Class Ftp

src/plugin/protocol-ftp/src/java/org/apache/nutch/protocol/ftp/Ftp.java:46–278

This class is a protocol plugin used for ftp: scheme. It creates FtpResponse object and gets the content of the url from it. Configurable parameters are ftp.username, ftp.password, ftp.content.limit, ftp.timeout, ftp.server.timeout, {@code ftp.password

 * . For details see "FTP properties" section in {@code nutch-default.xml}.
 */
public class Ftp implements Protocol {

  protected static final Logger LOG = LoggerFactory
      .getLogger(MethodHandles.lookup().lookupClass());

  private static final Collection<WebPage.Field> FIELDS = new HashSet<WebPage.Field>();

  static {
    FIELDS.add(WebPage.Field.MODIFIED_TIME);
    FIELDS.add(WebPage.Field.HEADERS);
  }

  static final int BUFFER_SIZE = 16384; // 16*1024 = 16384

  static final int MAX_REDIRECTS = 5;

  int timeout;

  int maxContentLength;

  String userName;
  String passWord;

  // typical/default server timeout is 120*1000 millisec.
  // better be conservative here
  int serverTimeout;

  // when to have client start anew
  long renewalTime = -1;

  boolean keepConnection;

  boolean followTalk;

  // ftp client
  Client client = null;
  // ftp dir list entry parser
  FTPFileEntryParser parser = null;

  private Configuration conf;

  private FtpRobotRulesParser robots = null;

  // constructor
  public Ftp() {
    robots = new FtpRobotRulesParser();
  }

  /** Set the timeout. */
  public void setTimeout(int to) {
    timeout = to;
  }

  /** Set the point at which content is truncated. */
  public void setMaxContentLength(int length) {
    maxContentLength = length;
  }