当前位置：首页 > Java

java如何获取网页

2026-02-05 06:11:50Java

使用 Java 获取网页内容

使用 `HttpURLConnection` 获取网页

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

public class HttpURLConnectionExample {
    public static void main(String[] args) {
        try {
            URL url = new URL("https://example.com");
            HttpURLConnection connection = (HttpURLConnection) url.openConnection();
            connection.setRequestMethod("GET");

            int responseCode = connection.getResponseCode();
            System.out.println("Response Code: " + responseCode);

            BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
            String inputLine;
            StringBuilder content = new StringBuilder();

            while ((inputLine = in.readLine()) != null) {
                content.append(inputLine);
            }
            in.close();
            System.out.println("Content: " + content.toString());
            connection.disconnect();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

使用 `HttpClient`（Java 11+）获取网页

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class HttpClientExample {
    public static void main(String[] args) {
        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
                .uri(URI.create("https://example.com"))
                .build();

        client.sendAsync(request, HttpResponse.BodyHandlers.ofString())
                .thenApply(HttpResponse::body)
                .thenAccept(System.out::println)
                .join();
    }
}

使用第三方库 `Jsoup` 获取并解析网页

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

public class JsoupExample {
    public static void main(String[] args) {
        try {
            Document doc = Jsoup.connect("https://example.com").get();
            String title = doc.title();
            System.out.println("Title: " + title);
            System.out.println("Content: " + doc.body().text());
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

使用 `Apache HttpClient` 获取网页

import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;

public class ApacheHttpClientExample {
    public static void main(String[] args) {
        try (CloseableHttpClient client = HttpClients.createDefault()) {
            HttpGet request = new HttpGet("https://example.com");
            CloseableHttpResponse response = client.execute(request);

            String content = EntityUtils.toString(response.getEntity());
            System.out.println("Content: " + content);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}