Java how to read all the page source of a large web page

Hi,

I am using Nutch to crawl some web pages, some of which are big .html file. The http plugin used in Nutch can't read all the page source of such big .html file.

I attach two code snippets down below. In either case,  the content variable  (byte[] content) actually holds the page source of a web page.

It turns out that both ways return almost the same length of the contents requested. So I guess maybe there is a maximum length of contents that can be returned.

However, how can I overcome this content limit?

Thanks

this.url = url;
    GetMethod get = new GetMethod(url.toString());
    get.setFollowRedirects(followRedirects);
    get.setDoAuthentication(true);
    if (datum.getModifiedTime() > 0) {
      get.setRequestHeader("If-Modified-Since",
          HttpDateFormat.toString(datum.getModifiedTime()));
    }

    // Set HTTP parameters
    HttpMethodParams params = get.getParams();
    if (http.getUseHttp11()) {
      params.setVersion(HttpVersion.HTTP_1_1);
    } else {
      params.setVersion(HttpVersion.HTTP_1_0);
    }
    params.makeLenient();
    params.setContentCharset("UTF-8");
    params.setCookiePolicy(CookiePolicy.BROWSER_COMPATIBILITY);
    params.setBooleanParameter(HttpMethodParams.SINGLE_COOKIE_HEADER, true);
    // XXX (ab) not sure about this... the default is to retry 3 times; if
    // XXX the request body was sent the method is not retried, so there is
    // XXX little danger in retrying...
    // params.setParameter(HttpMethodParams.RETRY_HANDLER, null);
    try {
      code = Http.getClient().executeMethod(get);

      Header[] heads = get.getResponseHeaders();

      for (int i = 0; i < heads.length; i++) {
        headers.set(heads[i].getName(), heads[i].getValue());
      }
      
      // Limit download size
      int contentLength = Integer.MAX_VALUE;
      String contentLengthString = headers.get(Response.CONTENT_LENGTH);
      if (contentLengthString != null) {
        try {
          contentLength = Integer.parseInt(contentLengthString.trim());
        } catch (NumberFormatException ex) {
          throw new HttpException("bad content length: " +
              contentLengthString);
        }
      }
      if (http.getMaxContent() >= 0 &&
          contentLength > http.getMaxContent()) {
        contentLength = http.getMaxContent();
      }

      // always read content. Sometimes content is useful to find a cause
      // for error.
      InputStream in = get.getResponseBodyAsStream();
      try {
        byte[] buffer = new byte[HttpBase.BUFFER_SIZE];
    	//byte[] buffer = new byte[contentLength];
        int bufferFilled = 0;
        int totalRead = 0;
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        while ((bufferFilled = in.read(buffer, 0, buffer.length)) != -1
            && totalRead < contentLength) {
          totalRead += bufferFilled;
          out.write(buffer, 0, bufferFilled);
        }

        content = out.toByteArray();
        
      } catch (Exception e) {
        if (code == 200) throw new IOException(e.toString());
        // for codes other than 200 OK, we are fine with empty content
      } finally {
        if (in != null) {
          in.close();
        }
        get.abort();
      }

Select all Open in new window

try {
      socket = new Socket();                    // create the socket
      socket.setSoTimeout(http.getTimeout());


      // connect
      String sockHost = http.useProxy() ? http.getProxyHost() : host;
      int sockPort = http.useProxy() ? http.getProxyPort() : port;
      InetSocketAddress sockAddr= new InetSocketAddress(sockHost, sockPort);
      socket.connect(sockAddr, http.getTimeout());

      // make request
      OutputStream req = socket.getOutputStream();

      StringBuffer reqStr = new StringBuffer("GET ");
      if (http.useProxy()) {
      	reqStr.append(url.getProtocol()+"://"+host+portString+path);
      } else {
      	reqStr.append(path);
      }

      reqStr.append(" HTTP/1.0\r\n");

      reqStr.append("Host: ");
      reqStr.append(host);
      reqStr.append(portString);
      reqStr.append("\r\n");

      reqStr.append("Accept-Encoding: x-gzip, gzip, deflate\r\n");

      String userAgent = http.getUserAgent();
      if ((userAgent == null) || (userAgent.length() == 0)) {
        if (Http.LOG.isFatalEnabled()) { Http.LOG.fatal("User-agent is not set!"); }
      } else {
        reqStr.append("User-Agent: ");
        reqStr.append(userAgent);
        reqStr.append("\r\n");
      }
      
      reqStr.append("Accept-Language: ");
      reqStr.append(this.http.getAcceptLanguage());
      reqStr.append("\r\n");

      if (datum.getModifiedTime() > 0) {
        reqStr.append("If-Modified-Since: " + HttpDateFormat.toString(datum.getModifiedTime()));
        reqStr.append("\r\n");
      }
      reqStr.append("\r\n");
      
      byte[] reqBytes= reqStr.toString().getBytes();

      req.write(reqBytes);
      req.flush();
        
      PushbackInputStream in =                  // process response
        new PushbackInputStream(
          new BufferedInputStream(socket.getInputStream(), Http.BUFFER_SIZE), 
          Http.BUFFER_SIZE) ;

      StringBuffer line = new StringBuffer();

      boolean haveSeenNonContinueStatus= false;
      while (!haveSeenNonContinueStatus) {
        // parse status code line
        this.code = parseStatusLine(in, line); 
        // parse headers
        parseHeaders(in, line);
        haveSeenNonContinueStatus= code != 100; // 100 is "Continue"
      }

      readPlainContent(in);

      String contentEncoding = getHeader(Response.CONTENT_ENCODING);
      if ("gzip".equals(contentEncoding) || "x-gzip".equals(contentEncoding)) {
        content = http.processGzipEncoded(content, url);
      } else if ("deflate".equals(contentEncoding)) {
       content = http.processDeflateEncoded(content, url);
      } else {
        if (Http.LOG.isTraceEnabled()) {
          Http.LOG.trace("fetched " + content.length + " bytes from " + url);
        }
      }

Select all Open in new window