Parse HTML in Android

How can you parse HTML in android?

You can use XmlPullParser for parsing XML.

For e.g. refer to http://developer.android.com/reference/org/xmlpull/v1/XmlPullParser.html

How to Parse Html tags From Website in Android

using jsoup http://jsoup.org/ you can get this

download the jsoup.jar file then add it to your libs folder then go to android dependancies right click >> build path >> configure build path >> ADD JARS>> libs >> then choose the jsoup.jar file you downloaded

 try {
      String website="http://www.mcpss.com/?PN='News2'&SubP='DNewsStory'&gn=&NewsID=47318&ShowNav=&StoryGroup=Current";
      Document doc = Jsoup.connect(website).get();
      Elements el=doc.getElementsByClass("header");
      String text=el.text();
    } catch (Exception e) {
        Log.wtf("name of activity","error message to show in log", e);
    }

Android: How do I parse an HTML page?

look the code below and let me know if you have any doubts and see this link it may help you

http://wptrafficanalyzer.in/blog/android-lazy-loading-images-and-text-in-listview-from-http-json-data/

public class MainActivity extends Activity {

    ListView mListView;

    @Override
    public void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_main);

        // URL to the JSON data
        String strUrl = "ur url/countries";

        // Creating a new non-ui thread task to download json data
        DownloadTask downloadTask = new DownloadTask();

        // Starting the download process
        downloadTask.execute(strUrl);

        // Getting a reference to ListView of activity_main
        mListView = (ListView) findViewById(R.id.lv_countries);

    }

    /** A method to download json data from url */
    private String downloadUrl(String strUrl) throws IOException{
        String data = "";
        InputStream iStream = null;
        try{
            URL url = new URL(strUrl);

            // Creating an http connection to communicate with url
            HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();

            // Connecting to url
            urlConnection.connect();

            // Reading data from url
            iStream = urlConnection.getInputStream();

            BufferedReader br = new BufferedReader(new InputStreamReader(iStream));

            StringBuffer sb  = new StringBuffer();

            String line = "";
            while( ( line = br.readLine())  != null){
                sb.append(line);
            }

            data = sb.toString();

            br.close();

        }catch(Exception e){
            Log.d("Exception while downloading url", e.toString());
        }finally{
            iStream.close();
        }

        return data;
    }

    /** AsyncTask to download json data */
    private class DownloadTask extends AsyncTask<String, Integer, String>{
        String data = null;
        @Override
        protected String doInBackground(String... url) {
            try{
                data = downloadUrl(url[0]);
            }catch(Exception e){
                Log.d("Background Task",e.toString());
            }
            return data;
        }

        @Override
        protected void onPostExecute(String result) {

            // The parsing of the xml data is done in a non-ui thread
            ListViewLoaderTask listViewLoaderTask = new ListViewLoaderTask();

            // Start parsing xml data
            listViewLoaderTask.execute(result);
        }
    }

    /** AsyncTask to parse json data and load ListView */
    private class ListViewLoaderTask extends AsyncTask<String, Void, SimpleAdapter>{

        JSONObject jObject;
        // Doing the parsing of xml data in a non-ui thread
        @Override
        protected SimpleAdapter doInBackground(String... strJson) {
            try{
                jObject = new JSONObject(strJson[0]);
                CountryJSONParser countryJsonParser = new CountryJSONParser();
                countryJsonParser.parse(jObject);
            }catch(Exception e){
                Log.d("JSON Exception1",e.toString());
            }

            // Instantiating json parser class
            CountryJSONParser countryJsonParser = new CountryJSONParser();

            // A list object to store the parsed countries list
            List<HashMap<String, Object>> countries = null;

            try{
                // Getting the parsed data as a List construct
                countries = countryJsonParser.parse(jObject);
            }catch(Exception e){
                Log.d("Exception",e.toString());
            }

            // Keys used in Hashmap
            String[] from = { "country"

            // Ids of views in listview_layout
            int[] to = { R.id.tv_country};

            // Instantiating an adapter to store each items
            // R.layout.listview_layout defines the layout of each item
            SimpleAdapter adapter = new SimpleAdapter(getBaseContext(), countries, R.layout.lv_layout, from, to);

            return adapter;
        }

        /** Invoked by the Android on "doInBackground" is executed */
        @Override
        protected void onPostExecute(SimpleAdapter adapter) {

            // Setting adapter for the listview
            mListView.setAdapter(adapter);

            for(int i=0;i<adapter.getCount();i++){
                HashMap<String, Object> hm = (HashMap<String, Object>) adapter.getItem(i);
                                   HashMap<String, Object> hmDownload = new HashMap<String, Object>();
                hm.put("flag_path",imgUrl);
                hm.put("position", i);


            }
        }
    }

             @Override
        protected void onPostExecute(HashMap<String, Object> result) {
            // Getting the path to the downloaded image
            String path = (String) result.get("flag");

            // Getting the position of the downloaded image
            int position = (Integer) result.get("position");

            // Getting adapter of the listview
            SimpleAdapter adapter = (SimpleAdapter ) mListView.getAdapter();

            // Getting the hashmap object at the specified position of the listview
            HashMap<String, Object> hm = (HashMap<String, Object>) adapter.getItem(position);

            // Overwriting the existing path in the adapter
            hm.put("flag",path);

            // Noticing listview about the dataset changes
            adapter.notifyDataSetChanged();
        }
    }

    @Override
    public boolean onCreateOptionsMenu(Menu menu) {
        getMenuInflater().inflate(R.menu.activity_main, menu);
        return true;
    }
}

Android use JSoup parse HTML convert to String

It is useful to first check, if JSoup can parse the content: http://try.jsoup.org/~8W0oCmiiYnFL01nUM6HDbQ9wwTA

You are using Jsoup.parse which expects html stored in a string. If you want to use parse to retrieve the html source you have to pass a URL and a timeout:

String url = "http://servertrj.com/news/index/208";
Document doc = Jsoup.parse(new URL(url), 3000);

Most of the time you find the get() syntax to pull html source, compare your syntax to this simple example:

String url = "http://servertrj.com/news/index/208";
String userAgent = "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36";
Document doc = Jsoup.connect(url).userAgent(userAgent).get();
Elements elements = doc.select(".margin-box");
System.out.println(elements.size() + "\n" + elements.toString());

Output:

1
<div class="margin-box"> 
<p style="margin: 0px 0px 15px; padding: 0px; border: 0px; line-height: 30px; font-family: "Microsoft YaHei;, SimSun, Verdana, Arial; color: rgb(0, 0, 0); font-size: 15px;">[... truncated because of spam detection, but same as try.jsoup]</p> 
</div>

---

Related Topics