Lib/ftplib.py

"""An FTP client class and some helper functions.

Based on RFC 959: File Transfer Protocol (FTP), by J. Postel and J. Reynolds

Example:

>>> from ftplib import FTP
>>> ftp = FTP('ftp.python.org') # connect to host, default port
>>> ftp.login() # default, i.e.: user anonymous, passwd anonymous@
'230 Guest login ok, access restrictions apply.'
>>> ftp.retrlines('LIST') # list directory contents
total 9
drwxr-xr-x   8 root     wheel        1024 Jan  3  1994 .
drwxr-xr-x   8 root     wheel        1024 Jan  3  1994 ..
drwxr-xr-x   2 root     wheel        1024 Jan  3  1994 bin
drwxr-xr-x   2 root     wheel        1024 Jan  3  1994 etc
d-wxrwxr-x   2 ftp      wheel        1024 Sep  5 13:43 incoming
drwxr-xr-x   2 root     wheel        1024 Nov 17  1993 lib
drwxr-xr-x   6 1094     wheel        1024 Sep 13 19:07 pub
drwxr-xr-x   3 root     wheel        1024 Jan  3  1994 usr
-rw-r--r--   1 root     root          312 Aug  1  1994 welcome.msg
'226 Transfer complete.'
>>> ftp.quit()
'221 Goodbye.'
>>>

A nice test that reveals some of the network dialogue would be:
python ftplib.py -d localhost -l -p -l
"""

#
# Changes and improvements suggested by Steve Majewski.
# Modified by Jack to work on the mac.
# Modified by Siebren to support docstrings and PASV.
#

import os
import sys

# Import SOCKS module if it exists, else standard socket module socket
try:
    import SOCKS; socket = SOCKS; del SOCKS # import SOCKS as socket
    from socket import getfqdn; socket.getfqdn = getfqdn; del getfqdn
except ImportError:
    import socket

__all__ = ["FTP","Netrc"]

# Magic number from <socket.h>
MSG_OOB = 0x1                           # Process data out of band


# The standard FTP server control port
FTP_PORT = 21


# Exception raised when an error or invalid response is received
class Error(Exception): pass
class error_reply(Error): pass          # unexpected [123]xx reply
class error_temp(Error): pass           # 4xx errors
class error_perm(Error): pass           # 5xx errors
class error_proto(Error): pass          # response does not begin with [1-5]


# All exceptions (hopefully) that may be raised here and that aren't
# (always) programming errors on our side
all_errors = (Error, socket.error, IOError, EOFError)


# Line terminators (we always output CRLF, but accept any of CRLF, CR, LF)
CRLF = '\r\n'


# The class itself
class FTP:

    '''An FTP client class.

    To create a connection, call the class using these argument:
            host, user, passwd, acct
    These are all strings, and have default value ''.
    Then use self.connect() with optional host and port argument.

    To download a file, use ftp.retrlines('RETR ' + filename),
    or ftp.retrbinary() with slightly different arguments.
    To upload a file, use ftp.storlines() or ftp.storbinary(),
    which have an open file as argument (see their definitions
    below for details).
    The download/upload functions first issue appropriate TYPE
    and PORT or PASV commands.
'''

    debugging = 0
    host = ''
    port = FTP_PORT
    sock = None
    file = None
    welcome = None
    passiveserver = 1

    # Initialization method (called by class instantiation).
    # Initialize host to localhost, port to standard ftp port
    # Optional arguments are host (for connect()),
    # and user, passwd, acct (for login())
    def __init__(self, host='', user='', passwd='', acct=''):
        if host:
            self.connect(host)
            if user: self.login(user, passwd, acct)

    def connect(self, host = '', port = 0):
        '''Connect to host.  Arguments are:
        - host: hostname to connect to (string, default previous host)
        - port: port to connect to (integer, default previous port)'''
        if host: self.host = host
        if port: self.port = port
        msg = "getaddrinfo returns an empty list"
        for res in socket.getaddrinfo(self.host, self.port, 0, socket.SOCK_STREAM):
            af, socktype, proto, canonname, sa = res
            try:
                self.sock = socket.socket(af, socktype, proto)
                self.sock.connect(sa)
            except socket.error as err:
                msg = err
                if self.sock:
                    self.sock.close()
                self.sock = None
                continue
            break
        if not self.sock:
            raise socket.error, msg
        self.af = af
        self.file = self.sock.makefile('rb')
        self.welcome = self.getresp()
        return self.welcome

