Android HTML Parser示例

Question

我正在研究许多用于android的HTML解析器。我尝试了很多库。谁能告诉我一个如何做的例子。我想提取每个标签的内容。请帮忙。我坚持这个。

Answer 1

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。以下是一个使用示例：

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<TagNode> getLinksByClass(String CSSClassname)
    {
        List<TagNode> linkList = new ArrayList<TagNode>();

        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<String, Void, List<String>> {

        protected List<String> doInBackground(String... arg) {
            List<String> output = new ArrayList<String>();

            try
            {
                HtmlHelper hh = new HtmlHelper(new URL(arg[0]));
                List<TagNode> links = hh.getLinksByClass("question-hyperlink");

                for (Iterator<TagNode> 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<String> output) {

            pd.dismiss();

            ListView listview = (ListView) findViewById(R.id.listViewData);
            listview.setAdapter(new ArrayAdapter<String>(StackParser.this, android.R.layout.simple_list_item_1 , output));
        }
    }
}