Parse CDATA with XMLParser in this specific case for ANDROID

Question

I've seen quite a few posts about this, but actually I did not get any to work. I am building a simple TV guide android application. I simply Use RSS from a tvprofil.net to show whats on TV today. The problem is, I do not know how to Parse CDATA in XML. I am using some standard parser with DOM... at least I think so..

This is a bit of XML:

.
.
.
<item>
<title>RTS1 14.08.2012</title>
<pubDate>Tue, 14 Aug 2012 06:00:00</pubDate>
<content:encoded><![CDATA[06:00 Vesti<br>06:05 Jutarnji program<br>08:00 Dnevnik
<br>8:15 Jutarnji Program<br>09:00 Vesti ... ]]></content:encoded>
</item>
.
.
.

now, this is my main app:

public class Main extends ListActivity {

// All static variables
static final String URL = "http://tvprofil.net/rss/feed/channel-group-2.xml";
// XML node keys
static final String KEY_ITEM = "item"; // parent node
static final String KEY_NAME = "title";
static final String KEY_DATE = "pubDate";
static final String KEY_DESC = "content:encoded";

@Override
public void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);
    setContentView(R.layout.activity_main);


    ArrayList<HashMap<String,String>> menuItems = new ArrayList<HashMap<String,String>>();



    XMLParser parser = new XMLParser();
    String xml = parser.getXmlFromUrl(URL); //get XML
    Document doc = parser.getDomElement(xml); // get DOM elem.



    NodeList nl = doc.getElementsByTagName(KEY_ITEM);
    //loop
    for (int i=0; i< nl.getLength(); i++){
        HashMap<String, String> map = new HashMap<String, String>();
        Element e = (Element) nl.item(i);
        //add to map
        map.put(KEY_NAME, parser.getValue(e, KEY_NAME));
        map.put(KEY_DATE, parser.getValue(e, KEY_DATE));
        map.put(KEY_DESC, parser.getValue(e, KEY_DESC));

        // hash => list
        menuItems.add(map);
    }

    ListAdapter adapter = new SimpleAdapter(this, menuItems, R.layout.list_item,
            new String[]{KEY_NAME, KEY_DESC, KEY_DATE}, new int[]{
            R.id.name, R.id.description, R.id.date
    });
    setListAdapter(adapter);

    //singleView
    ListView lv = getListView();

    lv.setOnItemClickListener(new OnItemClickListener(){
        @Override
        public void onItemClick(AdapterView<?> parent, View view, int position, long id){
            String name = ((TextView)view.findViewById(R.id.name)).getText().toString();
            String date = ((TextView)view.findViewById(R.id.date)).getText().toString();
            String description = ((TextView)view.findViewById(R.id.description)).getText().toString();

            //intent
            Intent in = new Intent(getApplicationContext(), SingleMenuItemActivity.class);
            in.putExtra(KEY_NAME, name);
            in.putExtra(KEY_DATE, date);
            in.putExtra(KEY_DESC, description);
            startActivity(in);
        }
    });

}

}

and the parser class:

public class XMLParser {

// constructor
public XMLParser() {

}

/**
 * Getting XML from URL making HTTP request
 * @param url string
 * */
public String getXmlFromUrl(String url) {
    String xml = null;


    try {
        // defaultHttpClient
        DefaultHttpClient httpClient = new DefaultHttpClient();
        HttpPost httpPost = new HttpPost(url);

        HttpResponse httpResponse = httpClient.execute(httpPost);
        HttpEntity httpEntity = httpResponse.getEntity();
        xml = EntityUtils.toString(httpEntity);

    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (ClientProtocolException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
    // return XML
    return xml;
}

/**
 * Getting XML DOM element
 * @param XML string
 * */

public Document getDomElement(String xml){

    Document doc = null;
    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
    try {

        DocumentBuilder db = dbf.newDocumentBuilder();

        InputSource is = new InputSource();
            is.setCharacterStream(new StringReader(xml));
            doc = db.parse(is); 

        } catch (ParserConfigurationException e) {
            Log.e("Error: ", e.getMessage());
            return null;
        } catch (SAXException e) {
            Log.e("Error: ", e.getMessage());
            return null;
        } catch (IOException e) {
            Log.e("Error: ", e.getMessage());
            return null;
        }

        return doc;
}

/** Getting node value
  * @param elem element
  */
 public final String getElementValue( Node elem ) {

     Node child;
     if( elem != null){
         if (elem.hasChildNodes()){
             for( child = elem.getFirstChild(); child != null; child = child.getNextSibling() ){
                 if( child.getNodeType() == Node.TEXT_NODE  ){
                     return child.getNodeValue();
                 }
             }
         }
     }
     return "";
 }

 /**
  * Getting node value
  * @param Element node
  * @param key string
  * */
 public String getValue(Element item, String str) {     
        NodeList n = item.getElementsByTagName(str);        
        return this.getElementValue(n.item(0));
    }
}

there is one more class for Single menu item.. but I think it's irrelevant in this case. Now, I'd just like to see no HTML tags after parsing it and dealing with CDATA... Anyone got idea about this one?

Answer 1

1. First add this method

   public String getCharacterDataFromElement(Element e, String str) {
   NodeList n = e.getElementsByTagName(str);   
   Element e1=(Element) n.item(0);
   
   Node child = e1.getFirstChild();
   if (child instanceof CharacterData) {
     CharacterData cd = (CharacterData) child;
     return cd.getData();
   }
   return "";
   }
   

2. Call the above method as so-

   map.put(KEY_DESC, parser.getCharacterDataFromElement(e, KEY_DESC));
   

This should get you the CDATA in String format. HOpe this helps

Answer 2

zg_spring's answer worked perfectly for me when I needed to extract image URLs from CDATA in a set of "description" xml elements:

//Get the content of all "item" elements    
DocumentBuilder db = DocumentBuilderFactory.newInstance().newDocumentBuilder();
Document doc = db.parse(new InputSource(new StringReader(xml)));
NodeList nlDetails = doc.getElementsByTagName("item");    

//Loop through elements and extract content of "description" elements    
for(int k = 0; k < numDetails; k++) {
    Element nDetails = (Element)nlDetails.item(k);
    NodeList nlCoverURL = nDetails.getElementsByTagName("description");         
    Node nCoverURL = nlCoverURL.item(0);
    String sCoverURL = nCoverURL.getTextContent();

    //Isolate the relevant part of the String and load it into an ArrayList
    String[] descriptionContent = sCoverURL.split("\"");
    String s = descriptionContent[11]
    alImages.add(s);
} 

Answer 3

getTextContent. This attribute returns the text content of this node and its descendants

getNodeValue() The value of this node, depending on its type;

usually you shouled use getTextContent.

Answer 4

Add this

 dbf.setCoalescing(true); 

where dbf is

DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();