ccache_ftp.c

harvest是一个下载html网页得机器人

static char rcsid[] = "ccache_ftp.c,v 1.17 1996/01/04 04:12:23 duane Exp";
/******************************************************************************
 *
 * FILE
 *      ftp.c
 *
 * DESCRIPTION
 *      Contains code for ftp client, these calls are used by processes
 *	desiring ftp services
 *	Contains functions for communicating with FTP server (i.e. socket
 *	level control of data transfer and request)
 *
 * FUNCTIONS
 *	FTPInit()
 *	Login()
 *	Disconnect()
 *	Retrieve()
 *
 *	InitSocket()
 *	ReadServReply()
 *	SendMessage()
 *	ReadOutText()
 *	CheckServReply()
 *	PrepareDataConnect()
 *	RetrieveFile()	
 *	WriteToSocket()
 *
 *  David Merkel & Mark Peterson, University of Colorado - Boulder, July 1994  
 *
 *  ----------------------------------------------------------------------
 *  Copyright (c) 1994, 1995.  All rights reserved.
 *  
 *    The Harvest software was developed by the Internet Research Task
 *    Force Research Group on Resource Discovery (IRTF-RD):
 *  
 *          Mic Bowman of Transarc Corporation.
 *          Peter Danzig of the University of Southern California.
 *          Darren R. Hardy of the University of Colorado at Boulder.
 *          Udi Manber of the University of Arizona.
 *          Michael F. Schwartz of the University of Colorado at Boulder.
 *          Duane Wessels of the University of Colorado at Boulder.
 *  
 *    This copyright notice applies to software in the Harvest
 *    ``src/'' directory only.  Users should consult the individual
 *    copyright notices in the ``components/'' subdirectories for
 *    copyright information about other software bundled with the
 *    Harvest source code distribution.
 *  
 *  TERMS OF USE
 *    
 *    The Harvest software may be used and re-distributed without
 *    charge, provided that the software origin and research team are
 *    cited in any use of the system.  Most commonly this is
 *    accomplished by including a link to the Harvest Home Page
 *    (http://harvest.cs.colorado.edu/) from the query page of any
 *    Broker you deploy, as well as in the query result pages.  These
 *    links are generated automatically by the standard Broker
 *    software distribution.
 *    
 *    The Harvest software is provided ``as is'', without express or
 *    implied warranty, and with no support nor obligation to assist
 *    in its use, correction, modification or enhancement.  We assume
 *    no liability with respect to the infringement of copyrights,
 *    trade secrets, or any patents, and are not responsible for
 *    consequential damages.  Proper use of the Harvest software is
 *    entirely the responsibility of the user.
 *  
 *  DERIVATIVE WORKS
 *  
 *    Users may make derivative works from the Harvest software, subject 
 *    to the following constraints:
 *  
 *      - You must include the above copyright notice and these 
 *        accompanying paragraphs in all forms of derivative works, 
 *        and any documentation and other materials related to such 
 *        distribution and use acknowledge that the software was 
 *        developed at the above institutions.
 *  
 *      - You must notify IRTF-RD regarding your distribution of 
 *        the derivative work.
 *  
 *      - You must clearly notify users that your are distributing 
 *        a modified version and not the original Harvest software.
 *  
 *      - Any derivative product is also subject to these copyright 
 *        and use restrictions.
 *  
 *    Note that the Harvest software is NOT in the public domain.  We
 *    retain copyright, as specified above.
 *  
 *  HISTORY OF FREE SOFTWARE STATUS
 *  
 *    Originally we required sites to license the software in cases
 *    where they were going to build commercial products/services
 *    around Harvest.  In June 1995 we changed this policy.  We now
 *    allow people to use the core Harvest software (the code found in
 *    the Harvest ``src/'' directory) for free.  We made this change
 *    in the interest of encouraging the widest possible deployment of
 *    the technology.  The Harvest software is really a reference
 *    implementation of a set of protocols and formats, some of which
 *    we intend to standardize.  We encourage commercial
 *    re-implementations of code complying to this set of standards.  
 *  
******************************************************************************/
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <fcntl.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/stat.h>
#include <sys/socket.h>
#include <netdb.h>
#include <netinet/in.h>
#include "ccache.h"

