Python3 shutil模块

　　平时我们总会用到复制文件的命令，Python中自带了相应模块，那就是shutil模块，下面是shutil模块的分析及用法。

　　1、copyfileobj(fsrc, fdst, length=16*1024)

　　将源文件拷贝到目标文件，每次拷贝16KB。这个方法中，原文件及目标文件并没有进行关闭，所以这是一个基本方法，并不经常使用。

def copyfileobj(fsrc, fdst, length=16*1024):
    """copy data from file-like object fsrc to file-like object fdst"""
    while 1:
        buf = fsrc.read(length)
        if not buf:
            break
        fdst.write(buf)

　　2、copyfile(src, dst, *, follow_symlinks=True)

　　拷贝源文件到目标文件，如果follow_symlinks项没有设定并且源文件是一个链接，则只拷贝连接，不拷贝指向的文件。

def copyfile(src, dst, *, follow_symlinks=True):
    """Copy data from src to dst.

    If follow_symlinks is not set and src is a symbolic link, a new
    symlink will be created instead of copying the file it points to.

    """
    if _samefile(src, dst):
        raise SameFileError("{!r} and {!r} are the same file".format(src, dst))

    for fn in [src, dst]:
        try:
            st = os.stat(fn)
        except OSError:
            # File most likely does not exist
            pass
        else:
            # XXX What about other special files? (sockets, devices...)
            if stat.S_ISFIFO(st.st_mode):
                raise SpecialFileError("`%s` is a named pipe" % fn)

    if not follow_symlinks and os.path.islink(src):
        os.symlink(os.readlink(src), dst)
    else:
        with open(src, 'rb') as fsrc:
            with open(dst, 'wb') as fdst:
                copyfileobj(fsrc, fdst)
    return dst

　　3、copymode(src, dst, *, follow_symlinks=True)

　　仅拷贝文件权限，如果follow_symlinks项没有设定并且两个文件都是链接，如果lchmod（比如linux系统）不可用，那么这个方法也不可用。

def copymode(src, dst, *, follow_symlinks=True):
    """Copy mode bits from src to dst.

    If follow_symlinks is not set, symlinks aren't followed if and only
    if both `src` and `dst` are symlinks.  If `lchmod` isn't available
    (e.g. Linux) this method does nothing.

    """
    if not follow_symlinks and os.path.islink(src) and os.path.islink(dst):
        if hasattr(os, 'lchmod'):
            stat_func, chmod_func = os.lstat, os.lchmod
        else:
            return
    elif hasattr(os, 'chmod'):
        stat_func, chmod_func = os.stat, os.chmod
    else:
        return

    st = stat_func(src)
    chmod_func(dst, stat.S_IMODE(st.st_mode))

　　4、copystat(src, dst, *, follow_symlinks=True)

　　拷贝状态信息

def copystat(src, dst, *, follow_symlinks=True):
    """Copy all stat info (mode bits, atime, mtime, flags) from src to dst.

    If the optional flag `follow_symlinks` is not set, symlinks aren't followed if and
    only if both `src` and `dst` are symlinks.

    """
    def _nop(*args, ns=None, follow_symlinks=None):
        pass

    # follow symlinks (aka don't not follow symlinks)
    follow = follow_symlinks or not (os.path.islink(src) and os.path.islink(dst))
    if follow:
        # use the real function if it exists
        def lookup(name):
            return getattr(os, name, _nop)
    else:
        # use the real function only if it exists
        # *and* it supports follow_symlinks
        def lookup(name):
            fn = getattr(os, name, _nop)
            if fn in os.supports_follow_symlinks:
                return fn
            return _nop