    def getwelcome(self):
        '''Get the welcome message from the server.
        (this is read and squirreled away by connect())'''
        if self.debugging:
            print '*welcome*', self.sanitize(self.welcome)
        return self.welcome

    def set_debuglevel(self, level):
        '''Set the debugging level.
        The required argument level means:
        0: no debugging output (default)
        1: print commands and responses but not body text etc.
        2: also print raw lines read and sent before stripping CR/LF'''
        self.debugging = level
    debug = set_debuglevel

    def set_pasv(self, val):
        '''Use passive or active mode for data transfers.
        With a false argument, use the normal PORT mode,
        With a true argument, use the PASV command.'''
        self.passiveserver = val

    # Internal: "sanitize" a string for printing
    def sanitize(self, s):
        if s[:5] == 'pass ' or s[:5] == 'PASS ':
            i = len(s)
            while i > 5 and s[i-1] in '\r\n':
                i = i-1
            s = s[:5] + '*'*(i-5) + s[i:]
        return repr(s)

    # Internal: send one line to the server, appending CRLF
    def putline(self, line):
        line = line + CRLF
        if self.debugging > 1: print '*put*', self.sanitize(line)
        self.sock.sendall(line)

    # Internal: send one command to the server (through putline())
    def putcmd(self, line):
        if self.debugging: print '*cmd*', self.sanitize(line)
        self.putline(line)

    # Internal: return one line from the server, stripping CRLF.
    # Raise EOFError if the connection is closed
    def getline(self):
        line = self.file.readline()
        if self.debugging > 1:
            print '*get*', self.sanitize(line)
        if not line: raise EOFError
        if line[-2:] == CRLF: line = line[:-2]
        elif line[-1:] in CRLF: line = line[:-1]
        return line

    # Internal: get a response from the server, which may possibly
    # consist of multiple lines.  Return a single string with no
    # trailing CRLF.  If the response consists of multiple lines,
    # these are separated by '\n' characters in the string
    def getmultiline(self):
        line = self.getline()
        if line[3:4] == '-':
            code = line[:3]
            while 1:
                nextline = self.getline()
                line = line + ('\n' + nextline)
                if nextline[:3] == code and \
                        nextline[3:4] != '-':
                    break
        return line

    # Internal: get a response from the server.
    # Raise various errors if the response indicates an error
    def getresp(self):
        resp = self.getmultiline()
        if self.debugging: print '*resp*', self.sanitize(resp)
        self.lastresp = resp[:3]
        c = resp[:1]
        if c in ('1', '2', '3'):
            return resp
        if c == '4':
            raise error_temp, resp
        if c == '5':
            raise error_perm, resp
        raise error_proto, resp

    def voidresp(self):
        """Expect a response beginning with '2'."""
        resp = self.getresp()
        if resp[0] != '2':
            raise error_reply, resp
        return resp

    def abort(self):
        '''Abort a file transfer.  Uses out-of-band data.
        This does not follow the procedure from the RFC to send Telnet
        IP and Synch; that doesn't seem to work with the servers I've
        tried.  Instead, just send the ABOR command as OOB data.'''
        line = 'ABOR' + CRLF
        if self.debugging > 1: print '*put urgent*', self.sanitize(line)
        self.sock.sendall(line, MSG_OOB)
        resp = self.getmultiline()
        if resp[:3] not in ('426', '226'):
            raise error_proto, resp

    def sendcmd(self, cmd):
        '''Send a command and return the response.'''
        self.putcmd(cmd)
        return self.getresp()

    def voidcmd(self, cmd):
        """Send a command and expect a response beginning with '2'."""
        self.putcmd(cmd)
        return self.voidresp()

    def sendport(self, host, port):
        '''Send a PORT command with the current host and the given
        port number.
        '''
        hbytes = host.split('.')
        pbytes = [repr(port/256), repr(port%256)]
        bytes = hbytes + pbytes
        cmd = 'PORT ' + ','.join(bytes)
        return self.voidcmd(cmd)

