Java爬虫----HttpClient方式(获取数据篇)
目录
一、爬虫的定义
二、获取数据
(1)基于Get方式的请求(无参)
(2)基于Get方式请求(有参)
(3)基于Post方式的请求(无参)
(4)基于Post方式的请求(有参)
一、爬虫的定义
爬虫指的是一种自动化程序,能够模拟人类在互联网上的浏览行为,自动从互联网上抓取、预处理并保存所需要的信息。
爬虫运行的过程一般是先制定规则(如指定要抓取的网址、要抓取的信息的类型等),紧接着获取该网址的HTML源代码,根据规则对源代码进行解析和抽取,最后进行处理和保存。爬虫在实际应用中广泛使用,如搜索引擎、大数据分析、交易数据采集等领域,都需要用到爬虫技术来实现信息的定向采集和处理
关于爬虫,我们基本上可以分为两步,第一是获取数据,第二是解析数据;
二、获取数据
(1)基于Get方式的请求(无参)
public static void main(String[] args) throws IOException {CloseableHttpClient httpClient = HttpClients.createDefault();HttpGet httpGet=new HttpGet("https://www.lanqiao.cn/");//发送http中的get请求HttpEntity entity=null;CloseableHttpResponse response=null;//判断是否得到正确的数据try {response= httpClient.execute(httpGet);if(response.getStatusLine().getStatusCode()==200){//获取响应数据entity=response.getEntity();//获取的数据输出其实是个对象System.out.println(entity);//将响应数据以html源码形式展示String html = EntityUtils.toString(entity, "UTF-8");System.out.println(html);}}catch (Exception e){e.printStackTrace();}finally {try{if(response!=null)response.close();//响应成功后关闭if(httpClient!=null)httpClient.close();}catch(Exception e){e.printStackTrace();}}}
(2)基于Get方式请求(有参)
public static void main(String[] args) throws IOException {CloseableHttpClient httpClient = HttpClients.createDefault();HttpGet httpGet=new HttpGet("https://www.lanqiao.cn/");//发送http中的get请求HttpEntity entity=null;CloseableHttpResponse response=null;//判断是否得到正确的数据try {response= httpClient.execute(httpGet);if(response.getStatusLine().getStatusCode()==200){//获取响应数据entity=response.getEntity();//获取的数据输出其实是个对象System.out.println(entity);//将响应数据以html源码形式展示String html = EntityUtils.toString(entity, "UTF-8");System.out.println(html);}}catch (Exception e){e.printStackTrace();}finally {try{if(response!=null)response.close();//响应成功后关闭if(httpClient!=null)httpClient.close();}catch(Exception e){e.printStackTrace();}}}
(3)基于Post方式的请求(无参)
public class HtppClientDemo1 {public static void main(String[] args) throws IOException {CloseableHttpClient httpClient=HttpClients.createDefault();//创建post请求HttpPost httpPost=new HttpPost("https://www.lanqiao.cn/");HttpEntity entity=null;CloseableHttpResponse response=null;try{response=httpClient.execute(httpPost);if(response.getStatusLine().getStatusCode()==200){//获取响应数据entity=response.getEntity();System.out.println(entity);//网页源代码String html=EntityUtils.toString(entity,"UTF-8");System.out.println(html);}}catch(Exception e){e.printStackTrace();}finally {try{if(response!=null)response.close();if(httpClient!=null)httpClient.close();}catch (Exception e){e.printStackTrace();}}}
(4)基于Post方式的请求(有参)
public static void main(String[] args) {CloseableHttpClient httpClient = HttpClients.createDefault();//创建post请求HttpPost httpPost = new HttpPost("https://www.lanqiao.cn/");HttpEntity entity = null;CloseableHttpResponse response = null;try {//设置参数BasicNameValuePair basicNameValuePair=new BasicNameValuePair("progid","20");//装入集合List<BasicNameValuePair> list=new ArrayList<>();list.add(basicNameValuePair);//开始进行参数请求,进行网络请求UrlEncodedFormEntity urlEncodedFormEntity=new UrlEncodedFormEntity(list,"UTF-8");httpPost.setEntity(urlEncodedFormEntity);//请求参数结束response = httpClient.execute(httpPost);if (response.getStatusLine().getStatusCode() == 200) {//获取响应数据entity = response.getEntity();System.out.println(entity);//网页源代码String html = EntityUtils.toString(entity, "UTF-8");System.out.println(html);}} catch (Exception e) {e.printStackTrace();} finally {try {if (response != null) response.close();if (httpClient != null) httpClient.close();} catch (Exception e) {e.printStackTrace();}}}