0

这是我要从中提取数据的 RSS、XML 文件。我已经用 SAX 解析器完成了我的全部工作，一切正常。但我解析了整个 RSS 文件并获取了每个元素数据，例如 .

但我的问题是我正在获取整个文件元素数据，但我只想要其中的元素。

<rss version="2.0">
<channel>
<title>RSS Feed</title>
<link>http://www.xyz.com</link>
<description>Calendar RSS Feeds</description>
<language>en-us</language>
<ttl>60</ttl>
<item>
<title>
title 1
</title>
<description>description 1</description>
<link>
http://www.xyz.com
</link>
<guid isPermaLink="false">6027@http://www.xyz.com</guid>
</item>
<item>
<title>
title 2
</title>
<description>description 2</description>
<link>
http://www.xyz.com
</link>
<guid isPermaLink="false">5554@http://www.xyz.com</guid>
</item>
<item>
</channel>
</rss>

我已经尝试了所有的组合来设置这个我会在这里展示我的代码我做了 startElement 和 endElement 方法： -

public void startElement(String uri, String localName, String qName,
            Attributes attributes) throws SAXException {
        // TODO Auto-generated method stub

        current = true;

        if (localName.equals("channel"))
        {
            itemList = new ItemList();
        }
    }

    @Override
    public void endElement(String uri, String localName, String qName)
            throws SAXException {
        // TODO Auto-generated method stub
        current = false;

        if(localName.equals("title"))
        {
            itemList.setTitle(currentValue);
        }

    }

    @Override
    public void characters(char[] ch, int start, int length)
            throws SAXException {
        // TODO Auto-generated method stub

        if(current)
        {
            currentValue = new String(ch, start, length);
            current=false;
        }
    }

任何人请建议我如何只检索仅在元素下的元素。

我也试过这个，但这给了我错误

public void startElement(String uri, String localName, String qName,
            Attributes attributes) throws SAXException {
        // TODO Auto-generated method stub

        current = true;

        if (localName.equals("channel"))
        {
            if (localName.equals("item"))
            {
            itemList = new ItemList();
            }
        }
    }

提前致谢。

4

2 回答 2

0

试试这个，希望对你有帮助......

url = new URL("http://www.abcd.com/rss.xml");//.......
    HttpURLConnection conn = (HttpURLConnection) url.openConnection();

    if(conn.getResponseCode() == HttpURLConnection.HTTP_OK){
          DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
          DocumentBuilder db = dbf.newDocumentBuilder();
          Document doc;
          doc = db.parse(url.openStream());
          doc.getDocumentElement().normalize();
          NodeList itemLst = doc.getElementsByTagName("item");



          Array.Description = new String[itemLst.getLength()];//........
          Array.Title = new String[itemLst.getLength()];
          Array.image = new String[itemLst.getLength()];
          Array.Date = new String[itemLst.getLength()];

          for(int i=0; i < itemLst.getLength(); i++){

                Node item = itemLst.item(i);
                if(item.getNodeType() == Node.ELEMENT_NODE){
                      Element ielem = (Element)item;
                      NodeList title = ielem.getElementsByTagName("title");
                      NodeList date = ielem.getElementsByTagName("pubDate");

                      NodeList description = ielem.getElementsByTagName("description");

                    ////.........
                      Array.Title[i] = title.item(0).getChildNodes().item(0).getNodeValue();
                      Array.Description[i] = description.item(0).getChildNodes().item(0).getNodeValue();
                      Array.Date[i] = date.item(0).getChildNodes().item(0).getNodeValue();
于 2012-04-26T10:07:35.187 回答
0 
public class headlinesparser {


public static void parse(){
URL url;
try {
    url = new URL("http://www.abcd.com/taxonomy/term/19/rss.xml");//.......
    HttpURLConnection conn = (HttpURLConnection) url.openConnection();

    if(conn.getResponseCode() == HttpURLConnection.HTTP_OK){
          DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
          DocumentBuilder db = dbf.newDocumentBuilder();
          Document doc;
          doc = db.parse(url.openStream());
          doc.getDocumentElement().normalize();
          NodeList itemLst = doc.getElementsByTagName("item");



          Headlines.Description = new String[itemLst.getLength()];//........
          Headlines.Title = new String[itemLst.getLength()];
          Headlines.image = new String[itemLst.getLength()];
          Headlines.Date = new String[itemLst.getLength()];

          for(int i=0; i < itemLst.getLength(); i++){

                Node item = itemLst.item(i);
                if(item.getNodeType() == Node.ELEMENT_NODE){
                      Element ielem = (Element)item;
                      NodeList title = ielem.getElementsByTagName("title");
                      NodeList date = ielem.getElementsByTagName("pubDate");

                      NodeList description = ielem.getElementsByTagName("description");

                    ////.........
                      Headlines.Title[i] = title.item(0).getChildNodes().item(0).getNodeValue();
                      Headlines.Description[i] = description.item(0).getChildNodes().item(0).getNodeValue();
                      Headlines.Date[i] = date.item(0).getChildNodes().item(0).getNodeValue();

                    if (Headlines.Description[i].contains("<img ")){

                    String img  = Headlines.Description[i].substring(Headlines.Description[i].indexOf("<img "));
                    String cleanUp = img.substring(0, img.indexOf(">")+1);
                    img = img.substring(img.indexOf("src=") + 5);
                    int indexOf = img.indexOf("'");
                    if (indexOf==-1){
                        indexOf = img.indexOf("\"");
                    }
                    img = img.substring(0, indexOf);

                    //setImgLink(img);

                    Headlines.image[i]=img;

                      }




                }

          }

    }

} catch (MalformedURLException e) {
    // TODO Auto-generated catch block
    e.printStackTrace();
} catch (DOMException e) {
    // TODO Auto-generated catch block
    e.printStackTrace();
} catch (IOException e) {
    // TODO Auto-generated catch block
    e.printStackTrace();
} catch (ParserConfigurationException e) {
    // TODO Auto-generated catch block
    e.printStackTrace();
} catch (SAXException e) {
    // TODO Auto-generated catch block
    e.printStackTrace();
}

}


}
于 2012-04-26T10:22:32.683 回答