ftplib.py

mallet是自然语言处理、机器学习领域的一个开源项目。

"""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 string

# 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, msg:
                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 `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 == '4':
            raise error_temp, resp
        if c == '5':
            raise error_perm, resp
        if c not in '123':
            raise error_proto, resp
        return 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 = [`port/256`, `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 = ['', `af`, host, `port`, '']
        cmd = 'EPRT ' + string.joinfields(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, 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)
            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)
            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 not callback: 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*', `line`
            if not line:
                break