extern int select();		/* UNIX sys call */

/******************************************************************************
** function name: FTPInit()
**
** preconditions: hostAddr should be a valid IP address.  portNum is a TCP
**	port to connect to.  errorReply has been allocated by caller.
**
** postconditions: On success a socket descriptor is returned to caller
**	that is connect to hostAddr, portNum.  The value is a negative
**	error otherwise.
**
** author/credits: David Merkel, 4/94
**
******************************************************************************/

int FTPInit(hostAddr, portNum, errorReply)
     u_long hostAddr;		/* address to connect to */
     int portNum;		/* TCP port */
     char *errorReply;		/* string for returning FTP server reply */
{
	int theSocket;		/* socket descriptor to return */
	int error;
	/* string to get FTP server reply */
	char servReply[SERV_REPLY_LENGTH];

	/* initialize socket by connecting to hostAddr, portNum */
	theSocket = InitSocket(hostAddr, portNum);
	if (theSocket < 0)
		return (INIT_SOCKET_ERR);

	/* read FTP server reply */
	error = ReadServReply(theSocket, servReply);
	if (error != NO_ERROR)
		return (error);

	/* check to see if we can continue */
	error = CheckServReply(CONNECT_CHK, servReply);

	/* error found, return to caller */
	if (error != NO_ERROR) {
		memcpy(errorReply, servReply, SERV_REPLY_LENGTH);
		return (error);
	}
	/* no errors, return socket descriptor */
	return (theSocket);
}


/******************************************************************************
** function name: Login()
**
** preconditions: userName and password are valid (i.e. allocated), theSocket
**	is a socket descriptor that has been connected to an FTP server,
**	firstUse indicates if this is the first login attempted on theSocket,
**	and errorReply is preallocated by caller
**
** postconditions: on success userName has been logged in to FTP server and
**	may begin FTP operations.  A negative error value is returned
**	on failure.  If success, the mode is STREAM, and the type
**	is IMAGE (see rfc959).
**
** author/credits: David Merkel, 4/94
**
******************************************************************************/

int Login(userName, password, theSocket, firstUse, errorReply)
     char *userName;		/* user to log into FTP server */
     char *password;		/* password of user */
     int theSocket;		/* socket descriptor to use for communication */
     Boolean firstUse;		/* is this the first login on theSocket? */
     char *errorReply;		/* for returning server replies */
{
	int error;
	char servReply[SERV_REPLY_LENGTH];	/* for storing server replies */
	char modeCode[2], typeCode[2];	/* for setting mode and type */


#if DEBUG > 4
	printf("Login: '%s' @ '%s'   %s\n", userName, password, firstUse ? "TRUE" : "FALSE");
#endif
	/* we've already used this socket before */
	if (!firstUse) {
		/* must send 'REIN' message to reset state of login on
		 * FTP server
		 */
		error = SendMessage(REINIT, NULL, theSocket);
		if (error != NO_ERROR)
			return (error);

		/* read reply for REIN command */
		error = ReadServReply(theSocket, servReply);
		if (error != NO_ERROR)
			return (error);

		/* check reply for REIN command */
		error = CheckServReply(CONNECT_CHK, servReply);
		if (error != NO_ERROR) {
			memcpy(errorReply, servReply, SERV_REPLY_LENGTH);
			return (error);
		}
	}
	/* send USER command */
	error = SendMessage(USER, userName, theSocket);
	if (error != NO_ERROR)
		return (error);

	error = ReadServReply(theSocket, servReply);
	if (error != NO_ERROR)
		return (error);

	/* check for errors on USER reply */
	error = CheckServReply(USER_CHK, servReply);
	if (error == NO_PASS_REQ)
		return (NO_ERROR);
	else if (error != NO_ERROR) {
		memcpy(errorReply, servReply, SERV_REPLY_LENGTH);
		return (error);
	}
	/* finish login sequence with PASS */
	error = SendMessage(PASSWD, password, theSocket);
	if (error != NO_ERROR)
		return (error);

	error = ReadServReply(theSocket, servReply);
	if (error != NO_ERROR)
		return (error);

