本文研究的主要是java网络爬虫连接超时的问题,具体如下。
在网络爬虫中,经常会遇到如下报错。即连接超时。针对此问题,一般解决思路为:将连接时间、请求时间设置长一下。如果出现连接超时的情况,则在重新请求【设置重新请求次数】。
Exception in thread "main" java.net.ConnectException: Connection timed out: connect
下面的代码便是使用httpclient解决连接超时的样例程序。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:合肥工业大学 管院学院 钱洋 *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); //设置参数 HttpParams params = httpclient.getParams(); //连接时间 HttpConnectionParams.setConnectionTimeout(params, 6000); HttpConnectionParams.setSoTimeout(params, 6000*20); //超时重新请求次数 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(); //获取响应状态码 System.out.println(StatusCode); if(StatusCode == 200){ //状态码200表示响应成功 //获取实体内容 rawHTML = EntityUtils.toString (response.getEntity()); System.out.println(rawHTML); //输出实体内容 EntityUtils.consume(response.getEntity()); //消耗实体 } else { //关闭HttpEntity的流实体 EntityUtils.consume(response.getEntity()); //消耗实体 Thread.sleep(20*60*1000); //如果报错先休息30分钟 } httpclient.close(); System.out.println(rawHTML); return rawHTML; } }
结果:
总结
以上就是本文关于java网络爬虫连接超时解决实例代码的全部内容,希望对大家有所帮助。感兴趣的朋友可以继续参阅本站其他相关专题,如有不足之处,欢迎留言指出。感谢朋友们对本站的支持!