Cómo analizar XML para <![CDATA[]]>

Question

Cómo analizar un XML que tiene datos incluidos en <![CDATA[---]... ¿cómo podemos analizar el xml y obtener los datos incluidos en CDATA ???

Answer 1

public static void main(String[] args) throws Exception { 
    File file = new File("data.xml"); 
    DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder(); 
//if you are using this code for blackberry xml parsing 
    builder.setCoalescing(true); 
    Document doc = builder.parse(file); 

    NodeList nodes = doc.getElementsByTagName("topic"); 
    for (int i = 0; i < nodes.getLength(); i++) { 
    Element element = (Element) nodes.item(i); 
    NodeList title = element.getElementsByTagName("title"); 
    Element line = (Element) title.item(0); 
    System.out.println("Title: " + getCharacterDataFromElement(line)); 
    } 
} 
public static String getCharacterDataFromElement(Element e) { 
    Node child = e.getFirstChild(); 
    if (child instanceof CharacterData) { 
    CharacterData cd = (CharacterData) child; 
    return cd.getData(); 
    } 
    return ""; 
} 

(http://www.java2s.com/Code/Java/XML/GetcharacterdataCDATAfromxmldocument.htm)

Answer 2

CDATA solo dice que los datos incluidos no se deben escapar. Entonces, solo toma el texto de la etiqueta. El analizador XML debe devolver los datos claros sin CDATA.

Answer 3

aquí r.get().getResponseBody() es el cuerpo de la respuesta

Document doc = getDomElement(r.get().getResponseBody());    
    NodeList nodes = doc.getElementsByTagName("Title"); 
    for (int i = 0; i < nodes.getLength(); i++) { 
    Element element = (Element) nodes.item(i); 
    NodeList title = element.getElementsByTagName("Child tag where cdata present"); 
    Element line = (Element) title.item(0); 
    System.out.println("Title: "+ getCharacterDataFromElement(line)); 


    public static Document getDomElement(String xml) { 
     Document doc = null; 
     DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance(); 
     dbf.setCoalescing(true); 
     dbf.setNamespaceAware(true); 
     try { 
      DocumentBuilder db = dbf.newDocumentBuilder(); 
      InputSource is = new InputSource(); 
      is.setCharacterStream(new StringReader(xml)); 
      doc = db.parse(is); 
     } catch (Exception e) { 
      e.printStackTrace(); 
     } 
     return doc; 
    } 

    public static String getCharacterDataFromElement(Element e) { 
     Node child = e.getFirstChild(); 
     if (child instanceof CharacterData) { 
      CharacterData cd = (CharacterData) child; 
      return cd.getData(); 
     } 
     return ""; 
    } 

Answer 4

Puesto que todas las respuestas anteriores están utilizando un enfoque basado en DOM. Esta es la forma de analizar CDATA con un enfoque basado en flujo usando STAX.

Utilice el siguiente patrón:

switch (EventType) { 
     case XMLStreamConstants.CHARACTERS: 
     case XMLStreamConstants.CDATA: 
      System.out.println(r.getText()); 
      break; 
     default: 
      break; 
     } 

muestra completa:

import java.io.BufferedInputStream; 
import java.io.FileInputStream; 
import java.io.InputStream; 

import javax.xml.stream.XMLInputFactory; 
import javax.xml.stream.XMLStreamConstants; 
import javax.xml.stream.XMLStreamReader; 

public void readCDATAFromXMLUsingStax() { 
    String yourSampleFile = "/path/toYour/sample/file.xml"; 
    XMLStreamReader r = null; 
    try (InputStream in = 
      new BufferedInputStream(new FileInputStream(yourSampleFile));) { 
     XMLInputFactory factory = XMLInputFactory.newInstance(); 
     r = factory.createXMLStreamReader(in); 
     while (r.hasNext()) { 
      switch (r.getEventType()) { 
      case XMLStreamConstants.CHARACTERS: 
      case XMLStreamConstants.CDATA: 
       System.out.println(r.getText()); 
       break; 
      default: 
       break; 
      } 
      r.next(); 
     } 
    } catch (Exception e) { 
     throw new RuntimeException(e); 
    } finally { 
     if (r != null) { 
      try { 
       r.close(); 
      } catch (Exception e) { 
       throw new RuntimeException(e); 
      } 
     } 
    } 
} 

Con /path/toYour/sample/file.xml

<data> 
    <![CDATA[ Sat Nov 19 18:50:15 2016 (1672822)]]> 
    <![CDATA[Sat, 19 Nov 2016 18:50:14 -0800 (PST)]]> 
</data> 

Da:

Sat Nov 19 18:50:15 2016 (1672822)        
Sat, 19 Nov 2016 18:50:14 -0800 (PST)