Java实现 抓取网页内容

import java.io.IOException;
import okhttp3.Call;
import okhttp3.OkHttpClient;
import okhttp3.Request;

public class GetPage {

  /**
   * 根据输入的url，读取页面内容并返回
   */
  public String getContent(String url) {
    // okHttpClient 实例
    OkHttpClient okHttpClient = new OkHttpClient();
    // 定义一个request
    Request request = new Request.Builder().url(url).build();
    // 使用client去请求
    Call call = okHttpClient.newCall(request);
    // 返回结果字符串
    String result = null;
    try {
      // 获得返回结果
      result = call.execute().body().string();
    } catch (IOException e) {
      // 抓取异常
      System.out.println("request " + url + " error . ");
      e.printStackTrace();
    }
    return result;
  }

  public static void main(String[] args) {
    GetPage getPage = new GetPage();
    String url = "https://www.ustc.edu.cn/";
    String content = getPage.getContent(url);
  
    System.out.println("call " + url + " , content=" + content);
  }
}

/*  pom.xml文件内容如下：
<?xml version="1.0" encoding="UTF-8" ?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.youkeda.course</groupId>
    <artifactId>app</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <java.version>1.8</java.version>
        <resource.delimiter>@</resource.delimiter>
        <maven.compiler.source>${java.version}</maven.compiler.source>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <maven.compiler.target>${java.version}</maven.compiler.target>
    </properties>

    <dependencies>
      <dependency>
        <groupId>com.squareup.okhttp3</groupId>    
        <artifactId>okhttp</artifactId>    
        <version>4.1.0</version>    
      </dependency>  
    </dependencies>

</project>*/