爬虫入门程序开门见山

建立一个maven项目，然后在pom.xml中加入依赖

<dependencies>
    <!-- HttpClient -->
    <dependency>
        <groupId>org.apache.httpcomponents</groupId>
        <artifactId>httpclient</artifactId>
        <version>4.5.3</version>
    </dependency>

    <!-- 日志 -->
    <dependency>
        <groupId>org.slf4j</groupId>
        <artifactId>slf4j-log4j12</artifactId>
        <version>1.7.25</version>
    </dependency>
</dependencies>

书写测试的代码如图

public static void main(String[] args) throws Exception {
    CloseableHttpClient httpClient = HttpClients.createDefault();

    HttpGet httpGet = new HttpGet("http://www.baidu.cn/");

    CloseableHttpResponse response = httpClient.execute(httpGet);

    if (response.getStatusLine().getStatusCode() == 200) {
        String content = EntityUtils.toString(response.getEntity(), "UTF-8");
        System.out.println(content);
    }
}