Introduction

FTPHost instances can be created with the following call:

ftp_host = ftputil.FTPHost(server, user, password, account,
                           session_factory=ftplib.FTP)

The first four parameters are strings with the same meaning as for the FTP class in the ftplib module. Usually the account and session_factory arguments aren't needed though.

FTPHost objects can also be used in a with statement:

import ftputil

with ftputil.FTPHost(server, user, password) as ftp_host:
    print(ftp_host.listdir(ftp_host.curdir))

After the with block, the FTPHost instance and the associated FTP sessions will be closed automatically.

If something goes wrong during the FTPHost construction or in the body of the with statement, the instance is closed as well. Exceptions will be propagated (as with try ... finally).

Session factories

The keyword argument session_factory may be used to generate FTP connections with other factories than the default ftplib.FTP. For example, the standard library of Python 3 contains a class ftplib.FTP_TLS which extends ftplib.FTP to use an encrypted connection.

In fact, all positional and keyword arguments other than session_factory are passed to the factory to generate a new background session. This also happens for every remote file that is opened; see below.

This functionality of the constructor also allows to wrap ftplib.FTP objects to do something that wouldn't be possible with the ftplib.FTP constructor alone.

As an example, assume you want to connect to another than the default port, but ftplib.FTP only offers this by means of its connect method, not via its constructor. One solution is to use a custom class as a session factory:

import ftplib
import ftputil

EXAMPLE_PORT = 50001

class MySession(ftplib.FTP):

    def __init__(self, host, userid, password, port):
        """Act like ftplib.FTP's constructor but connect to another port."""
        ftplib.FTP.__init__(self)
        self.connect(host, port)
        self.login(userid, password)

# Try _not_ to use an _instance_ `MySession()` as factory, -
# use the class itself.
with ftputil.FTPHost(host, userid, password, port=EXAMPLE_PORT,
                     session_factory=MySession) as ftp_host:
    # Use `ftp_host` as usual.
    ...

On login, the format of the directory listings (needed for stat'ing files and directories) should be determined automatically. If not, please enter a ticket.

For the most common uses you don't need to create your own session factory class though. The ftputil.session module has a function session_factory that can create session factories for a variety of parameters:

session_factory(base_class=ftplib.FTP,
                port=21,
                use_passive_mode=None,
                encrypt_data_channel=True,
                debug_level=None)

with

• base_class is a base class to inherit a new session factory class from. By default, this is ftplib.FTP from the Python standard library.
• port is the command channel port. The default is 21, used in most FTP server configurations.
• use_passive_mode is either a boolean that determines whether passive mode should be used or None. None means to let the base class choose active or passive mode.
• encrypt_data_channel defines whether to encrypt the data channel for secure connections. This is only supported for the base classes ftplib.FTP_TLS and M2Crypto.ftpslib.FTP_TLS, otherwise the parameter is ignored.
• debug_level sets the debug level for FTP session instances. The semantics is defined by the base class. For example, a debug level of 2 causes the most verbose output for Python's ftplib.FTP class.

All of these parameters can be combined. For example, you could use

import ftplib

import ftputil
import ftputil.session


my_session_factory = ftputil.session.session_factory(
                       base_class=ftpslib.FTP_TLS,
                       port=31,
                       encrypt_data_channel=True,
                       debug_level=2)

with ftputil.FTPHost(server, user, password,
                     session_factory=my_session_factory) as ftp_host:
    ...

to create and use a session factory derived from ftplib.FTP_TLS that connects on command channel 31, will encrypt the data channel and print output for debug level 2.

Note: Generally, you can achieve everything you can do with ftputil.session.session_factory with an explicit session factory as described at the start of this section. However, the class M2Crypto.ftpslib.FTP_TLS has a limitation so that you can't use it with ftputil out of the box. The function session_factory contains a workaround for this limitation. For details refer to this ticket.

Attributes

• curdir, pardir, sep

  are strings which denote the current and the parent directory on the remote server. sep holds the path separator. Though RFC 959 (File Transfer Protocol) notes that these values may depend on the FTP server implementation, the Unix variants seem to work well in practice, even for non-Unix servers.

