网络爬虫就是用程序帮助我们访问网络上的资源，我们一直以来都是使用HTTP协议来访问互联网上的网页，网络爬虫需要编写程序，在这里使用同样的HTTP协议来访问网页。
1.pom依赖
<dependency><groupId>org.apache.httpcomponents</groupId><artifactId>httpclient</artifactId><version>4.5.2</version></dependency><dependency><groupId>org.slf4j</groupId><artifactId>slf4j-log4j12</artifactId><version>1.7.25</version></dependency>
2.log4j的配置文件
log4j.properties
log4j.rootLogger=DEBUG,.yfy = DEBUGlog4j.appender.A1=org.apache.log4j.ConsoleAppenderlog4j.appender.A1.layout=org.apache.log4j.PatternLayoutlog4j.appender.A1.layout.ConversionPattern=%-d{yyyy-MM-dd HH:mm:ss,SSS} [%t] [%c]-[%p] %m%n
3.GET请求
public class HttpGetTest {public static void main(String[] args) throws URISyntaxException {//1.创建HttpClient对象CloseableHttpClient httpClient = HttpClients.createDefault();//设置请求地址是：/search?keys=Java//创建URIBuilderURIBuilder uriBuilder = new URIBuilder("/top250");uriBuilder.setParameter("start", "25");//2.创建HttpGet对象，设置url访问地址HttpGet httpGet = new HttpGet(uriBuilder.build());//配置请求信息//有时候因为网络，获取目标服务器的原因，请求需要更长的时间才能完成，我们需要自定义相关时间RequestConfig config = RequestConfig.custom().setConnectTimeout(1000) //创建连接的最长时间，单位是毫秒.setConnectionRequestTimeout(500)//设置获取连接的最长时间.setSocketTimeout(10 * 1000) //设置数据传输的最长时间.build();System.out.println("发起请求的信息:" + httpGet);//3.使用HttpClient发起请求，获取responseCloseableHttpResponse response = null;try {response = httpClient.execute(httpGet);//4.解析响应if (response.getStatusLine().getStatusCode() == 200) {String content = EntityUtils.toString(response.getEntity(), "utf8");System.out.println(content);System.out.println(content.length());}} catch (IOException e) {e.printStackTrace();} finally {try {response.close();} catch (IOException e) {e.printStackTrace();}try {httpClient.close();} catch (IOException e) {e.printStackTrace();}}}}
4.POST请求
public class HttpParamTest {public static void main(String[] args) throws UnsupportedEncodingException {//1.创建HttpClient对象CloseableHttpClient httpClient = HttpClients.createDefault();//2.创建HttpPost对象，设置url访问地址HttpPost httpPost = new HttpPost("/search");System.out.println("发起请求的信息:" + httpPost);//声明List集合，封装表单中的餐胡List<NameValuePair> params = new ArrayList<>();params.add(new BasicNameValuePair("keys", "Java"));//创建表单的Entity对象UrlEncodedFormEntity formEntity = new UrlEncodedFormEntity(params, "utf8");httpPost.setEntity(formEntity);//3.使用HttpClient发起请求，获取responseCloseableHttpResponse response = null;try {response = httpClient.execute(httpPost);//4.解析响应if (response.getStatusLine().getStatusCode() == 200) {String content = EntityUtils.toString(response.getEntity(), "utf8");System.out.println(content.length());}} catch (IOException e) {e.printStackTrace();} finally {try {response.close();} catch (IOException e) {e.printStackTrace();}try {httpClient.close();} catch (IOException e) {e.printStackTrace();}}}}
5.连接池
如果每次请求都创建HttpClient，会有频繁创建和销毁的问题，可以使用连接池来解决这个问题
public class HttpClientPoolTest {public static void main(String[] args) {//创建连接池管理器PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager();//设置最大连接数cm.setMaxTotal(100);//设置每个主机的最大连接数cm.setDefaultMaxPerRoute(10);//使用连接池管理器发起请求doGet(cm);doGet(cm);}private static void doGet(PoolingHttpClientConnectionManager cm) {//不是每次创建新的HttpClient，而是从连接池中获取HttpClientCloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(cm).build();HttpGet httpGet = new HttpGet("/top250");CloseableHttpResponse response = null;try {response = httpClient.execute(httpGet);if (response.getStatusLine().getStatusCode() == 200) {String content = EntityUtils.toString(response.getEntity(), "utf8");System.out.println(content.length());}} catch (IOException e) {e.printStackTrace();} finally {if (response != null) {try {response.close();} catch (IOException e) {e.printStackTrace();}}//不能关闭HttpClient，由连接池管理}}}
