Web Scrapping Example in Android Java

Output:

1/  Create A New Project: ( Web Scrapping Example )

2/ Add dependency to your build.gralde file ( app module )

implementation("org.jsoup:jsoup:1.15.4")

3/ Add permission to your AndroidManifest.xml file

<uses-permission android:name="android.permission.INTERNET" />

4/  Modify your activity_main.xml

<?xml version="1.0" encoding="utf-8"?>
<LinearLayout xmlns:android="http://schemas.android.com/apk/res/android"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
    android:orientation="vertical"
    android:layout_marginTop="50dp"
    android:padding="16dp">

    <ScrollView
        android:layout_width="match_parent"
        android:layout_height="wrap_content"
        >
        <LinearLayout
            android:layout_width="match_parent"
            android:layout_height="wrap_content"
            android:orientation="vertical"
            android:gravity="center"
            >
            <Button
                android:id="@+id/btnScrape"
                android:layout_width="wrap_content"
                android:layout_height="wrap_content"
                android:text="Scrape Web Data" />

            <TextView
                android:id="@+id/tvResult"
                android:lineHeight="30dp"
                android:layout_width="wrap_content"
                android:layout_height="wrap_content"
                android:text="Web Data Will Be Displayed Here"
                android:paddingTop="20dp" />
            <ProgressBar
                android:id="@+id/progressbar"
                android:layout_marginTop="16dp"
                android:layout_width="wrap_content"
                android:layout_height="wrap_content"
                android:visibility="gone"
                />
        </LinearLayout>
    </ScrollView>

</LinearLayout>

5/  Modify your MainActivity.java

package com.example.webscrappingexample;

import android.os.Bundle;
import android.os.Handler;
import android.os.Looper;
import android.util.Log;
import android.view.View;
import android.widget.Button;
import android.widget.ProgressBar;
import android.widget.TextView;

import androidx.activity.EdgeToEdge;
import androidx.appcompat.app.AppCompatActivity;
import androidx.core.graphics.Insets;
import androidx.core.view.ViewCompat;
import androidx.core.view.WindowInsetsCompat;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;

import java.io.IOException;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;

public class MainActivity extends AppCompatActivity {

    private TextView tvResult;
    private Button btnScrape;
    private ProgressBar progressBar;


    private Handler mainHandler = new Handler(Looper.getMainLooper());
    private ExecutorService executorService = Executors.newSingleThreadExecutor();


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

        tvResult = findViewById(R.id.tvResult);
        btnScrape = findViewById(R.id.btnScrape);
        progressBar = findViewById(R.id.progressbar);


        btnScrape.setOnClickListener(new View.OnClickListener() {
            @Override
            public void onClick(View v) {
                startWebScraping();
            }
        });
    }

    private void startWebScraping() {
        progressBar.setVisibility(View.VISIBLE);
        executorService.submit(new Runnable() {
            @Override
            public void run() {
                final String resultText = scrapeWebData();

                mainHandler.post(new Runnable() {
                    @Override
                    public void run() {
                        progressBar.setVisibility(View.GONE);
                        tvResult.setText(resultText);
                    }
                });
            }
        });
    }

    private String scrapeWebData() {
        String resultText = "";
        try {
            Document doc = Jsoup.connect("https://books.toscrape.com").get();


            resultText = doc.text();


        } catch (IOException e) {
            e.printStackTrace();
            resultText = "Error fetching data!";

        }

        return resultText;
    }

    @Override
    protected void onDestroy() {
        super.onDestroy();
        executorService.shutdown();
        progressBar.setVisibility(View.GONE);

    }
}

1/  For web Scrapping I use the website: https://books.toscrape.com/

    if you want to scrap data from other websites you can replace your site URL here:

//previous url
Document doc = Jsoup.connect("https://books.toscrape.com").get();
//replaced url
Document doc = Jsoup.connect("https://your-url.com").get()