  Nevertheless, it's recommended that you don't hardcode these values for remote paths, but use FTPHost.path as you would use os.path to write platform-independent Python code for local filesystems. Keep in mind that most, but not all, arguments of FTPHost methods refer to remote directories or files. For example, in FTPHost.upload, the first argument is a local path and the second a remote path. Both of these should use their respective path separators.

Remote file system navigation

• getcwd()

  returns the absolute current directory on the remote host. This method works like os.getcwd.

• chdir(directory)

  sets the current directory on the FTP server. This resembles os.chdir, as you may have expected.

Uploading and downloading files

• upload(source, target, callback=None)

  copies a local source file (given by a filename, i. e. a string) to the remote host under the name target. Both source and target may be absolute paths or relative to their corresponding current directory (on the local or the remote host, respectively).

  The file content is always transferred in binary mode.

  The callback, if given, will be invoked for each transferred chunk of data:

  callback(chunk)
  

  where chunk is a bytestring. An example usage of a callback method is to display a progress indicator.

• download(source, target, callback=None)

  performs a download from the remote source file to a local target file. Both source and target are strings. See the description of upload for more details.

• upload_if_newer(source, target, callback=None)

  is similar to the upload method. The only difference is that the upload is only invoked if the time of the last modification for the source file is more recent than that of the target file or the target doesn't exist at all. The check for the last modification time considers the precision of the timestamps and transfers a file "if in doubt". Consequently the code

  ftp_host.upload_if_newer("source_file", "target_file")
  time.sleep(10)
  ftp_host.upload_if_newer("source_file", "target_file")
  

  might upload the file again if the timestamp of the target file is precise up to a minute, which is typically the case because the remote datetime is determined by parsing a directory listing from the server. To avoid unnecessary transfers, wait at least a minute between calls of upload_if_newer for the same file. If it still seems that a file is uploaded unnecessarily (or not when it should), read the subsection on time shift settings.

  If an upload actually happened, the return value of upload_if_newer is a True, else False.

  Note that the method only checks the existence and/or the modification time of the source and target file; it doesn't compare any other file properties, say, the file size.

  This also means that if a transfer is interrupted, the remote file will have a newer modification time than the local file, and thus the transfer won't be repeated if upload_if_newer is used a second time. There are at least two possibilities after a failed upload:

  • use upload instead of upload_if_newer, or
  • remove the incomplete target file with FTPHost.remove, then use upload or upload_if_newer to transfer it again.

• download_if_newer(source, target, callback=None)

  corresponds to upload_if_newer but performs a download from the server to the local host. Read the descriptions of download and upload_if_newer for more information. If a download actually happened, the return value is True, else False.

Time zone correction

For upload_if_newer and download_if_newer to work correctly, the time zone of the server must be taken into account. By default, ftputil assumes that the timestamps in server listings are in UTC.

• set_time_shift(time_shift)

  sets the so-called time shift value, measured in seconds. The time shift here is defined as the difference between the time used in server listings and UTC.

  time_shift = server_time - utc_time
  

  For example, a server in Berlin/Germany set to the local time (currently UTC+03:00), would require a time shift value of 3 * 3600.0 = 10800.0 seconds to be handled correctly by ftputil's upload_if_newer and download_if_newer, as well as the stat and lstat calls.

  Note that servers don't necessarily send their file system listings in their local time zone. Some use UTC, which actually makes sense because UTC doesn't lead to an ambiguity when there's a switch back from the daylight saving time to the "normal" time of the server location.

  If the time shift value is invalid, for example its absolute value is larger than 24 hours, a TimeShiftError is raised.

  Note

  Versions of ftputil before 4.0.0 used a different definition of "time shift", server_time - local_client_time.

  This had the advantage that the default of 0.0 would be correct if the server was set to the same time zone as the client where ftputil runs. On the other hand, this approach meant that the time shift depended on two time zones, not only the one used on the server side. This could be confusing if server and client didn't use the same time zone.