    st = lookup("stat")(src, follow_symlinks=follow)
    mode = stat.S_IMODE(st.st_mode)
    lookup("utime")(dst, ns=(st.st_atime_ns, st.st_mtime_ns),
        follow_symlinks=follow)
    try:
        lookup("chmod")(dst, mode, follow_symlinks=follow)
    except NotImplementedError:
        # if we got a NotImplementedError, it's because
        #   * follow_symlinks=False,
        #   * lchown() is unavailable, and
        #   * either
        #       * fchownat() is unavailable or
        #       * fchownat() doesn't implement AT_SYMLINK_NOFOLLOW.
        #         (it returned ENOSUP.)
        # therefore we're out of options--we simply cannot chown the
        # symlink.  give up, suppress the error.
        # (which is what shutil always did in this circumstance.)
        pass
    if hasattr(st, 'st_flags'):
        try:
            lookup("chflags")(dst, st.st_flags, follow_symlinks=follow)
        except OSError as why:
            for err in 'EOPNOTSUPP', 'ENOTSUP':
                if hasattr(errno, err) and why.errno == getattr(errno, err):
                    break
            else:
                raise
    _copyxattr(src, dst, follow_symlinks=follow)

　　5、copy(src, dst, *, follow_symlinks=True)

　　拷贝文件及权限

def copy(src, dst, *, follow_symlinks=True):
    """Copy data and mode bits ("cp src dst"). Return the file's destination.

    The destination may be a directory.

    If follow_symlinks is false, symlinks won't be followed. This
    resembles GNU's "cp -P src dst".

    If source and destination are the same file, a SameFileError will be
    raised.

    """
    if os.path.isdir(dst):
        dst = os.path.join(dst, os.path.basename(src))
    copyfile(src, dst, follow_symlinks=follow_symlinks)
    copymode(src, dst, follow_symlinks=follow_symlinks)
    return dst

　　6、copy2(src, dst, *, follow_symlinks=True)

 　　拷贝文件和状态信息

def copy2(src, dst, *, follow_symlinks=True):
    """Copy data and all stat info ("cp -p src dst"). Return the file's
    destination."

    The destination may be a directory.

    If follow_symlinks is false, symlinks won't be followed. This
    resembles GNU's "cp -P src dst".

    """
    if os.path.isdir(dst):
        dst = os.path.join(dst, os.path.basename(src))
    copyfile(src, dst, follow_symlinks=follow_symlinks)
    copystat(src, dst, follow_symlinks=follow_symlinks)
    return dst

　　7、ignore_patterns(*patterns)

 　　忽略特定文件。与递归拷贝等进行连用去除不需要操作的文件。

def ignore_patterns(*patterns):
    """Function that can be used as copytree() ignore parameter.

    Patterns is a sequence of glob-style patterns
    that are used to exclude files"""
    def _ignore_patterns(path, names):
        ignored_names = []
        for pattern in patterns:
            ignored_names.extend(fnmatch.filter(names, pattern))
        return set(ignored_names)
    return _ignore_patterns

　　8、copytree(src, dst, symlinks=False, ignore=None, copy_function=copy2,ignore_dangling_symlinks=False)

 　　递归拷贝文件

def copytree(src, dst, symlinks=False, ignore=None, copy_function=copy2,
             ignore_dangling_symlinks=False):
    """Recursively copy a directory tree.

    The destination directory must not already exist.
    If exception(s) occur, an Error is raised with a list of reasons.

    If the optional symlinks flag is true, symbolic links in the
    source tree result in symbolic links in the destination tree; if
    it is false, the contents of the files pointed to by symbolic
    links are copied. If the file pointed by the symlink doesn't
    exist, an exception will be added in the list of errors raised in
    an Error exception at the end of the copy process.

    You can set the optional ignore_dangling_symlinks flag to true if you
    want to silence this exception. Notice that this has no effect on
    platforms that don't support os.symlink.

    The optional ignore argument is a callable. If given, it
    is called with the `src` parameter, which is the directory
    being visited by copytree(), and `names` which is the list of
    `src` contents, as returned by os.listdir():

        callable(src, names) -> ignored_names

    Since copytree() is called recursively, the callable will be
    called once for each directory that is copied. It returns a
    list of names relative to the `src` directory that should
    not be copied.

