2017-02-22 38 views
0

我正在製作命令行工具多次訪問網站。我一次使用多個線程訪問頁面,每個線程使用循環重複訪問網站。工具工作正常,並根據需要訪問網站,但唯一的問題是面臨打開網站並在幾分鐘後關閉它。所以每次訪問的會話持續時間限制在3到4秒。我需要增加此會話持續時間至少60秒。以下是我的代碼。HtmlUnit WebClient Session Duration

package directUrl; 

import java.io.IOException; 
import java.net.MalformedURLException; 
import java.net.URL; 

import com.gargoylesoftware.htmlunit.BrowserVersion; 
import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException; 
import com.gargoylesoftware.htmlunit.WebClient; 

public class ThreadDirectUrl extends Thread { 

    private String url; 
    private String paramUserAgent; 
    private String paramReferer; 
    private int loopSize; 

    public ThreadDirectUrl(String url, String paramUserAgent, String paramReferer, int loopSize) { 
     this.url = url; 
     this.paramUserAgent = paramUserAgent; 
     this.paramReferer = paramReferer; 
     this.loopSize = loopSize; 
    } 

    public void run() { 
     String userAgent = new String(); 

     // Get User Agent 
     if (paramUserAgent.equals("1")) { 
      userAgent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:17.0) Gecko/17.0 Firefox/17.0"; 
     } else if (paramUserAgent.equals("2")) { 
      userAgent = "Mozilla/5.0 (Linux; U; Android 2.2; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"; 
     } else if (paramUserAgent.equals("3")) { 
      userAgent = "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_0 like Mac OS X; en-us) AppleWebKit/532.9 (KHTML, like Gecko) Version/4.0.5 Mobile/8A293 Safari/6531.22.7"; 
     } else if (paramUserAgent.equals("4")) { 
      userAgent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.79 Safari/537.1"; 
     } 

     BrowserVersion bv = new BrowserVersion("Netscape", "Version", userAgent, 0); 

     try { 
      URL openUrl = new URL(url); 
      for (int i = 1; i <= loopSize; i++) { 
       WebClient webClient = new WebClient(bv); 
       webClient.addRequestHeader("Accept-Encoding", "compress, gzip"); 
       webClient.addRequestHeader("Referer", paramReferer); 
       webClient.getOptions().setPrintContentOnFailingStatusCode(true); 
       webClient.getOptions().setThrowExceptionOnFailingStatusCode(false); 
       webClient.getOptions().setThrowExceptionOnScriptError(false); 
       webClient.getOptions().setJavaScriptEnabled(true); 
       webClient.getOptions().setCssEnabled(false); 
       webClient.getOptions().setPopupBlockerEnabled(true); 
       webClient.getOptions().setMaxInMemory(3); 
       webClient.getPage(openUrl); 

       System.out.println(Thread.currentThread().getName() + "----" + i + "----\nSuccess!\nUser Agent: " 
         + bv.getUserAgent() + "\n\n"); 
       Thread.sleep(60000); 
       webClient.getCurrentWindow().getJobManager().removeAllJobs(); 
       webClient.close(); 
      } 
      System.out.println(Thread.currentThread().getName() + "COMPLETED"); 

     } catch (FailingHttpStatusCodeException e) { 
      System.out.println("Error!"); 
     } catch (MalformedURLException e) { 
      System.out.println("Error - Use URL with \"http://\" or \"https://\"!"); 
     } catch (IOException e) { 
      System.out.println("Error!"); 
     } catch (ArrayIndexOutOfBoundsException e) { 
      System.out.println("Error!"); 
     } catch (InterruptedException e) { 
      System.out.println(Thread.currentThread().getName() + "Interrupted"); 
     } finally { 

      System.gc(); 
     } 
    } 
} 

主要類是如下

package directUrl; 

import java.util.logging.Level; 
import java.util.logging.Logger; 

public class DirectUrl { 

    public static void main(String[] args) { 

     // Production Variables 
     String url = args[0]; // URL 
     String paramUserAgent = args[1]; // User Agent Choice 
     String paramReferer = args[2]; // Referrer URL 
     int loopSize = Integer.parseInt(args[3]); // Loop Size 
     int threadSize = Integer.parseInt(args[4]); // Counts of threads 

     Logger logger = Logger.getLogger(""); 
     logger.setLevel(Level.OFF); 

     // Create Multiple Threads 
     ThreadDirectUrl aThread; 
     for (int i = 1; i <= threadSize; i++) { 
      aThread = new ThreadDirectUrl(url, paramUserAgent, paramReferer, loopSize); 
      aThread.setName("thread" + i); 
      aThread.start(); 
     } 

    } 

} 

在類ThreadDirectUrl,我使用;

Thread.sleep(60000); 

getPage()方法但它不工作。請建議。

+0

什麼錯誤,你的睡眠後''弄,你可以通過'LogManager.getLogger(「org.apache.http.wire」),參見頭餅乾setLevel(ORG .apache.log4j.Level.ALL);'請發佈示例URL –

+0

@AhmedAshour沒有錯誤。 –

+0

那麼,你期望什麼?你得到一個頁面(隱含會話),接下來應該做什麼?什麼'不工作'。 –

回答

0

如果希望服務器看到會話壽命更長,那麼請與客戶端進行一些操作。

E.g.再次加載相同頁面:?

webClient.getPage(openUrl); 

Thread.sleep(60000); 

// then get the same page again 
webClient.getPage(openUrl); 
+0

在發佈答案之前,我做了同樣的事情,並且在做了一些關於服務器如何查看會話持續時間的研究之後,我做了同樣的工作。但我會標記你的答案是正確的。 –

+0

謝謝,也嘗試使用剛剛發佈的最新版本2.25。 –