请看这个清单.实际上,那里有很多选择.例如,我选择了
HtmlCleaner库来实现.以下是一个用法示例:
项目结构:
实际源代码:
public class HtmlHelper {
TagNode rootNode;
public HtmlHelper(URL htmlPage) throws IOException
{
HtmlCleaner cleaner = new HtmlCleaner();
rootNode = cleaner.clean(htmlPage);
}
List getLinksByClass(String CSSClassname)
{
List linkList = new ArrayList();
TagNode linkElements[] = rootNode.getElementsByName("a",true);
for (int i = 0; linkElements != null && i < linkElements.length; i++)
{
String classType = linkElements[i].getAttributeByName("class");
if (classType != null && classType.equals(CSSClassname))
{
linkList.add(linkElements[i]);
}
}
return linkList;
}
}
public class StackParser extends Activity {
/** Called when the activity is first created. */
@Override
public void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.main);
Button button = (Button)findViewById(R.id.parse);
button.setOnClickListener(myListener);
}
private ProgressDialog pd;
private OnClickListener myListener = new OnClickListener() {
public void onClick(View v) {
pd = ProgressDialog.show(StackParser.this,"Working...","request to server",true,false);
new ParseSite().execute("http://www.stackoverflow.com");
}
};
private class ParseSite extends AsyncTask> {
protected List doInBackground(String... arg) {
List output = new ArrayList();
try
{
HtmlHelper hh = new HtmlHelper(new URL(arg[0]));
List links = hh.getLinksByClass("question-hyperlink");
for (Iterator iterator = links.iterator(); iterator.hasNext();)
{
TagNode divElement = (TagNode) iterator.next();
output.add(divElement.getText().toString());
}
}
catch(Exception e)
{
e.printStackTrace();
}
return output;
}
protected void onPostExecute(List output) {
pd.dismiss();
ListView listview = (ListView) findViewById(R.id.listViewData);
listview.setAdapter(new ArrayAdapter(StackParser.this,android.R.layout.simple_list_item_1,output));
}
}
}