快捷導(dǎo)航

java網(wǎng)絡(luò)爬蟲連接超時解決實例代碼

更新時間：2018年01月24日 10:22:11 作者：sober_qianyang

這篇文章主要介紹了java網(wǎng)絡(luò)爬蟲連接超時解決的問題，分享了一則使用httpclient解決連接超時的Java爬蟲實例代碼，小編覺得還是挺不錯的，具有一定借鑒價值，需要的朋友可以參考下

本文研究的主要是java網(wǎng)絡(luò)爬蟲連接超時的問題，具體如下。

在網(wǎng)絡(luò)爬蟲中，經(jīng)常會遇到如下報錯。即連接超時。針對此問題，一般解決思路為：將連接時間、請求時間設(shè)置長一下。如果出現(xiàn)連接超時的情況，則在重新請求【設(shè)置重新請求次數(shù)】。

Exception in thread "main" java.net.ConnectException: Connection timed out: connect

下面的代碼便是使用httpclient解決連接超時的樣例程序。直接上程序。

package daili;
import java.io.IOException;
import java.net.URI;
import org.apache.http.HttpRequest;
import org.apache.http.HttpResponse;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.params.CookiePolicy;
import org.apache.http.client.protocol.ClientContext;
import org.apache.http.impl.client.BasicCookieStore;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.impl.client.DefaultHttpRequestRetryHandler;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.impl.cookie.BasicClientCookie2;
import org.apache.http.params.HttpConnectionParams;
import org.apache.http.params.HttpParams;
import org.apache.http.protocol.BasicHttpContext;
import org.apache.http.protocol.ExecutionContext;
import org.apache.http.protocol.HttpContext;
import org.apache.http.util.EntityUtils;
/*
 * author:合肥工業(yè)大學(xué) 管院學(xué)院 錢洋 
 *1563178220@qq.com
*/
public class Test1 {
	public static void main(String[] args) throws ClientProtocolException, IOException, InterruptedException {
		getRawHTML("http://club.autohome.com.cn/bbs/forum-c-2098-1.html#pvareaid=103447");
	}
	public static String getRawHTML ( String url ) throws ClientProtocolException, IOException, InterruptedException{
		//初始化
		DefaultHttpClient httpclient = new DefaultHttpClient();
		httpclient.getParams().setParameter("http.protocol.cookie-policy", 
		        CookiePolicy.BROWSER_COMPATIBILITY);
		//設(shè)置參數(shù)
		HttpParams params = httpclient.getParams();
		//連接時間
		HttpConnectionParams.setConnectionTimeout(params, 6000);
		HttpConnectionParams.setSoTimeout(params, 6000*20);
		//超時重新請求次數(shù)
		DefaultHttpRequestRetryHandler dhr = new DefaultHttpRequestRetryHandler(5,true);
		HttpContext localContext = new BasicHttpContext();
		HttpRequest request2 = (HttpRequest) localContext.getAttribute( 
		        ExecutionContext.HTTP_REQUEST);
		httpclient.setHttpRequestRetryHandler(dhr);
		BasicCookieStore cookieStore = new BasicCookieStore();
		BasicClientCookie2 cookie = new BasicClientCookie2("Content-Type","text/html;charset=UTF-8");
		BasicClientCookie2 cookie1 = new BasicClientCookie2("User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36");
		cookieStore.addCookie(cookie);
		cookieStore.addCookie(cookie1);
		localContext.setAttribute(ClientContext.COOKIE_STORE, cookieStore);
		HttpGet request = new HttpGet();
		request.setURI(URI.create(url));
		HttpResponse response = null;
		String rawHTML = "";
		response = httpclient.execute(request,localContext);
		int StatusCode = response.getStatusLine().getStatusCode();
		//獲取響應(yīng)狀態(tài)碼
		System.out.println(StatusCode);
		if(StatusCode == 200){
			//狀態(tài)碼200表示響應(yīng)成功
			//獲取實體內(nèi)容
			rawHTML = EntityUtils.toString (response.getEntity());
			System.out.println(rawHTML);
			//輸出實體內(nèi)容
			EntityUtils.consume(response.getEntity());
			//消耗實體
		} else {
			//關(guān)閉HttpEntity的流實體
			EntityUtils.consume(response.getEntity());
			//消耗實體
			Thread.sleep(20*60*1000);
			//如果報錯先休息30分鐘
		}
		httpclient.close();
		System.out.println(rawHTML);
		return rawHTML;
	}
}

結(jié)果：