    def sendeprt(self, host, port):
        '''Send a EPRT command with the current host and the given port number.'''
        af = 0
        if self.af == socket.AF_INET:
            af = 1
        if self.af == socket.AF_INET6:
            af = 2
        if af == 0:
            raise error_proto, 'unsupported address family'
        fields = ['', repr(af), host, repr(port), '']
        cmd = 'EPRT ' + '|'.join(fields)
        return self.voidcmd(cmd)

    def makeport(self):
        '''Create a new socket and send a PORT command for it.'''
        msg = "getaddrinfo returns an empty list"
        sock = None
        for res in socket.getaddrinfo(None, 0, self.af, socket.SOCK_STREAM, 0, socket.AI_PASSIVE):
            af, socktype, proto, canonname, sa = res
            try:
                sock = socket.socket(af, socktype, proto)
                sock.bind(sa)
            except socket.error as msg:
                if sock:
                    sock.close()
                sock = None
                continue
            break
        if not sock:
            raise socket.error, msg
        sock.listen(1)
        port = sock.getsockname()[1] # Get proper port
        host = self.sock.getsockname()[0] # Get proper host
        if self.af == socket.AF_INET:
            resp = self.sendport(host, port)
        else:
            resp = self.sendeprt(host, port)
        return sock

    def makepasv(self):
        if self.af == socket.AF_INET:
            host, port = parse227(self.sendcmd('PASV'))
        else:
            host, port = parse229(self.sendcmd('EPSV'), self.sock.getpeername())
        return host, port

    def ntransfercmd(self, cmd, rest=None):
        """Initiate a transfer over the data connection.

        If the transfer is active, send a port command and the
        transfer command, and accept the connection.  If the server is
        passive, send a pasv command, connect to it, and start the
        transfer command.  Either way, return the socket for the
        connection and the expected size of the transfer.  The
        expected size may be None if it could not be determined.

        Optional `rest' argument can be a string that is sent as the
        argument to a RESTART command.  This is essentially a server
        marker used to tell the server to skip over any data up to the
        given marker.
        """
        size = None
        if self.passiveserver:
            host, port = self.makepasv()
            af, socktype, proto, canon, sa = socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM)[0]
            conn = socket.socket(af, socktype, proto)
            conn.connect(sa)
            if rest is not None:
                self.sendcmd("REST %s" % rest)
            resp = self.sendcmd(cmd)
            # Some servers apparently send a 200 reply to
            # a LIST or STOR command, before the 150 reply
            # (and way before the 226 reply). This seems to
            # be in violation of the protocol (which only allows
            # 1xx or error messages for LIST), so we just discard
            # this response.
            if resp[0] == '2':
               resp = self.getresp()
            if resp[0] != '1':
                raise error_reply, resp
        else:
            sock = self.makeport()
            if rest is not None:
                self.sendcmd("REST %s" % rest)
            resp = self.sendcmd(cmd)
            # See above.
            if resp[0] == '2':
               resp = self.getresp()
            if resp[0] != '1':
                raise error_reply, resp
            conn, sockaddr = sock.accept()
        if resp[:3] == '150':
            # this is conditional in case we received a 125
            size = parse150(resp)
        return conn, size

    def transfercmd(self, cmd, rest=None):
        """Like ntransfercmd() but returns only the socket."""
        return self.ntransfercmd(cmd, rest)[0]

    def login(self, user = '', passwd = '', acct = ''):
        '''Login, default anonymous.'''
        if not user: user = 'anonymous'
        if not passwd: passwd = ''
        if not acct: acct = ''
        if user == 'anonymous' and passwd in ('', '-'):
            # If there is no anonymous ftp password specified
            # then we'll just use anonymous@
            # We don't send any other thing because:
            # - We want to remain anonymous
            # - We want to stop SPAM
            # - We don't want to let ftp sites to discriminate by the user,
            #   host or country.
            passwd = passwd + 'anonymous@'
        resp = self.sendcmd('USER ' + user)
        if resp[0] == '3': resp = self.sendcmd('PASS ' + passwd)
        if resp[0] == '3': resp = self.sendcmd('ACCT ' + acct)
        if resp[0] != '2':
            raise error_reply, resp
        return resp

    def retrbinary(self, cmd, callback, blocksize=8192, rest=None):
        """Retrieve data in binary mode.

