Web Scraper

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * Web Scraper: fetches a page over real HTTP with java.net.http and extracts
 * every link from its HTML.
 */
public class WebScraper {

    private static final Pattern HREF = Pattern.compile("href=\"([^\"]+)\"");

    static String fetch(HttpClient client, String url) throws Exception {
        HttpRequest request = HttpRequest.newBuilder(URI.create(url)).GET().build();
        HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
        if (response.statusCode() != 200) {
            throw new RuntimeException("Unexpected status: " + response.statusCode());
        }
        return response.body();
    }

    static List<String> extractLinks(String html) {
        List<String> links = new ArrayList<>();
        Matcher m = HREF.matcher(html);
        while (m.find()) {
            links.add(m.group(1));
        }
        return links;
    }

    public static void main(String[] args) throws Exception {
        if (args.length != 1) {
            System.out.println("Usage: java WebScraper <url>");
            return;
        }
        HttpClient client = HttpClient.newHttpClient();
        String html = fetch(client, args[0]);
        List<String> links = extractLinks(html);
        System.out.println("Found " + links.size() + " links:");
        links.forEach(link -> System.out.println("  " + link));
    }
}

import com.sun.net.httpserver.HttpServer;
import org.junit.Test;
import java.net.InetSocketAddress;
import java.net.http.HttpClient;
import java.util.List;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;

public class WebScraperTest {

    @Test
    public void extractsHrefsFromHtml() {
        String html = "<a href=\"/one\">One</a><a href=\"/two\">Two</a>";
        List<String> links = WebScraper.extractLinks(html);
        assertEquals(List.of("/one", "/two"), links);
    }

    @Test
    public void noLinksMeansEmptyListNotNull() {
        assertTrue(WebScraper.extractLinks("<p>no links here</p>").isEmpty());
    }

    @Test
    public void fetchesAndExtractsLinksFromARealLocalServer() throws Exception {
        HttpServer server = HttpServer.create(new InetSocketAddress("localhost", 0), 0);
        server.createContext("/", exchange -> {
            byte[] body = "<a href=\"/about\">About</a><a href=\"/contact\">Contact</a>"
                    .getBytes();
            exchange.sendResponseHeaders(200, body.length);
            exchange.getResponseBody().write(body);
            exchange.close();
        });
        server.start();
        try {
            int port = server.getAddress().getPort();
            HttpClient client = HttpClient.newHttpClient();
            String html = WebScraper.fetch(client, "http://localhost:" + port + "/");
            List<String> links = WebScraper.extractLinks(html);
            assertEquals(List.of("/about", "/contact"), links);
        } finally {
            server.stop(0);
        }
    }

    @Test(expected = RuntimeException.class)
    public void nonOkStatusThrows() throws Exception {
        HttpServer server = HttpServer.create(new InetSocketAddress("localhost", 0), 0);
        server.createContext("/", exchange -> {
            exchange.sendResponseHeaders(404, -1);
            exchange.close();
        });
        server.start();
        try {
            int port = server.getAddress().getPort();
            HttpClient client = HttpClient.newHttpClient();
            WebScraper.fetch(client, "http://localhost:" + port + "/");
        } finally {
            server.stop(0);
        }
    }
}

$ python3 -m http.server 8099 &
$ java WebScraper http://localhost:8099/index.html
Found 3 links:
  /about
  /contact
  https://example.com

// Jenkinsfile — runs the tests automatically every time the code changes.
pipeline {
    agent any                          // run on any available machine
    environment {
        CP = 'junit-4.13.2.jar:hamcrest-core-1.3.jar'   // JUnit + its one dependency
    }

    stages {
        stage('Get the code') {
            steps { checkout scm }     // download the latest code
        }
        stage('Set up JDK') {
            steps {
                sh 'java -version'           // confirm a JDK is installed
                sh 'javac -cp "$CP" *.java'   // compile the program and its tests together
            }
        }
        stage('Run the tests') {
            steps {
                sh 'java -cp ".:$CP" org.junit.runner.JUnitCore WebScraperTest'
            }
        }
    }

    post {
        success { echo 'All tests passed.' }
        failure { echo 'A test failed — look above.' }
    }
}