java爬虫之HtmlUnit介绍
前端有时候会遇到项目临时需要网上收集数据的情况，什么方案是简单易懂、长期可用的呢，当然是用浏览器终端测试单元做爬虫是最方便的啦，将平时工作中的测试程序进行简单的修改，然后配合爬虫代理，就可以马上开始数据采集，是不是很方便呀。刚好之前也分享了一篇关于java爬虫的文章，那今天也是爬虫方面的知识，我们可以继续分享下java爬虫。不知道做学java的对HtmlUnit熟悉不呢？它是是java下的一款无头浏览器方案，通过相应的API模拟HTML协议，可以请求页面，提交表单，打开链接等等操作，完全模拟用户终端。支持复杂的JavaScript、AJAX库，可以模拟多种浏览器，包括Chrome，Firefox或IE等。下面提供一个简单的demo，通过调用爬虫代理访问IP查询网站，如果将目标网站修改为需要采集的数据链接，即可获取相应的数据，再加上数据分析模块就可以基本使用，示例是根据实际项目需求写的，看下要复杂些：import java.io.BufferedReader;import java.io.InputStreamReader;
import java.io.IOException;
import java.net.URI;
import java.util.Arrays;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import org.apache.http.Header;
import org.apache.http.HeaderElement;
import org.apache.http.HttpHost;
import org.apache.http.auth.AuthScope;
import org.apache.http.auth.UsernamePasswordCredentials;
import org.apache.http.client.AuthCache;
import org.apache.http.client.CredentialsProvider;
import org.apache.http.client.HttpRequestRetryHandler;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.config.AuthSchemes;
import org.apache.http.client.entity.GzipDecompressingEntity;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.methods.HttpRequestBase;
import org.apache.http.client.protocol.HttpClientContext;
import org.apache.http.config.Registry;
import org.apache.http.config.RegistryBuilder;
import org.apache.http.conn.socket.ConnectionSocketFactory;
import org.apache.http.conn.socket.LayeredConnectionSocketFactory;
import org.apache.http.conn.socket.PlainConnectionSocketFactory;
import org.apache.http.conn.ssl.SSLConnectionSocketFactory;
import org.apache.http.impl.auth.BasicScheme;
import org.apache.http.impl.client.BasicAuthCache;
import org.apache.http.impl.client.BasicCredentialsProvider;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.impl.client.ProxyAuthenticationStrategy;
import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;
import org.apache.http.message.BasicHeader;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.NameValuePair;
import org.apache.http.util.EntityUtils;
public class Demo
{
// 代理服务器(产品官网 www.16yun.cn)
final static String proxyHost = "t.16yun.cn";
final static Integer proxyPort = 31000;
// 代理验证信息
final static String proxyUser = "username";
final static String proxyPass = "password";
private static PoolingHttpClientConnectionManager cm = null;
private static HttpRequestRetryHandler httpRequestRetryHandler = null;
private static HttpHost proxy = null;
private static CredentialsProvider credsProvider = null;
private static RequestConfig reqConfig = null;
static {
ConnectionSocketFactory plainsf = PlainConnectionSocketFactory.getSocketFactory();
LayeredConnectionSocketFactory sslsf = SSLConnectionSocketFactory.getSocketFactory();
Registry registry = RegistryBuilder.create()
.register("http", plainsf)
.register("https", sslsf)
.build();
cm = new PoolingHttpClientConnectionManager(registry);
cm.setMaxTotal(20);
cm.setDefaultMaxPerRoute(5);
proxy = new HttpHost(proxyHost, proxyPort, "http");
credsProvider = new BasicCredentialsProvider();
credsProvider.setCredentials(AuthScope.ANY, new UsernamePasswordCredentials(proxyUser, proxyPass));
reqConfig = RequestConfig.custom()
.setConnectionRequestTimeout(5000)
.setConnectTimeout(5000)
.setSocketTimeout(5000)
.setExpectContinueEnabled(false)
.setProxy(new HttpHost(proxyHost, proxyPort))
.build();
}
public static void doRequest(HttpRequestBase httpReq) {
CloseableHttpResponse httpResp = null;
try {
setHeaders(httpReq);
httpReq.setConfig(reqConfig);
CloseableHttpClient httpClient = HttpClients.custom()
.setConnectionManager(cm)
.setDefaultCredentialsProvider(credsProvider)
.build();
//设置TCP keep alive，访问https网站时保持IP不切换
// SocketConfig socketConfig = SocketConfig.custom().setSoKeepAlive(true).setSoTimeout(3600000).build();
// CloseableHttpClient httpClient =HttpClients.custom()
// .setConnectionManager(cm)
// .setDefaultCredentialsProvider(credsProvider)
// .setDefaultSocketConfig(socketConfig)
// .build();
AuthCache authCache = new BasicAuthCache();
authCache.put(proxy, new BasicScheme());
// 如果遇到407,可以设置代理认证 Proxy-Authenticate
// authCache.put(proxy, new BasicScheme(ChallengeState.PROXY));
HttpClientContext localContext = HttpClientContext.create();
localContext.setAuthCache(authCache);
httpResp = httpClient.execute(httpReq, localContext);
int statusCode = httpResp.getStatusLine().getStatusCode();
System.out.println(statusCode);
BufferedReader rd = new BufferedReader(new InputStreamReader(httpResp.getEntity().getContent()));
String line = "";
while((line = rd.readLine()) != null) {
System.out.println(line);
}
} catch (Exception e) {
e.printStackTrace();
} finally {
try {
if (httpResp != null) {
httpResp.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
}
/**
* 设置请求头
*
* @param httpReq
*/
private static void setHeaders(HttpRequestBase httpReq) {
// 设置Proxy-Tunnel
// Random random = new Random();
// int tunnel = random.nextInt(10000);
// httpReq.setHeader("Proxy-Tunnel", String.valueOf(tunnel));
httpReq.setHeader("Accept-Encoding", null);
}
public static void doGetRequest() {
// 要访问的目标页面
String targetUrl = "https://httpbin.org/ip";
try {
HttpGet httpGet = new HttpGet(targetUrl);
doRequest(httpGet);
} catch (Exception e) {
e.printStackTrace();
}
}
public static void main(String[] args) {
doGetRequest();
}
}示例参考来源于亿牛云，因之前的业务需求购买了代理，一直都还在使用。刚好分享这篇文章就一起分享给大家了，在代理方面有需求的可以试试他们家提供的隧道代理，是我使用众多代理商里面IP质量好，售后服务也最好的一家。代理的详细介
12312312
页:
[1]