        `cmd' is a RETR command.  `callback' is a callback function is
        called for each block.  No more than `blocksize' number of
        bytes will be read from the socket.  Optional `rest' is passed
        to transfercmd().

        A new port is created for you.  Return the response code.
        """
        self.voidcmd('TYPE I')
        conn = self.transfercmd(cmd, rest)
        while 1:
            data = conn.recv(blocksize)
            if not data:
                break
            callback(data)
        conn.close()
        return self.voidresp()

    def retrlines(self, cmd, callback = None):
        '''Retrieve data in line mode.
        The argument is a RETR or LIST command.
        The callback function (2nd argument) is called for each line,
        with trailing CRLF stripped.  This creates a new port for you.
        print_line() is the default callback.'''
        if callback is None: callback = print_line
        resp = self.sendcmd('TYPE A')
        conn = self.transfercmd(cmd)
        fp = conn.makefile('rb')
        while 1:
            line = fp.readline()
            if self.debugging > 2: print '*retr*', repr(line)
            if not line:
                break
            if line[-2:] == CRLF:
                line = line[:-2]
            elif line[-1:] == '\n':
                line = line[:-1]
            callback(line)
        fp.close()
        conn.close()
        return self.voidresp()

    def storbinary(self, cmd, fp, blocksize=8192):
        '''Store a file in binary mode.'''
        self.voidcmd('TYPE I')
        conn = self.transfercmd(cmd)
        while 1:
            buf = fp.read(blocksize)
            if not buf: break
            conn.sendall(buf)
        conn.close()
        return self.voidresp()

    def storlines(self, cmd, fp):
        '''Store a file in line mode.'''
        self.voidcmd('TYPE A')
        conn = self.transfercmd(cmd)
        while 1:
            buf = fp.readline()
            if not buf: break
            if buf[-2:] != CRLF:
                if buf[-1] in CRLF: buf = buf[:-1]
                buf = buf + CRLF
            conn.sendall(buf)
        conn.close()
        return self.voidresp()

    def acct(self, password):
        '''Send new account name.'''
        cmd = 'ACCT ' + password
        return self.voidcmd(cmd)

    def nlst(self, *args):
        '''Return a list of files in a given directory (default the current).'''
        cmd = 'NLST'
        for arg in args:
            cmd = cmd + (' ' + arg)
        files = []
        self.retrlines(cmd, files.append)
        return files

    def dir(self, *args):
        '''List a directory in long form.
        By default list current directory to stdout.
        Optional last argument is callback function; all
        non-empty arguments before it are concatenated to the
        LIST command.  (This *should* only be used for a pathname.)'''
        cmd = 'LIST'
        func = None
        if args[-1:] and type(args[-1]) != type(''):
            args, func = args[:-1], args[-1]
        for arg in args:
            if arg:
                cmd = cmd + (' ' + arg)
        self.retrlines(cmd, func)

    def rename(self, fromname, toname):
        '''Rename a file.'''
        resp = self.sendcmd('RNFR ' + fromname)
        if resp[0] != '3':
            raise error_reply, resp
        return self.voidcmd('RNTO ' + toname)

    def delete(self, filename):
        '''Delete a file.'''
        resp = self.sendcmd('DELE ' + filename)
        if resp[:3] in ('250', '200'):
            return resp
        elif resp[:1] == '5':
            raise error_perm, resp
        else:
            raise error_reply, resp

    def cwd(self, dirname):
        '''Change to a directory.'''
        if dirname == '..':
            try:
                return self.voidcmd('CDUP')
            except error_perm as msg:
                if msg.args[0][:3] != '500':
                    raise
        elif dirname == '':
            dirname = '.'  # does nothing, but could return error
        cmd = 'CWD ' + dirname
        return self.voidcmd(cmd)

    def size(self, filename):
        '''Retrieve the size of a file.'''
        # Note that the RFC doesn't say anything about 'SIZE'
        resp = self.sendcmd('SIZE ' + filename)
        if resp[:3] == '213':
            s = resp[3:].strip()
            try:
                return int(s)
            except (OverflowError, ValueError):
                return int(s)

    def mkd(self, dirname):
        '''Make a directory, return its full pathname.'''
        resp = self.sendcmd('MKD ' + dirname)
        return parse257(resp)

    def rmd(self, dirname):
        '''Remove a directory.'''
        return self.voidcmd('RMD ' + dirname)

    def pwd(self):
        '''Return current working directory.'''
        resp = self.sendcmd('PWD')
        return parse257(resp)

    def quit(self):
        '''Quit, and close the connection.'''
        resp = self.voidcmd('QUIT')
        self.close()
        return resp

    def close(self):
        '''Close the connection without assuming anything about it.'''
        if self.file:
            self.file.close()
            self.sock.close()
            self.file = self.sock = None