    The optional copy_function argument is a callable that will be used
    to copy each file. It will be called with the source path and the
    destination path as arguments. By default, copy2() is used, but any
    function that supports the same signature (like copy()) can be used.

    """
    names = os.listdir(src)
    if ignore is not None:
        ignored_names = ignore(src, names)
    else:
        ignored_names = set()

    os.makedirs(dst)
    errors = []
    for name in names:
        if name in ignored_names:
            continue
        srcname = os.path.join(src, name)
        dstname = os.path.join(dst, name)
        try:
            if os.path.islink(srcname):
                linkto = os.readlink(srcname)
                if symlinks:
                    # We can't just leave it to `copy_function` because legacy
                    # code with a custom `copy_function` may rely on copytree
                    # doing the right thing.
                    os.symlink(linkto, dstname)
                    copystat(srcname, dstname, follow_symlinks=not symlinks)
                else:
                    # ignore dangling symlink if the flag is on
                    if not os.path.exists(linkto) and ignore_dangling_symlinks:
                        continue
                    # otherwise let the copy occurs. copy2 will raise an error
                    if os.path.isdir(srcname):
                        copytree(srcname, dstname, symlinks, ignore,
                                 copy_function)
                    else:
                        copy_function(srcname, dstname)
            elif os.path.isdir(srcname):
                copytree(srcname, dstname, symlinks, ignore, copy_function)
            else:
                # Will raise a SpecialFileError for unsupported file types
                copy_function(srcname, dstname)
        # catch the Error from the recursive copytree so that we can
        # continue with other files
        except Error as err:
            errors.extend(err.args[0])
        except OSError as why:
            errors.append((srcname, dstname, str(why)))
    try:
        copystat(src, dst)
    except OSError as why:
        # Copying file access times may fail on Windows
        if getattr(why, 'winerror', None) is None:
            errors.append((src, dst, str(why)))
    if errors:
        raise Error(errors)
    return dst

# version vulnerable to race conditions

　　9、rmtree(path, ignore_errors=False, onerror=None)

 　　递归的删除文件

def rmtree(path, ignore_errors=False, onerror=None):
    """Recursively delete a directory tree.

    If ignore_errors is set, errors are ignored; otherwise, if onerror
    is set, it is called to handle the error with arguments (func,
    path, exc_info) where func is platform and implementation dependent;
    path is the argument to that function that caused it to fail; and
    exc_info is a tuple returned by sys.exc_info().  If ignore_errors
    is false and onerror is None, an exception is raised.

    """
    if ignore_errors:
        def onerror(*args):
            pass
    elif onerror is None:
        def onerror(*args):
            raise
    if _use_fd_functions:
        # While the unsafe rmtree works fine on bytes, the fd based does not.
        if isinstance(path, bytes):
            path = os.fsdecode(path)
        # Note: To guard against symlink races, we use the standard
        # lstat()/open()/fstat() trick.
        try:
            orig_st = os.lstat(path)
        except Exception:
            onerror(os.lstat, path, sys.exc_info())
            return
        try:
            fd = os.open(path, os.O_RDONLY)
        except Exception:
            onerror(os.lstat, path, sys.exc_info())
            return
        try:
            if os.path.samestat(orig_st, os.fstat(fd)):
                _rmtree_safe_fd(fd, path, onerror)
                try:
                    os.rmdir(path)
                except OSError:
                    onerror(os.rmdir, path, sys.exc_info())
            else:
                try:
                    # symlinks to directories are forbidden, see bug #1669
                    raise OSError("Cannot call rmtree on a symbolic link")
                except OSError:
                    onerror(os.path.islink, path, sys.exc_info())
        finally:
            os.close(fd)
    else:
        return _rmtree_unsafe(path, onerror)

　　10、move(src, dst, copy_function=copy2)

 　　递归的移动文件

def move(src, dst, copy_function=copy2):
    """Recursively move a file or directory to another location. This is
    similar to the Unix "mv" command. Return the file or directory's
    destination.

