherSet.setUnitSystem(dataAttr);
            }
            return;
        }

        if(qName.equals("condition")) {
            if(inCurrentConditions) {
                weatherSet.getCurrentCondition().setCondition(dataAttr);
            } else {
                weatherSet.getLastForecastCondition().setCondition(dataAttr);
            }
        } else if(qName.equals("temp_f")) {
            weatherSet.getCurrentCondition().setTempFahrenheit(dataAttr);
        } else if(qName.equals("temp_c")){
            weatherSet.getCurrentCondition().setTempCelcius(dataAttr);
        } else if(qName.equals("humidity")){
            weatherSet.getCurrentCondition().setHumidity(dataAttr);
        } else if(qName.equals("icon")){
            if(inCurrentConditions) {
                weatherSet.getCurrentCondition().setIcon(dataAttr);
            } else {
                weatherSet.getLastForecastCondition().setIcon(dataAttr);
            }
        } else if(qName.equals("wind_condition")){
            weatherSet.getCurrentCondition().setWindCondition(dataAttr);
        } else if(qName.equals("day_of_week")) {
            weatherSet.getLastForecastCondition().setDayOfWeek(dataAttr);
        } else if(qName.equals("low")) {
            weatherSet.getLastForecastCondition().setLow(dataAttr);
        } else if(qName.equals("high")) {
            weatherSet.getLastForecastCondition().setHigh(dataAttr);
        }
    }

    @Override
    public void endElement(String uri, String localName, String name)
            throws SAXException {
        if(name.equals("forecast_information")){
            inForecastInformation = false;
            return;
        }

        if(name.equals("current_conditions")){
            inCurrentConditions = false;
            return;
        }

        if(name.equals("forecast_conditions")){
            inForecastConditions = false;
            return;
        }
    }
}

评论

4 楼 asialee 2012-07-20  

dolphin0618 写道

我也遇到了跟你一样的情况，很奇怪

什么问题？ 可以交流下

3 楼 dolphin0618 2012-07-20  

dolphin0618 写道

你别用url.openStream()了，这样写就OK

new InputSource(new BufferedReader(new InputStreamReader(con.getInputStream(),"GBK")))

要用GBK，用UTF-8还会有乱码

2 楼 dolphin0618 2012-07-20  

你别用url.openStream()了，这样写就OK

new InputSource(new BufferedReader(new InputStreamReader(con.getInputStream(),"GBK")))

1 楼 dolphin0618 2012-07-20  

我也遇到了跟你一样的情况，很奇怪