_150_re = None

def parse150(resp):
    '''Parse the '150' response for a RETR request.
    Returns the expected transfer size or None; size is not guaranteed to
    be present in the 150 message.
    '''
    if resp[:3] != '150':
        raise error_reply, resp
    global _150_re
    if _150_re is None:
        import re
        _150_re = re.compile("150 .* \((\d+) bytes\)", re.IGNORECASE)
    m = _150_re.match(resp)
    if not m:
        return None
    s = m.group(1)
    try:
        return int(s)
    except (OverflowError, ValueError):
        return int(s)


_227_re = None

def parse227(resp):
    '''Parse the '227' response for a PASV request.
    Raises error_proto if it does not contain '(h1,h2,h3,h4,p1,p2)'
    Return ('host.addr.as.numbers', port#) tuple.'''

    if resp[:3] != '227':
        raise error_reply, resp
    global _227_re
    if _227_re is None:
        import re
        _227_re = re.compile(r'(\d+),(\d+),(\d+),(\d+),(\d+),(\d+)')
    m = _227_re.search(resp)
    if not m:
        raise error_proto, resp
    numbers = m.groups()
    host = '.'.join(numbers[:4])
    port = (int(numbers[4]) << 8) + int(numbers[5])
    return host, port


def parse229(resp, peer):
    '''Parse the '229' response for a EPSV request.
    Raises error_proto if it does not contain '(|||port|)'
    Return ('host.addr.as.numbers', port#) tuple.'''

    if resp[:3] != '229':
        raise error_reply, resp
    left = resp.find('(')
    if left < 0: raise error_proto, resp
    right = resp.find(')', left + 1)
    if right < 0:
        raise error_proto, resp # should contain '(|||port|)'
    if resp[left + 1] != resp[right - 1]:
        raise error_proto, resp
    parts = resp[left + 1:right].split(resp[left+1])
    if len(parts) != 5:
        raise error_proto, resp
    host = peer[0]
    port = int(parts[3])
    return host, port


def parse257(resp):
    '''Parse the '257' response for a MKD or PWD request.
    This is a response to a MKD or PWD request: a directory name.
    Returns the directoryname in the 257 reply.'''

    if resp[:3] != '257':
        raise error_reply, resp
    if resp[3:5] != ' "':
        return '' # Not compliant to RFC 959, but UNIX ftpd does this
    dirname = ''
    i = 5
    n = len(resp)
    while i < n:
        c = resp[i]
        i = i+1
        if c == '"':
            if i >= n or resp[i] != '"':
                break
            i = i+1
        dirname = dirname + c
    return dirname


def print_line(line):
    '''Default retrlines callback to print a line.'''
    print line


def ftpcp(source, sourcename, target, targetname = '', type = 'I'):
    '''Copy file from one FTP-instance to another.'''
    if not targetname: targetname = sourcename
    type = 'TYPE ' + type
    source.voidcmd(type)
    target.voidcmd(type)
    sourcehost, sourceport = parse227(source.sendcmd('PASV'))
    target.sendport(sourcehost, sourceport)
    # RFC 959: the user must "listen" [...] BEFORE sending the
    # transfer request.
    # So: STOR before RETR, because here the target is a "user".
    treply = target.sendcmd('STOR ' + targetname)
    if treply[:3] not in ('125', '150'): raise error_proto  # RFC 959
    sreply = source.sendcmd('RETR ' + sourcename)
    if sreply[:3] not in ('125', '150'): raise error_proto  # RFC 959
    source.voidresp()
    target.voidresp()


class Netrc:
    """Class to parse & provide access to 'netrc' format files.

    See the netrc(4) man page for information on the file format.

    WARNING: This class is obsolete -- use module netrc instead.