    If the destination is a directory or a symlink to a directory, the source
    is moved inside the directory. The destination path must not already
    exist.

    If the destination already exists but is not a directory, it may be
    overwritten depending on os.rename() semantics.

    If the destination is on our current filesystem, then rename() is used.
    Otherwise, src is copied to the destination and then removed. Symlinks are
    recreated under the new name if os.rename() fails because of cross
    filesystem renames.

    The optional `copy_function` argument is a callable that will be used
    to copy the source or it will be delegated to `copytree`.
    By default, copy2() is used, but any function that supports the same
    signature (like copy()) can be used.

    A lot more could be done here...  A look at a mv.c shows a lot of
    the issues this implementation glosses over.

    """
    real_dst = dst
    if os.path.isdir(dst):
        if _samefile(src, dst):
            # We might be on a case insensitive filesystem,
            # perform the rename anyway.
            os.rename(src, dst)
            return

        real_dst = os.path.join(dst, _basename(src))
        if os.path.exists(real_dst):
            raise Error("Destination path '%s' already exists" % real_dst)
    try:
        os.rename(src, real_dst)
    except OSError:
        if os.path.islink(src):
            linkto = os.readlink(src)
            os.symlink(linkto, real_dst)
            os.unlink(src)
        elif os.path.isdir(src):
            if _destinsrc(src, dst):
                raise Error("Cannot move a directory '%s' into itself"
                            " '%s'." % (src, dst))
            copytree(src, real_dst, copy_function=copy_function,
                     symlinks=True)
            rmtree(src)
        else:
            copy_function(src, real_dst)
            os.unlink(src)
    return real_dst

　　11、get_archive_formats()

　　返回用于存档支持的格式

def get_archive_formats():
    """Returns a list of supported formats for archiving and unarchiving.

    Each element of the returned sequence is a tuple (name, description)
    """
    formats = [(name, registry[2]) for name, registry in
               _ARCHIVE_FORMATS.items()]
    formats.sort()
    return formats

 　　12、register_archive_format(name, function, extra_args=None, description='')

　　注册档案格式（没有使用过），可以自定义压缩种类、调用程序以及相关描述。调用get_archive_formats()会返回相应数据。

def register_archive_format(name, function, extra_args=None, description=''):
    """Registers an archive format.

    name is the name of the format. function is the callable that will be
    used to create archives. If provided, extra_args is a sequence of
    (name, value) tuples that will be passed as arguments to the callable.
    description can be provided to describe the format, and will be returned
    by the get_archive_formats() function.
    """
    if extra_args is None:
        extra_args = []
    if not callable(function):
        raise TypeError('The %s object is not callable' % function)
    if not isinstance(extra_args, (tuple, list)):
        raise TypeError('extra_args needs to be a sequence')
    for element in extra_args:
        if not isinstance(element, (tuple, list)) or len(element) !=2:
            raise TypeError('extra_args elements are : (arg_name, value)')

    _ARCHIVE_FORMATS[name] = (function, extra_args, description)

　　13、unregister_archive_format(name)

　　删除压缩包种类

　　14、make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,dry_run=0, owner=None, group=None, logger=None)

　　创建压缩包并返回文件路径

　　base_name：文件名，如果没有路径，保存在当前路径下

　　format：压缩包种类，“zip”“tar”“bztar”“gztar”

　　root_dir：要压缩文件夹路径（默认当前目录）

　　owner：用户，默认为当前用户

　　group：组，默认为当前组

　　logger：日志记录

def make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,
                 dry_run=0, owner=None, group=None, logger=None):
    """Create an archive file (eg. zip or tar).

    'base_name' is the name of the file to create, minus any format-specific
    extension; 'format' is the archive format: one of "zip", "tar", "bztar"
    or "gztar".

