Midrib Tech

 

How to extract text from PDF file programmatically android studio

Xml file

<RelativeLayout
    xmlns:android="http://schemas.android.com/apk/res/android"
    xmlns:tools="http://schemas.android.com/tools"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
    android:orientation="vertical"
    tools:context=".MainActivity">

    <ScrollView
        android:layout_width="match_parent"
        android:layout_height="match_parent">

        <!--text view for displaying our extracted text-->
        <TextView
            android:id="@+id/id_txtPDF"
            android:layout_width="match_parent"
            android:layout_height="match_parent" />

    </ScrollView>

    <LinearLayout
        android:layout_width="match_parent"
        android:layout_height="wrap_content"
        android:orientation="vertical"
        android:layout_alignParentBottom="true">

        <Button
            android:id="@+id/id_btnExtract"
            android:layout_width="wrap_content"
            android:layout_height="wrap_content"
            android:layout_centerHorizontal="true"
            android:layout_marginBottom="20dp"
            android:text="Extract Text from PDF"
            android:textAllCaps="false" />


    </LinearLayout>


</RelativeLayout>

 

Java Class

public class MainActivity extends AppCompatActivity {


    private Button btn_extractPDF;
    private TextView txt_extract;
    String str_extract_Txt = "";

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


    txt_extract = findViewById(R.id.id_txtPDF);
    btn_extractPDF = findViewById(R.id.id_btnExtract);

btn_extractPDF.setOnClickListener(new View.OnClickListener() {

        @Override
        public void onClick(View v) {
       
            extractPDFFile();

        }

    });

}

private void extractPDFFile() {

        try {

        

            PdfReader reader = new PdfReader("res/raw/mubashir_hussain_cover_letter.pdf");
            int n = reader.getNumberOfPages();
              for (int i = 0; i < n; i++) {

                str_extract_Txt = str_extract_Txt + PdfTextExtractor.getTextFromPage(reader, i + 1).trim() + "\n";


            }


            txt_extract.setText(str_extract_Txt);


            reader.close();

        } catch (Exception e) {


            txt_extract.setText("Error found is : \n" + e);

        }

    }

}