    """
    __defuser = None
    __defpasswd = None
    __defacct = None

    def __init__(self, filename=None):
        if filename is None:
            if "HOME" in os.environ:
                filename = os.path.join(os.environ["HOME"],
                                        ".netrc")
            else:
                raise IOError, \
                      "specify file to load or set $HOME"
        self.__hosts = {}
        self.__macros = {}
        fp = open(filename, "r")
        in_macro = 0
        while 1:
            line = fp.readline()
            if not line: break
            if in_macro and line.strip():
                macro_lines.append(line)
                continue
            elif in_macro:
                self.__macros[macro_name] = tuple(macro_lines)
                in_macro = 0
            words = line.split()
            host = user = passwd = acct = None
            default = 0
            i = 0
            while i < len(words):
                w1 = words[i]
                if i+1 < len(words):
                    w2 = words[i + 1]
                else:
                    w2 = None
                if w1 == 'default':
                    default = 1
                elif w1 == 'machine' and w2:
                    host = w2.lower()
                    i = i + 1
                elif w1 == 'login' and w2:
                    user = w2
                    i = i + 1
                elif w1 == 'password' and w2:
                    passwd = w2
                    i = i + 1
                elif w1 == 'account' and w2:
                    acct = w2
                    i = i + 1
                elif w1 == 'macdef' and w2:
                    macro_name = w2
                    macro_lines = []
                    in_macro = 1
                    break
                i = i + 1
            if default:
                self.__defuser = user or self.__defuser
                self.__defpasswd = passwd or self.__defpasswd
                self.__defacct = acct or self.__defacct
            if host:
                if host in self.__hosts:
                    ouser, opasswd, oacct = \
                           self.__hosts[host]
                    user = user or ouser
                    passwd = passwd or opasswd
                    acct = acct or oacct
                self.__hosts[host] = user, passwd, acct
        fp.close()

    def get_hosts(self):
        """Return a list of hosts mentioned in the .netrc file."""
        return self.__hosts.keys()

    def get_account(self, host):
        """Returns login information for the named host.

        The return value is a triple containing userid,
        password, and the accounting field.

        """
        host = host.lower()
        user = passwd = acct = None
        if host in self.__hosts:
            user, passwd, acct = self.__hosts[host]
        user = user or self.__defuser
        passwd = passwd or self.__defpasswd
        acct = acct or self.__defacct
        return user, passwd, acct

    def get_macros(self):
        """Return a list of all defined macro names."""
        return self.__macros.keys()

    def get_macro(self, macro):
        """Return a sequence of lines which define a named macro."""
        return self.__macros[macro]



def test():
    '''Test program.
    Usage: ftp [-d] [-r[file]] host [-l[dir]] [-d[dir]] [-p] [file] ...

    -d dir
    -l list
    -p password
    '''

    if len(sys.argv) < 2:
        print test.__doc__
        sys.exit(0)

    debugging = 0
    rcfile = None
    while sys.argv[1] == '-d':
        debugging = debugging+1
        del sys.argv[1]
    if sys.argv[1][:2] == '-r':
        # get name of alternate ~/.netrc file:
        rcfile = sys.argv[1][2:]
        del sys.argv[1]
    host = sys.argv[1]
    ftp = FTP(host)
    ftp.set_debuglevel(debugging)
    userid = passwd = acct = ''
    try:
        netrc = Netrc(rcfile)
    except IOError:
        if rcfile is not None:
            sys.stderr.write("Could not open account file"
                             " -- using anonymous login.")
    else:
        try:
            userid, passwd, acct = netrc.get_account(host)
        except KeyError:
            # no account for host
            sys.stderr.write(
                    "No account -- using anonymous login.")
    ftp.login(userid, passwd, acct)
    for file in sys.argv[2:]:
        if file[:2] == '-l':
            ftp.dir(file[2:])
        elif file[:2] == '-d':
            cmd = 'CWD'
            if file[2:]: cmd = cmd + ' ' + file[2:]
            resp = ftp.sendcmd(cmd)
        elif file == '-p':
            ftp.set_pasv(not ftp.passiveserver)
        else:
            ftp.retrbinary('RETR ' + file, \
                           sys.stdout.write, 1024)
    ftp.quit()


if __name__ == '__main__':
    test()