    'root_dir' is a directory that will be the root directory of the
    archive; ie. we typically chdir into 'root_dir' before creating the
    archive.  'base_dir' is the directory where we start archiving from;
    ie. 'base_dir' will be the common prefix of all files and
    directories in the archive.  'root_dir' and 'base_dir' both default
    to the current directory.  Returns the name of the archive file.

    'owner' and 'group' are used when creating a tar archive. By default,
    uses the current owner and group.
    """
    save_cwd = os.getcwd()
    if root_dir is not None:
        if logger is not None:
            logger.debug("changing into '%s'", root_dir)
        base_name = os.path.abspath(base_name)
        if not dry_run:
            os.chdir(root_dir)

    if base_dir is None:
        base_dir = os.curdir

    kwargs = {'dry_run': dry_run, 'logger': logger}

    try:
        format_info = _ARCHIVE_FORMATS[format]
    except KeyError:
        raise ValueError("unknown archive format '%s'" % format)

    func = format_info[0]
    for arg, val in format_info[1]:
        kwargs[arg] = val

    if format != 'zip':
        kwargs['owner'] = owner
        kwargs['group'] = group

    try:
        filename = func(base_name, base_dir, **kwargs)
    finally:
        if root_dir is not None:
            if logger is not None:
                logger.debug("changing back to '%s'", save_cwd)
            os.chdir(save_cwd)

    return filename

　　15、get_unpack_formats()

　　返回解压缩包的类型

　　16、register_unpack_format(name, extensions, function, extra_args=None,description='')

　　注册解压缩包的类型

　　17、unregister_unpack_format(name)

　　取消解压缩包类型的注册

　　18、unpack_archive(filename, extract_dir=None, format=None)

　　解压缩命令，没有返回值

def unpack_archive(filename, extract_dir=None, format=None):
    """Unpack an archive.

    `filename` is the name of the archive.

    `extract_dir` is the name of the target directory, where the archive
    is unpacked. If not provided, the current working directory is used.

    `format` is the archive format: one of "zip", "tar", or "gztar". Or any
    other registered format. If not provided, unpack_archive will use the
    filename extension and see if an unpacker was registered for that
    extension.

    In case none is found, a ValueError is raised.
    """
    if extract_dir is None:
        extract_dir = os.getcwd()

    if format is not None:
        try:
            format_info = _UNPACK_FORMATS[format]
        except KeyError:
            raise ValueError("Unknown unpack format '{0}'".format(format))

        func = format_info[1]
        func(filename, extract_dir, **dict(format_info[2]))
    else:
        # we need to look at the registered unpackers supported extensions
        format = _find_unpack_format(filename)
        if format is None:
            raise ReadError("Unknown archive format '{0}'".format(filename))

        func = _UNPACK_FORMATS[format][1]
        kwargs = dict(_UNPACK_FORMATS[format][2])
        func(filename, extract_dir, **kwargs)

　　19、chown(path, user=None, group=None)

　　改变文件或目录的用户及属组信息

def chown(path, user=None, group=None):
    """Change owner user and group of the given path.

    user and group can be the uid/gid or the user/group names, and in that case,
    they are converted to their respective uid/gid.
    """

    if user is None and group is None:
        raise ValueError("user and/or group must be set")

    _user = user
    _group = group

    # -1 means don't change it
    if user is None:
        _user = -1
    # user can either be an int (the uid) or a string (the system username)
    elif isinstance(user, str):
        _user = _get_uid(user)
        if _user is None:
            raise LookupError("no such user: {!r}".format(user))

    if group is None:
        _group = -1
    elif not isinstance(group, int):
        _group = _get_gid(group)
        if _group is None:
            raise LookupError("no such group: {!r}".format(group))

    os.chown(path, _user, _group)

　　20、get_terminal_size(fallback=(80, 24))

　　获取终端大小，默认为（80，24）

　　21、which(cmd, mode=os.F_OK | os.X_OK, path=None)

　　返回命令的路径，可以自定义路径，否则使用os.environ.get（“PATH”）路径。如果没有找到返回None