开发者

Parse xml using java and keep html tags

开发者 https://www.devze.com 2023-03-01 01:42 出处:网络
I\'m having an xml which i parse and get the data from between the nodes. However this data is surrounded by html tags. i create another xml and put this data in it. Now i have to get parse it again t

I'm having an xml which i parse and get the data from between the nodes. However this data is surrounded by html tags. i create another xml and put this data in it. Now i have to get parse it again to get the proper html syntax.

Kindly help.

public class XMLfunctions {

public final static Document XMLfromString(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) {
        System.out.println("XML parse error: " + e.getMessage());
        return null;
    } catch (SAXException e) {
        System.out.println("Wrong XML file structure: " + e.getMessage());
        return null;
    } catch (IOException e) {
        System.out.println("I/O exeption: " + e.getMessage());
        return null;
    }

    return doc;

}


/** Returns element value
  * @param elem element (it is XML tag)
  * @return Element value otherwise empty String
  */
 public final static String getElementValue( Node elem ) {
     Node kid;
     if( elem != null){
         if (elem.hasChildNodes()){
             for( kid = elem.getFirstChild(); kid != null; kid = kid.getNextSibling() ){
                 if( kid.getNodeType() == Node.TEXT_NODE  ){
                     return kid.getNodeValue();
                 }
             }
         }
     }
     return "";
 }

/*Start Parsing Body */
 public static String getBodyXML(String id){     
        String line = null;
        try {
            DefaultHttpClient httpClient = new DefaultHttpClient();
            HttpPost httpPost = new HttpPost("http://192.168.1.44:9090/solr/core0/select/?q=content_id:"+id+"&version=2.2&start=0&rows=10&indent=on");
            HttpResponse httpResponse = httpClient.execute(httpPost);
            HttpEntity httpEntity = httpResponse.getEntity();
            line = EntityUtils.toString(httpEntity);

        } catch (UnsupportedEncodingException e) {
            line = "<results status=\"error\"><msg>Can't connect to server</msg></results>";
        } catch (MalformedURLException e) {
            line = "<results status=\"error\"><msg>Can't connect to server</msg></results>";
        } catch (IOException e) {
            line = "<results status=\"error\"><msg>Can't connect to server</msg></results>";
        }
        String st= ParseXMLBodyNode(line,"doc");
        return st;

}

public static String ParseXMLBodyNode(String str,String node){
     String xmlRecords = str;
     String results = "";
     String[] result = new String [1];
     StringBuffer sb = new StringBuffer();
     StringBuffer text = new StringBuffer(); 
     try {
         DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
         DocumentBuilder db = dbf.newDocumentBuilder();
         InputSource is = new InputSource();
         is.setCharacterStream(new StringReader(xmlRecords));
         Document doc = db.parse(is);
         NodeList indiatimes1 = doc.getElementsByTagName(node);
         sb.append("<results count=");
         sb.append("\"1\"");
         sb.append(">\r\n");

         for (int i = 0; i < indiatimes1.getLength(); i++) {
            Node node1 = indiatimes1.item(i);
            if (node1.getNodeType() == Node.ELEMENT_NODE) {
                Element element = (Element) node1;
                NodeList nodelist = element.getElementsByTagName("str");
                Element element1 = (Element) nodelist.item(0);
                NodeList title = element1.getChildNodes();
                title.getLength();
                for(int j=0; j<title.getLength();j++){
                    text.append(title.item(j).getNodeValue());
                }
                System.out.print((title.item(0)).getNodeValue());
                sb.append("<result>");
                    sb.append("<news>");
                    String tmpText = html2text(text.toString());
                        //sb.append("<![CDATA[<body>");
                            sb.append(tmpText);
                        //sb.append("</body>]]>");
                    sb.append("</news>");
                sb.append("</result>\r\n");
                result[i] = title.item(0).getNodeValue();
            }
         }
         sb.append("</results>");
     } catch (Exception e) {
         System.out.println("Exception........"+results );
开发者_Go百科         e.printStackTrace();
     }
     return sb.toString();
 }

 public static String html2text(String html) {

    String pText = Jsoup.clean(html, Whitelist.basic());
    return pText;
}

My class which inititates the process

public class NewsDetails extends ListActivity{

/** Called when the activity is first created. */
@Override
public void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);
    setContentView(R.layout.listplaceholder);
/*}

@Override
protected void onStart() {*/

    super.onStart();
    Intent myIntent = getIntent(); 
    String id = myIntent.getStringExtra("content_id");
    String title = myIntent.getStringExtra("title");

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


    String xml = XMLfunctions.getBodyXML(id);
    Document doc = XMLfunctions.XMLfromString(xml);

    int numResults = XMLfunctions.numResults(doc);

    if((numResults <= 0)){
        Toast.makeText(NewsDetails.this, "No Result Found", Toast.LENGTH_LONG).show();  
        finish();
    }

    NodeList nodes = doc.getElementsByTagName("result");

    for (int i = 0; i < nodes.getLength(); i++) {                           
        HashMap<String, String> map = new HashMap<String, String>();    
        map.put("title", title);
        Element e = (Element)nodes.item(i);
        map.put("news", XMLfunctions.getValue(e, "news"));
        mylist.add(map);            
    }       

    ListAdapter adapter = new SimpleAdapter(this, mylist , R.layout.list_item, new String[] { "title", "news" }, new int[] { R.id.item_title, R.id.item_subtitle });

    setListAdapter(adapter);

    final ListView lv = getListView();
    lv.setTextFilterEnabled(true);
}

Sample xml which i get after converting from jsoup

<results count="1">
<result>
    <news>
        <ul><li><p>as part of its growth plan,</p></li><li><p>in a bid to achieve the target</p></li><li><p>it is pointed out that most of ccl's production came from opencast mines and only 2 mt from underground (ug) mines. ccl is now trying to increase the share underground production. the board of ccl has, thus, approved the introduction of continuous mine in chiru ug at a cost of about rs 145 crore to raise this mine's production from 2 mt to 8 mt per annum.</p></li><li><p>mr ritolia said that.</p></li></ul>
    </news>
</result>
</results>

I want to extract the content between the news tags. This xml is fed to XMLfromString(String xml) function in XMLFunctions class which then returns only "<" and rest of the body is left.

I'm not able to get the body with html tags to provide formatting.


One option is to use XML CDATA section as:

    <result>
        <news><![CDATA[ 
<ul><li><p>as part of its growth plan,</p></li><li><p>in a bid to achieve the target</p></li><li><p>it is pointed out that most of ccl's production came from opencast mines and only 2 mt from underground (ug) mines. ccl is now trying to increase the share underground production. the board of ccl has, thus, approved the introduction of continuous mine in chiru ug at a cost of about rs 145 crore to raise this mine's production from 2 mt to 8 mt per annum.</p></li><li><p>mr ritolia said that.</p></li></ul>
]]>
        </news>
    </result>
    </results>

Then your parser will not treat HTML tags as XML and allow you access to raw content of the element. The other option is to encode the HTML tags i.e. convert all < into &lt;, > into &gt;, & into &amp; etc. For more on encoding see here

0

精彩评论

暂无评论...
验证码 换一张
取 消