我必须从服务器解析一个 xml 文件;我尝试使用 DOm 解析器和 Sax 解析器,但我无法解析 html 标签,并且在找到第一个“<”时停止
这是我的解析器类:
public class XMLParser {
// constructor
public XMLParser() {
}
public String getXmlFromUrl(String url) {
String xml = null;
BufferedReader in = null;
try {
// defaultHttpClient
DefaultHttpClient httpClient = new DefaultHttpClient();
HttpPost httpPost = new HttpPost(url);
HttpResponse httpResponse = httpClient.execute(httpPost);
in = new BufferedReader(new InputStreamReader(
httpResponse.getEntity().getContent(), "UTF-8"));
StringBuffer sb=new StringBuffer("");
String line = "";
String NL = System.getProperty("line.separator");
while ((line = in.readLine()) != null)
{
sb.append(line );
sb.append(NL );
line=in.readLine();
}
in.close();
xml = sb.toString();;
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
} catch (ClientProtocolException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
// return XML
return xml;
}
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;
}
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));
}
}