  See also synchronize_times for a way to set the time shift with a simple method call. If you can't use synchronize_times and the server uses the same time zone as the client, you can set the time shift value with

  set_time_shift(
    round( (datetime.datetime.now() - datetime.datetime.utcnow()).seconds, -2 )
  )
  

• time_shift()

  returns the currently-set time shift value. See set_time_shift above for its definition.

• synchronize_times()

  synchronizes the local times of the server and the client, so that upload_if_newer and download_if_newer work as expected, even if the client and the server use different time zones. For this to work, all of the following conditions must be true:

  • The connection between server and client is established.
  • The client has write access to the directory that is current when synchronize_times is called.

  If you can't fulfill these conditions, you can nevertheless set the time shift value explicitly with set_time_shift. Trying to call synchronize_times if the above conditions aren't met results in a TimeShiftError exception.

Creating and removing directories

• mkdir(path, [mode])

  makes the given directory on the remote host. This does not construct "intermediate" directories that don't already exist. The mode parameter is ignored; this is for compatibility with os.mkdir if an FTPHost object is passed into a function instead of the os module. See the explanation in the subsection Exception hierarchy.

• makedirs(path, [mode], exist_ok=False)

  works similar to mkdir (see above), but also makes intermediate directories like os.makedirs. The mode parameter is only there for compatibility with os.makedirs and is ignored.

  exist_ok controls whether the existence of any directory but the last in the path should be considered an error. If the default False is used or passed to makedirs, ftputil will raise a PermanentError if any directory but the last already exists.

• rmdir(path)

  removes the given remote directory. If it's not empty, raise a PermanentError.

• rmtree(path, ignore_errors=False, onerror=None)

  removes the given remote, possibly non-empty, directory tree. The interface of this method is rather complex, in favor of compatibility with shutil.rmtree.

  If ignore_errors is set to a true value, errors are ignored. If ignore_errors is a false value and onerror isn't set, all exceptions occurring during the tree iteration and processing are raised. These exceptions are all of type PermanentError.

  To distinguish between different kinds of errors, pass in a callable for onerror. This callable must accept three arguments: func, path and exc_info. func is a bound method object, for example your_host_object.listdir. path is the path that was the recent argument of the respective method (listdir, remove, rmdir). exc_info is the exception info as it is gotten from sys.exc_info.

  The code of rmtree is taken from Python's shutil module and adapted for ftputil.

Removing files and links

• remove(path)

  removes a file or link on the remote host, similar to os.remove.

• unlink(path)

  is an alias for remove.

Retrieving information about directories, files and links

• listdir(path)

  returns a list containing the names of the files and directories in the given path, similar to os.listdir. The special names . and .. are not in the list.

The methods lstat and stat (and some others) rely on the directory listing format used by the FTP server. When connecting to a host, FTPHost's constructor tries to guess the right format, which succeeds in most cases. However, if you get strange results or ParserError exceptions by a mere lstat call, please enter a ticket.

If lstat or stat give wrong modification dates or times, look at the methods that deal with time zone differences (time zone correction).

• lstat(path)

  returns an object similar to that from os.lstat. This is a kind of tuple with additional attributes; see the documentation of the os module for details.

  The result is derived by parsing the output of a LIST command on the server. Therefore, the result from FTPHost.lstat can not contain more information than the received text. In particular:

  • User and group ids can only be determined as strings, not as numbers, and that only if the server supplies them. This is usually the case with Unix servers but maybe not for other FTP servers.

  • Values for the time of the last modification may be rough, depending on the information from the server. For timestamps older than a year, this usually means that the precision of the modification timestamp value is not better than a day. For newer files, the information may be accurate to a minute.

    If the time of the last modification is before the epoch (usually 1970-01-01 UTC), set the time of the last modification to 0.0.

  • Links can only be recognized on servers that provide this information in the LIST output.

  • Stat attributes that can't be determined at all are set to

    None. For example, a line of a directory listing may not contain the date/time of a directory's last modification.

  • There's a special problem with stat'ing the root directory. (Stat'ing things in the root directory is fine though.) In this case, a RootDirError is raised. This has to do with the algorithm used by (l)stat, and I know of no approach which mends this problem.

