Question

我有以下代码。它被反复调用来抓取网络

    public GetWebPageResult(String htmlCode) //CONSTRUCTORS FOR GetWebPageResults
{
    if(htmlCode!=null)
    {
        this.htmlCode=htmlCode;
        htmlErrorCode=-1;
        excCode=0;

    }
    else
    {
        this.htmlCode=null;
        htmlErrorCode=-1;
        excCode=UNKNOWN_ERROR;
    }
}

public GetWebPageResult(int excCode, int htmlErrorCode)
{
    this.htmlCode=null;
    this.excCode=excCode;
    this.htmlErrorCode=htmlErrorCode;
} //END CONSTRUCTORS FOR GetWebPageResults


    static private GetWebPageResult getWebPage(PageNode pagenode)
{
    String result;
    String inputLine;
    URI url;
    int cicliLettura=0;
    long startTime=0, endTime, openConnTime=0,connTime=0, readTime=0;
    try
    {
        startTime=System.nanoTime();
        result="";
        url=pagenode.getUri();      //fare qualcosa se getURI è null
        if(Core.logGetWebPage())
            openConnTime=System.nanoTime();
        if(url!=null)
        {
            HttpURLConnection yc = (HttpURLConnection) url.toURL().openConnection(); //controllare yc
            if(url.toURL().getProtocol().equalsIgnoreCase("https"))
                yc=(HttpsURLConnection)yc;
            yc.addRequestProperty("User-Agent", "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB;     rv:1.9.2.13) Gecko/20101203 Firefox/3.6.13 (.NET CLR 3.5.30729)"); 
            yc.connect();           //controllare il risultato di .connect => non c'è! al max lancia IOEXC
            if(checkResponseCode(yc.getResponseCode())==false)
                return new GetWebPageResult(GetWebPageResult.ERR_BAD_RESPONSE_CODE,yc.getResponseCode());
            if(Core.logGetWebPage())
                connTime=System.nanoTime();

            BufferedReader in = new BufferedReader(new InputStreamReader(yc.getInputStream()));//può lanciare IOEXC
            StringBuffer buffer = new StringBuffer();
            while ((inputLine = in.readLine()) != null)
            {
                buffer.append(inputLine).append('\n');
                cicliLettura++;
            }
            result = buffer.toString();

            if(Core.logGetWebPage())
                readTime=System.nanoTime();
            in.close();
            yc.disconnect();
            if(Core.logGetWebPage())
            {
                endTime=System.nanoTime();
                        //url.toURL() non è null, controllato prima
                System.out.println(/*result+*/"getWebPage eseguito in "+(endTime-startTime)/1000000+" ms. Size: "+result.length()+" Response Code="+yc.getResponseCode()+" Protocollo="+url.toURL().getProtocol()+" openConnTime: "+(openConnTime-startTime)/1000000+" connTime:"+(connTime-openConnTime)/1000000+" readTime:"+(readTime-connTime)/1000000+" cicliLettura="+cicliLettura+" pagina:"+url.toURL());
            }
            return new GetWebPageResult(result);
        }
        else
            return new GetWebPageResult(GetWebPageResult.ERR_NULL_URI,-2);
    }catch(IOException e){
        System.out.println("Eccezione1: "+e.toString());
        e.printStackTrace();  
        return new GetWebPageResult(GetWebPageResult.ERR_HTML_IOEXCEPTION,-2);
    }catch(ClassCastException e){
        System.out.println("Eccezione2: "+e.toString());
        e.printStackTrace(); 
        return new GetWebPageResult(GetWebPageResult.ERR_CLASS_CAST_EXC,-2);
    }catch(Exception e){
        System.out.println("Eccezione ERR_NOT_LISTED_EXC: "+e.toString());
        return new GetWebPageResult(GetWebPageResult.ERR_NOT_LISTED_EXC,-2);
    }
}

线程因此异常而停止：

java.net.UnknownHostException: www.notjohnchow.com
at java.net.AbstractPlainSocketImpl.connect(Unknown Source)
at java.net.PlainSocketImpl.connect(Unknown Source)
at java.net.SocksSocketImpl.connect(Unknown Source)
at java.net.Socket.connect(Unknown Source)
at java.net.Socket.connect(Unknown Source)
at sun.net.NetworkClient.doConnect(Unknown Source)
at sun.net.www.http.HttpClient.openServer(Unknown Source)
at sun.net.www.http.HttpClient.openServer(Unknown Source)
at sun.net.www.http.HttpClient.<init>(Unknown Source)
at sun.net.www.http.HttpClient.New(Unknown Source)
at sun.net.www.http.HttpClient.New(Unknown Source)
at sun.net.www.protocol.http.HttpURLConnection.getNewHttpClient(Unknown Source)
at sun.net.www.protocol.http.HttpURLConnection.plainConnect(Unknown Source)
at sun.net.www.protocol.http.HttpURLConnection.connect(Unknown Source)
at WebsiteCrawler.getWebPage(WebsiteCrawler.java:315)
at WebsiteCrawler.crawlNextPage(WebsiteCrawler.java:71)
at Website.run(Website.java:51)

当尝试连接到＆＃34; www.notjohnchow.com＆＃34;时，yc.connect启动了例外。为什么不是最后一个获得异常的catch块？我已经设置了try-catch以捕获许多异常，如果当前异常不是第一个异常，我将其称为＆＃34;未知错误＆＃34;在catch（例外e）块中。

Answer 1

你确定你的线程死了吗？如果我的头脑中没有完全错误，则UnknownHostException是IOException的后代，并且由第一个catch块捕获，因此打印出StackTrace。

java：泛型异常不捕获java.net.UnknownHostException

1 个答案: