Examples of RequestHeader


Examples of net.yacy.cora.protocol.RequestHeader

    /**
     * @param url
     * @return
     */
    public static Map<String, String> loadFileAsMap(final DigestURI url) {
        final RequestHeader reqHeader = new RequestHeader();
        reqHeader.put(HeaderFramework.USER_AGENT, ClientIdentification.getUserAgent());
        final HTTPClient client = new HTTPClient();
        client.setHeader(reqHeader.entrySet());
        try {
            // sending request
            final Map<String, String> result = FileUtils.table(client.GETbytes(url));
            return (result == null) ? new HashMap<String, String>() : result;
        } catch (final Exception e) {
View Full Code Here

Examples of net.yacy.cora.protocol.RequestHeader

        // read password
        String encodedPassword = (String) config.get(SwitchboardConstants.ADMIN_ACCOUNT_B64MD5);
        if (encodedPassword == null) encodedPassword = ""; // not defined

        // send 'wget' to web interface
        final RequestHeader requestHeader = new RequestHeader();
        requestHeader.put(RequestHeader.AUTHORIZATION, "realm=" + encodedPassword); // for http-authentify
//        final Client con = new Client(10000, requestHeader);
        final HTTPClient con = new HTTPClient();
        con.setHeader(requestHeader.entrySet());
//        ResponseContainer res = null;
        try {
//            res = con.GET("http://localhost:"+ port +"/" + path);
            con.GETbytes("http://localhost:"+ port +"/" + path);
View Full Code Here

Examples of net.yacy.cora.protocol.RequestHeader

        String eTag=null, oldEtag = null;
        Date lastMod=null;
        downloadStart = System.currentTimeMillis();
       
        // if we previously have downloaded this robots.txt then we can set the if-modified-since header
        RequestHeader reqHeaders = new RequestHeader();
       
        // add yacybot user agent
        reqHeaders.put(HeaderFramework.USER_AGENT, ClientIdentification.getUserAgent());
       
        // adding referer
        reqHeaders.put(RequestHeader.REFERER, (MultiProtocolURI.newURL(robotsURL,"/")).toNormalform(true, true));
       
        if (entry != null) {
            oldEtag = entry.getETag();
            reqHeaders = new RequestHeader();
            final Date modDate = entry.getModDate();
            if (modDate != null) reqHeaders.put(RequestHeader.IF_MODIFIED_SINCE, HeaderFramework.formatRFC1123(entry.getModDate()));
           
        }
       
        // setup http-client
        //TODO: adding Traffic statistic for robots download?
        final HTTPClient client = new HTTPClient();
        client.setHeader(reqHeaders.entrySet());
        try {
            // check for interruption
            if (Thread.currentThread().isInterrupted()) throw new InterruptedException("Shutdown in progress.");
           
            // sending the get request
View Full Code Here

Examples of net.yacy.cora.protocol.RequestHeader

            if (cachedResponse != null && content != null) {
                // yes we have the content

                // create request header values and a response object because we need that
                // in case that we want to return the cached content in the next step
                final RequestHeader requestHeader = new RequestHeader();
                requestHeader.put(HeaderFramework.USER_AGENT, ClientIdentification.getUserAgent());
                DigestURI refererURL = null;
                if (request.referrerhash() != null) refererURL = this.sb.getURL(Segments.Process.LOCALCRAWLING, request.referrerhash());
                if (refererURL != null) requestHeader.put(RequestHeader.REFERER, refererURL.toNormalform(true, true));
                final Response response = new Response(
                        request,
                        requestHeader,
                        cachedResponse,
                        "200",
View Full Code Here

Examples of net.yacy.cora.protocol.RequestHeader

    }
   
    public Response(final Request request, final CrawlProfile profile) {
        this.request = request;
        // request and response headers may be zero in case that we process surrogates
        this.requestHeader = new RequestHeader();
        this.responseHeader = new ResponseHeader();
        if (request.size() > 0) this.responseHeader.put(HeaderFramework.CONTENT_LENGTH, Long.toString(request.size()));
        this.responseStatus = "200";
        this.profile = profile;
        this.status = QUEUE_STATE_FRESH;
View Full Code Here

Examples of net.yacy.cora.protocol.RequestHeader

       
        // take a file from the net
        Response response = null;
       
        // create a request header
        final RequestHeader requestHeader = new RequestHeader();
        requestHeader.put(HeaderFramework.USER_AGENT, ClientIdentification.getUserAgent());
        DigestURI refererURL = null;
        if (request.referrerhash() != null) refererURL = sb.getURL(Segments.Process.LOCALCRAWLING, request.referrerhash());
        if (refererURL != null) requestHeader.put(RequestHeader.REFERER, refererURL.toNormalform(true, true));
        requestHeader.put(HeaderFramework.ACCEPT_LANGUAGE, sb.getConfig("crawler.http.acceptLanguage", DEFAULT_LANGUAGE));
        requestHeader.put(HeaderFramework.ACCEPT_CHARSET, sb.getConfig("crawler.http.acceptCharset", DEFAULT_CHARSET));
        requestHeader.put(HeaderFramework.ACCEPT_ENCODING, sb.getConfig("crawler.http.acceptEncoding", DEFAULT_ENCODING));

        // HTTP-Client
        final HTTPClient client = new HTTPClient();
        client.setRedirecting(false); // we want to handle redirection ourselves, so we don't index pages twice
        client.setTimout(socketTimeout);
        client.setHeader(requestHeader.entrySet());
            // send request
          final byte[] responseBody = client.GETbytes(url, maxFileSize);
          final ResponseHeader header = new ResponseHeader(client.getHttpResponse().getAllHeaders());
          final int code = client.getHttpResponse().getStatusLine().getStatusCode();
View Full Code Here

Examples of net.yacy.cora.protocol.RequestHeader

       
        // take a file from the net
        Response response = null;
       
        // create a request header
        final RequestHeader requestHeader = new RequestHeader();
        requestHeader.put(HeaderFramework.USER_AGENT, ClientIdentification.getUserAgent());
        requestHeader.put(HeaderFramework.ACCEPT_LANGUAGE, DEFAULT_LANGUAGE);
        requestHeader.put(HeaderFramework.ACCEPT_CHARSET, DEFAULT_CHARSET);
        requestHeader.put(HeaderFramework.ACCEPT_ENCODING, DEFAULT_ENCODING);

        final HTTPClient client = new HTTPClient();
        client.setTimout(20000);
        client.setHeader(requestHeader.entrySet());
          final byte[] responseBody = client.GETbytes(request.url(), Long.MAX_VALUE);
          final ResponseHeader header = new ResponseHeader(client.getHttpResponse().getAllHeaders());
          final int code = client.getHttpResponse().getStatusLine().getStatusCode();
            // FIXME: 30*-handling (bottom) is never reached
            // we always get the final content because httpClient.followRedirects = true
View Full Code Here

Examples of net.yacy.cora.protocol.RequestHeader

   
    public Response load(final Request request, boolean acceptOnlyParseable) throws IOException {
        DigestURI url = request.url();
        if (!url.getProtocol().equals("file")) throw new IOException("wrong loader for FileLoader: " + url.getProtocol());

        RequestHeader requestHeader = new RequestHeader();
        if (request.referrerhash() != null) {
            DigestURI ur = sb.getURL(Segments.Process.LOCALCRAWLING, request.referrerhash());
            if (ur != null) requestHeader.put(RequestHeader.REFERER, ur.toNormalform(true, false));
        }
       
        // process directories: transform them to html with meta robots=noindex (using the ftpc lib)
        String[] l = null;
        try {l = url.list();} catch (IOException e) {}
View Full Code Here

Examples of net.yacy.cora.protocol.RequestHeader

   
    public Response load(final Request request, boolean acceptOnlyParseable) throws IOException {
        DigestURI url = request.url();
        if (!url.getProtocol().equals("smb")) throw new IOException("wrong loader for SMBLoader: " + url.getProtocol());

        RequestHeader requestHeader = new RequestHeader();
        if (request.referrerhash() != null) {
            DigestURI ur = sb.getURL(Segments.Process.LOCALCRAWLING, request.referrerhash());
            if (ur != null) requestHeader.put(RequestHeader.REFERER, ur.toNormalform(true, false));
        }
       
        // process directories: transform them to html with meta robots=noindex (using the ftpc lib)
        String[] l = null;
        try {l = url.list();} catch (IOException e) {}
View Full Code Here

Examples of net.yacy.cora.protocol.RequestHeader

                }
            }

            if (file.length() == 0) {
                // directory -> get list of files
                RequestHeader requestHeader = new RequestHeader();
                if (request.referrerhash() != null) {
                    DigestURI u = sb.getURL(Segments.Process.LOCALCRAWLING, request.referrerhash());
                    if (u != null) requestHeader.put(RequestHeader.REFERER, u.toNormalform(true, false));
                }
               
                StringBuilder dirList = ftpClient.dirhtml(path);

                if (dirList == null) {
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.