	/* check for errors */
	error = CheckServReply(PASSWD_CHK, servReply);
	if (error != NO_ERROR) {
		memcpy(errorReply, servReply, SERV_REPLY_LENGTH);
		return (error);
	}
	/* if this is first use, setup STREAM mode, IMAGE data type */
	if (firstUse) {
		modeCode[0] = STREAM;
		modeCode[1] = '\0';

		/* send MODE message */
		error = SendMessage(MODE, modeCode, theSocket);
		if (error != NO_ERROR)
			return (error);

		error = ReadServReply(theSocket, servReply);
		if (error != NO_ERROR)
			return (error);

		/* check MODE reply */
		error = CheckServReply(MODE_CHK, servReply);
		if (error != NO_ERROR) {
			memcpy(errorReply, servReply, SERV_REPLY_LENGTH);
			return (error);
		}
		typeCode[0] = IMAGE;
		typeCode[1] = '\0';

		/* send TYPE message */
		error = SendMessage(TYPE, typeCode, theSocket);
		if (error != NO_ERROR)
			return (error);

		error = ReadServReply(theSocket, servReply);
		if (error != NO_ERROR)
			return (error);

		/* check TYPE reply */
		error = CheckServReply(TYPE_CHK, servReply);
		if (error != NO_ERROR) {
			memcpy(errorReply, servReply, SERV_REPLY_LENGTH);
			return (error);
		}
	}
	return (NO_ERROR);
}


/******************************************************************************
** function name: Disconnect()
**
** preconditions: errorReply is preallocated for return of FTP server errors,
**	theSocket is connected to an FTP server.
**
** postconditions: theSocket has been disconnected from the FTP server.  If
**	an error occurred the result code is returned in errorReply
**
** author/credits: David Merkel, 4/94
**
******************************************************************************/

int Disconnect(theSocket, errorReply)
     int theSocket;		/* socket identifier */
     char *errorReply;		/* string for return of reply codes */
{
	char servReply[SERV_REPLY_LENGTH];	/* to check reply codes */
	int error;

	/* Tell FTP server we're disconnecting */
	error = SendMessage(DISCONNECT, NULL, theSocket);
	if (error != NO_ERROR) {
		close(theSocket);
		return (error);
	}
	/* read its reply */
	error = ReadServReply(theSocket, errorReply);

	/* if no reply, continue disconnect anyway */
	if (error == NO_REPLY_PRESENT) {
		close(theSocket);
		return (NO_ERROR);
	}
	/* return error code to caller */
	memcpy(errorReply, servReply, SERV_REPLY_LENGTH);
	close(theSocket);
	return (SERV_REPLY_ERROR);
}


/******************************************************************************
** function name:  Retrieve()
**
** preconditions:  fileName is name of file to retrieve, theSocket is 
**	the control connection, dataSocket is a socket for data retrieval,
**	isListening tells us if theSocket is already listening for a
**	data connection, sendPort indicates whether or not to use FTP port 
**	command, errorReply is preallocated for return of FTP error codes,
**	data is the returns the retrieved data (preallocated by caller)
**
** postconditions: 
**	File returned inside of data.
**
** author/credits: Dave Merkel, 4/94
**
******************************************************************************/

int Retrieve(fileName, theSocket, dataSocket, isListening, sendPort, errorReply, data)
     char *fileName;		/* name of file to retrieve */
     int theSocket;		/* control connection */
     int dataSocket;		/* data connection (not required) */
     Boolean isListening;	/* theSocket is already listening */
     Boolean sendPort;		/* use PORT command */
     char *errorReply;		/* return error codes */
     DataReturn *data;		/* data storage struct */
{
	extern int gethostname();	/* unix system call */
	struct sockaddr_in theAddr;	/* for use in PORT */
	struct hostent *theEntry = NULL;	/* for use in PORT */

	/* return strings for error codes and send strings for FTP PORT
	 * command
	 */
	char servReply[SERV_REPLY_LENGTH];
	char portMessage[PORT_MESSAGE_LENGTH];
	char hostName[HOST_NAME_LENGTH];

	char *port, *host;	/* for use in PORT */
	int error;
	int newSocket;		/* new data socket */
	int addrLen = sizeof(theAddr);

	/* if using port command or default method with no listen, prepare
	 * a new data connection