  Currently, ftputil recognizes the common Unix-style and Microsoft/DOS-style directory formats. If you need to parse output from another server type, please write to the ftputil mailing list. You may consider writing your own parser.

• stat(path)

  returns stat information also for files which are pointed to by a link. This method follows multiple links until a regular file or directory is found. If an infinite link chain is encountered or the target of the last link in the chain doesn't exist, a PermanentError is raised.

  The limitations of the lstat method also apply to stat.

FTPHost objects contain an attribute named path, similar to os.path. The following methods can be applied to the remote host with the same semantics as for os.path:

abspath(path)
basename(path)
commonprefix(path_list)
dirname(path)
exists(path)
getmtime(path)
getsize(path)
isabs(path)
isdir(path)
isfile(path)
islink(path)
join(path1, path2, ...)
normcase(path)
normpath(path)
split(path)
splitdrive(path)
splitext(path)
walk(path, func, arg)

Like Python's counterparts under os.path, ftputil's is... methods return False if they can't find the path given by their argument.

Local caching of file system information

Many of the above methods need access to the remote file system to obtain data on directories and files. To get the most recent data, each call to lstat, stat, exists, getmtime etc. would require to fetch a directory listing from the server, which can make the program very slow. This effect is more pronounced for operations which mostly scan the file system rather than transferring file data.

For this reason, ftputil by default saves the results from directory listings locally and reuses those results. This reduces network accesses and so speeds up the software a lot. However, since data is more rarely fetched from the server, the risk of obsolete data also increases. This will be discussed below.

Caching can be controlled -- if necessary at all -- via the stat_cache object in an FTPHost's namespace. For example, after calling

ftp_host = ftputil.FTPHost(host, user, password)

the cache can be accessed as ftp_host.stat_cache.

While ftputil usually manages the cache quite well, there are two possible reasons for modifying cache parameters.

The first is when the number of possible entries is too low. You may notice that when you are processing very large directories and the program becomes much slower than before. It's common for code to read a directory with listdir and then process the found directories and files. This can also happen implicitly by a call to FTPHost.walk. Since version 2.6 ftputil automatically increases the cache size if directories with more entries than the current maximum cache size are to be scanned. Most of the time, this works fine.

However, if you need access to stat data for several directories at the same time, you may need to increase the cache explicitly. This is done by the resize method:

ftp_host.stat_cache.resize(20000)

where the argument is the maximum number of lstat results to store (the default is 5000, in versions before 2.6 it was 1000). Note that each path on the server, e. g. "/home/schwa/some_dir", corresponds to a single cache entry. Methods like exists or getmtime all derive their results from a previously fetched lstat result.

The value 5000 above means that the cache will hold at most 5000 entries (unless increased automatically by an explicit or implicit listdir call, see above). If more are about to be stored, the entries which haven't been used for the longest time will be deleted to make place for newer entries.

The second possible reason to change the cache parameters is to avoid stale cache data. Caching is so effective because it reduces network accesses. This can also be a disadvantage if the file system data on the remote server changes after a stat result has been retrieved; the client, when looking at the cached stat data, will use obsolete information.

There are two potential ways to get such out-of-date stat data. The first happens when an FTPHost instance modifies a file path for which it has a cache entry, e. g. by calling remove or rmdir. Such changes are handled transparently; the path will be deleted from the cache. A different matter are changes unknown to the FTPHost object which inspects its cache. Obviously, for example, these are changes by programs running on the remote host. On the other hand, cache inconsistencies can also occur if two FTPHost objects change a file system simultaneously:

with (
  ftputil.FTPHost(server, user1, password1) as ftp_host1,
  ftputil.FTPHost(server, user1, password1) as ftp_host2
):
    stat_result1 = ftp_host1.stat("some_file")
    stat_result2 = ftp_host2.stat("some_file")
    ftp_host2.remove("some_file")
    # `ftp_host1` will still see the obsolete cache entry!
    print(ftp_host1.stat("some_file"))
    # Will raise an exception since an `FTPHost` object
    # knows of its own changes.
    print(ftp_host2.stat("some_file"))

At first sight, it may appear to be a good idea to have a shared cache among several FTPHost objects. After some thinking, this turns out to be very error-prone. For example, it won't help with different processes using ftputil. So, if you have to deal with concurrent write/read accesses to a server, you have to handle them explicitly.

