Java基於httpclient獲取網頁資料,實現簡單網路爬蟲
1、pom檔案引入httpclient依賴
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.3</version>
</dependency>
2、直接上程式碼
public static void getInternetData(String url) {
logger.info("目標網路地址:url="+url);
//初始化httpclient
CloseableHttpClient client = HttpClients.createDefault();
//get方法請求
HttpGet getMethod = new HttpGet(url);
//post方法請求
HttpPost postMethod = new HttpPost(url);
try {
//執行響應 ,初始化response
CloseableHttpResponse response = client.execute(getMethod);
//獲取響應狀態碼
int statusCode = response.getStatusLine().getStatusCode();
logger.info("訪問響應狀態碼,statusCode="+statusCode);
//獲取實體內容
String entity = EntityUtils.toString(response.getEntity(),"utf-8");
logger.info("訪問網路響應資訊:response="+entity);
//消耗實體:關閉HttpEntity的流實體
EntityUtils.consume(response.getEntity());
response.close();
client.close();
} catch (Exception e) {
logger.info("獲取網路資料異常",e);
}
}
public static void main(String[] args) {
getInternetData("https://cn.bing.com/");
}