- user-agent的作用,防止请求时,被资源服务器当做非法访问,拒绝服务.
- refer: 防盗链功能,当爬取某个资源的时候,会被服务器提示不是从本网站请求的,从而被拦截
@Test
public void test1() {
CloseableHttpClient closeableHttpClient = HttpClients.createDefault();
String urlStr = "https://www.baidu.com/";
HttpGet httpGet = new HttpGet(urlStr);
httpGet.addHeader("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36");
httpGet.addHeader("Referrer","https://www.baidu.com/");
CloseableHttpResponse response = null;
try{
response = closeableHttpClient.execute(httpGet);
HttpEntity entity = response.getEntity();
String toStringResult = EntityUtils.toString(entity, StandardCharsets.UTF_8);
System.out.println("toStringResult: " + toStringResult);
EntityUtils.consume(entity);
}catch (Exception e){
e.printStackTrace();
}finally {
if(closeableHttpClient != null){
try{
closeableHttpClient.close();
}catch (Exception e){
e.printStackTrace();
}
}
if( response != null){
try{
response.close();
}catch (Exception e){
e.printStackTrace();
}
}
}
}