The most useful tool for this is the invalidate method. In the example above, it could be used like this:

with (
  ftputil.FTPHost(server, user1, password1) as ftp_host1,
  ftputil.FTPHost(server, user1, password1) as ftp_host2
):
    stat_result1 = ftp_host1.stat("some_file")
    stat_result2 = ftp_host2.stat("some_file")
    ftp_host2.remove("some_file")
    # Invalidate using an absolute path.
    absolute_path = ftp_host1.path.abspath(
                      ftp_host1.path.join(ftp_host1.getcwd(), "some_file"))
    ftp_host1.stat_cache.invalidate(absolute_path)
    # Will now raise an exception as it should.
    print(ftp_host1.stat("some_file"))
    # Would raise an exception since an `FTPHost` object
    # knows of its own changes, even without `invalidate`.
    print(ftp_host2.stat("some_file"))

The method invalidate can be used on any absolute path, be it a directory, a file or a link.

By default, the cache entries (if not replaced by newer ones) are stored for an infinite time. That is, if you start your Python process using ftputil and let it run for three days a stat call may still access cache data that old. To avoid this, you can set the max_age attribute:

with ftputil.FTPHost(server, user, password) as ftp_host:
    ftp_host.stat_cache.max_age = 60 * 60  # = 3600 seconds

This sets the maximum age of entries in the cache to an hour. This means any entry older won't be retrieved from the cache but its data instead fetched again from the remote host and then again stored for up to an hour. To reset max_age to the default of unlimited age, i. e. cache entries never expire, use None as value.

If you are certain that the cache will be in the way, you can disable and later re-enable it completely with disable and enable:

with ftputil.FTPHost(server, user, password) as ftp_host:
    ftp_host.stat_cache.disable()
    ...
    ftp_host.stat_cache.enable()

During that time, the cache won't be used; all data will be fetched from the network. After enabling the cache again, its entries will be the same as when the cache was disabled, that is, entries won't get updated with newer data during this period. Note that even when the cache is disabled, the file system data in the code can become inconsistent:

with ftputil.FTPHost(server, user, password) as ftp_host:
    ftp_host.stat_cache.disable()
    if ftp_host.path.exists("some_file"):
        mtime = ftp_host.path.getmtime("some_file")

In that case, the file some_file may have been removed by another process between the calls to exists and getmtime!

Iteration over directories

• walk(top, topdown=True, onerror=None, followlinks=False)

  iterates over a directory tree, similar to os.walk. Actually, FTPHost.walk uses the code from Python with just the necessary modifications, so see the linked documentation.

• path.walk(path, func, arg)

  Similar to os.path.walk, the walk method in FTPHost.path can be used, though FTPHost.walk is probably easier to use.

Other methods

• close()

  closes the connection to the remote host. After this, no more interaction with the FTP server is possible with this FTPHost object. Usually you don't need to close an FTPHost instance with close if you set up the instance in a with statement.

• rename(source, target)

  renames the source file (or directory) on the FTP server.

• chmod(path, mode)

  sets the access mode (permission flags) for the given path. The mode is an integer as returned for the mode by the stat and lstat methods. Be careful: Usually, mode values are written as octal numbers, for example 0755 to make a directory readable and writable for the owner, but not writable for the group and others. If you want to use such octal values, rely on Python's support for them:

  ftp_host.chmod("some_directory", 0o755)
  

  Not all FTP servers support the chmod command. In case of an exception, how do you know if the path doesn't exist or if the command itself is invalid? If the FTP server complies with RFC 959, it should return a status code 502 if the SITE CHMOD command isn't allowed. ftputil maps this special error response to a CommandNotImplementedError which is derived from PermanentError.

  So you need to code like this:

  with ftputil.FTPHost(server, user, password) as ftp_host:
      try:
          ftp_host.chmod("some_file", 0o644)
      except ftputil.error.CommandNotImplementedError:
          # `chmod` not supported
          ...
      except ftputil.error.PermanentError:
          # Possibly a non-existent file
          ...
  

