使用 web 抓取、Jsoup 库、Java、Android Studio 从网站仅获取表的奇数行。 但是想要一个表的所有行

Question

HTML CODE of a website

<table align="center" border="0" cellpadding="1" cellspacing="1" class="tableborder" width="100%">
    <tbody>
                        
        
                
        <tr align="center" class="grideheader">
            <td width="5%" height="30">S.No.</td>
          <td width="10%">Date</td>
          <td width="70%">Title</td>
        </tr>
                <tr class="griderow1">
            <td align="center" height="30">
                1</td>
<td align="center" height="23">
                19 May 2021</td>
            <td align="left">
            <a href="https://jntuh.ac.in/uploads/calendars/RevisedAcademiccalendarBTechB.PharmII_IIIYear_II_Semester_MBA_MCA_II_Year_II_Semester_and_Pharm._D_(Regular)_II_III_IV_V_Year_and_Pharm.D(PB)IIYear.pdf" target="_blank">Revised Academic calendar -B. Tech.- B.Pharm. II & III Year - II Semester, MBA-MCA II Year II Semester and Pharm. D (Regular) II, III, IV, V Year and Pharm.D (PB) II Year<img src=https://jntuh.ac.in/images/new_icon_red.gif></a>         </td>
            
        </tr>
                <tr class="griderow2">
            <td align="center" height="30">
                2</td>
<td align="center" height="23">
                15 May 2021</td>
            <td align="left">
            <a href="https://jntuh.ac.in/uploads/bulletins/UG_PGProjects.pdf" target="_blank">Information Regarding UG/PG Projects - Regd<img src=https://jntuh.ac.in/images/new_icon_red.gif></a>          </td>
            
        </tr>
                <tr class="griderow1">
            <td align="center" height="30">
                3</td>
<td align="center" height="23">
                15 May 2021</td>
            <td align="left">
            <a href="https://jntuh.ac.in/uploads/bulletins/PharmDPhamD(PB)internships.pdf" target="_blank">Information Regarding Internship Details of  PharmD/PharmD(PB) - Reg<img src=https://jntuh.ac.in/images/new_icon_red.gif></a>            </td>
            
        </tr>
                <tr class="griderow2">
            <td align="center" height="30">
                4</td>
<td align="center" height="23">
                12 May 2021</td>
            <td align="left">
            <a href="https://jntuh.ac.in/uploads/bulletins/Circular1.pdf" target="_blank">JNTUH-Establishment-Imposing the lockdown by the Government of Telangana across the State to contain the spread of COVID-19 Virus-Regarding.<img src=https://jntuh.ac.in/images/new_icon_red.gif></a>         </td>
            
        </tr>

My Activity Code(in JAVA)

public class ActivityJNTUH_Bulletin extends AppCompatActivity {

private RecyclerView recyclerView;
private JNTUHBulletinAdapter jntuhBulletinAdapter;
private ArrayList<JNTUHBulletinModel> jntuhBulletinModels = new ArrayList<>();
private ProgressBar progressBar;

@Override
protected void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);
    setContentView(R.layout.activity_jntuh__bulletin);


    progressBar = (ProgressBar) findViewById(R.id.jntuh_bulletin_progress_bar);
    recyclerView = (RecyclerView) findViewById(R.id.jntuh_bulletin_recycler_view);

    recyclerView.setHasFixedSize(true);
    recyclerView.setLayoutManager(new LinearLayoutManager(this));
    jntuhBulletinAdapter = new JNTUHBulletinAdapter(jntuhBulletinModels, this);
    recyclerView.setAdapter(jntuhBulletinAdapter);


    Content content = new Content();
    content.execute();
}

private class Content extends AsyncTask<Void, Void, Void> {
    @Override
    protected void onCancelled() {
        super.onCancelled();
    }

    @Override
    protected void onPreExecute() {
        super.onPreExecute();

        progressBar.setVisibility(View.VISIBLE);
        progressBar.startAnimation(AnimationUtils.loadAnimation(ActivityJNTUH_Bulletin.this, android.R.anim.fade_in));

    }

    @Override
    protected void onPostExecute(Void aVoid) {
        super.onPostExecute(aVoid);
        progressBar.setVisibility(View.GONE);
        progressBar.startAnimation(AnimationUtils.loadAnimation(ActivityJNTUH_Bulletin.this, android.R.anim.fade_out));
        jntuhBulletinAdapter.notifyDataSetChanged();
    }

    @Override
    protected Void doInBackground(Void... voids) {

        try {

            String url = "https://jntuh.ac.in/bulletins";
            Document doc = Jsoup.connect(url).get();

            Element element = doc.select("table.tableborder").first();

           

            for (Element tr : element.select("tr.griderow1")) {


                  String date = tr
                            .select("td")

                            .text();

                    String bulletin = tr.select("td.griderow1")

                            .select("a")

                            .attr("href");

                    jntuhBulletinModels.add(new JNTUHBulletinModel(date, bulletin));
                    Log.d("items", "date: " + date + "bulletin: " + bulletin);



            }


            

        } catch (IOException e) {
            e.printStackTrace();

        }
        return null;
    }
}

}

I'm using web scraping for the first time and I think I'm not getting how to run the loop, in doInBackground(). And if I pass tr.griderow2 in select(), then I'm getting only even rows. So I think there is either a logical error or I need one more loop for even rows. Thank you in advance for the answer.

Answer 1

Change In For Loop

for (Element tr : element.select("tr[class^=griderow]")) {



                    String date = tr
                            .select("td")

                            .text();



                    String bulletin = tr
                            .select("td[class^=griderow]")

                            .select("a")

                            .attr("href");

                    jntuhBulletinModels.add(new JNTUHBulletinModel(date, bulletin));
                    Log.d("items", "date: " + date + "bulletin: " + bulletin);


            }