  Because the CommandNotImplementedError is more specific, you have to test for it first.

• copyfileobj(source, target, length=64*1024)

  copies the contents from the file-like object source to the file-like object target. The only difference to shutil.copyfileobj is the default buffer size. Note that arbitrary file-like objects can be used as arguments (e. g. local files, remote FTP files).

  However, the interfaces of source and target have to match; the string type read from source must be an accepted string type when written to target. For example, if you open source in Python 3 as a local text file and target as a remote file object in binary mode, the transfer will fail since source.read gives unicode strings (str) whereas target.write only accepts byte strings (bytes).

  See File-like objects for the construction and use of remote file-like objects.

• set_parser(parser)

  sets a custom parser for FTP directories. Note that you have to pass in a parser instance, not the class.

  An extra section shows how to write own parsers if the default parsers in ftputil don't work for you.

• keep_alive()

  attempts to keep the connection to the remote server active in order to prevent timeouts from happening. This method is primarily intended to keep the underlying FTP connection of an FTPHost object alive while a file is uploaded or downloaded. This will require either an extra thread while the upload or download is in progress or calling keep_alive from a callback function.

  The keep_alive method won't help if the connection has already timed out. In this case, a ftputil.error.TemporaryError is raised.

  If you want to use this method, keep in mind that FTP servers define a timeout for a reason. A timeout prevents running out of server connections because of clients that never disconnect on their own.

  Note that the keep_alive method does not affect the "hidden" FTP child connections established by FTPHost.open (see section FTPHost instances vs. FTP connections for details). You can't use keep_alive to avoid a timeout in a stalling transfer like this:

  with ftputil.FTPHost(server, userid, password) as ftp_host:
      with ftp_host.open("some_remote_file", "rb") as fobj:
          data = fobj.read(100)
          # _Futile_ attempt to avoid file connection timeout.
          for i in range(15):
              time.sleep(60)
              ftp_host.keep_alive()
          # Will raise an `ftputil.error.TemporaryError`.
          data += fobj.read()
  

Basics

FTPFile objects are returned by a call to FTPHost.open; never use the FTPFile constructor directly.

The APIs for remote file-like objects is modeled after the APIs of the built-in open function and its return value.

• FTPHost.open(path, mode="r", buffering=None, encoding=None, errors=None, newline=None, rest=None)

  returns a file-like object that refers to the path on the remote host. This path may be absolute or relative to the current directory on the remote host (this directory can be determined with the getcwd method). As with local file objects, the default mode is "r", i. e. reading text files. Valid modes are "r", "rb", "w", and "wb".

  If a file is opened in binary mode, you must not specify an encoding. On the other hand, if you open a file in text mode, an encoding is used. By default, this is the return value of locale.getpreferredencoding, but you can (and probably should) specify a distinct encoding.

  If you open a file in binary mode, the read and write operations use bytes objects. That is, read operations return bytes and write operations only accept bytes.

  Similarly, text files always work with strings (str). Here, read operations return string and write operations only accept strings.

  The arguments buffering, errors and newline have the same semantics as in open.

  If the file is opened in binary mode, you may pass 0 or a positive integer for the rest argument. The argument is passed to the underlying FTP session instance (for example an instance of ftplib.FTP) to start reading or writing at the given byte offset. For example, if a remote file contains the letters "abcdef" in ASCII encoding, rest=3 will start reading at "d".

  Warning

  If you pass rest values which point after the file, the behavior is undefined and may even differ from one FTP server to another. Therefore, use the rest argument only for error recovery in case of interrupted transfers. You need to keep track of the transferred data so that you can provide a valid rest argument for a resumed transfer.

FTPHost.open can also be used in a with statement:

import ftputil

with ftputil.FTPHost(...) as ftp_host:
    ...
    with ftp_host.open("new_file", "w", encoding="utf8") as fobj:
        fobj.write("This is some text.")

At the end of the with block, the remote file will be closed automatically.

If something goes wrong during the construction of the file or in the body of the with statement, the file will be closed as well. Exceptions will be propagated as with try ... finally.