shutil模塊的使用

　　shutil模塊

　　高級的文件，文件夾，壓縮包處理模塊

　　shutil.copyfileobj(fsrc,fdst,length)　　將文件內容拷貝到另一個文件中，能夠部分。fdst目標length長度（長度是每次讀取的長度）

　　使用方法

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)

　　shutil.copyfile(src,dst)　　拷貝文件

　　使用方法

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

View Code

　　shutil.copymode(src,dst)　　僅拷貝權限。內容、組、用戶不變

　　使用方法

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))

if hasattr(os, 'listxattr'):
    def _copyxattr(src, dst, *, follow_symlinks=True):
        """Copy extended filesystem attributes from `src` to `dst`.

        Overwrite existing attributes.

        If `follow_symlinks` is false, symlinks won't be followed.

        """

        try:
            names = os.listxattr(src, follow_symlinks=follow_symlinks)
        except OSError as e:
            if e.errno not in (errno.ENOTSUP, errno.ENODATA):
                raise
            return
        for name in names:
            try:
                value = os.getxattr(src, name, follow_symlinks=follow_symlinks)
                os.setxattr(dst, name, value, follow_symlinks=follow_symlinks)
            except OSError as e:
                if e.errno not in (errno.EPERM, errno.ENOTSUP, errno.ENODATA):
                    raise
else:
    def _copyxattr(*args, **kwargs):
        pass

View Code

　　shutil.copystat(src,dst)　　拷貝狀態的信息,包括：mode bits,atime,mtime,flags

　　使用方法

def copystat(src, dst, *, follow_symlinks=True):
    """Copy file metadata

    Copy the permission bits, last access time, last modification time, and
    flags from `src` to `dst`. On Linux, copystat() also copies the "extended
    attributes" where possible. The file contents, owner, and group are
    unaffected. `src` and `dst` are path names given as strings.

    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)

View Code

　　shutil.copy(src,dst)　　拷貝文件和權限

　　使用方法

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

View Code

　　shutil.copy2(src,dst)　　拷貝文件和狀態信息

　　使用方法

def copy2(src, dst, *, follow_symlinks=True):
    """Copy data and metadata. Return the file's destination.

    Metadata is copied with copystat(). Please see the copystat function
    for more information.

    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

View Code

　　shutil.ignore_patterns(*patterns)

　　shutil.copytree(src,dst,syminks=False,ignore=None)　　遞歸的拷貝文件src原文件夾dst拷貝的新文件名稱syminks軟鏈接默認不copy;ignore=None 忽略的文件（新文件夾名稱若是存在會報錯）

　　使用方法

　　例如：shutil.copytree(src,dst,syminks=False,ignore=shutil.ignore_patterns(*patterns))

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

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

View Code

　　shutil.rmtree(path, ignore_errors=False, onerror=None)　　遞歸的去刪除文件（刪除全部文件）

　　使用方法

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:
        try:
            if os.path.islink(path):
                # 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())
            # can't continue even if onerror hook returns
            return
        return _rmtree_unsafe(path, onerror)

# Allow introspection of whether or not the hardening against symlink
# attacks is supported on the current platform
rmtree.avoids_symlink_attacks = _use_fd_functions

View Code

　　shutil.move(src,dst)　　遞歸的移動文件（相似於重命名）

　　使用方法

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

View Code

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

　　base_name：壓縮包的文件名，也能夠是壓縮包的路徑，只是文件名時，則保存至當前目錄，不然保存至指定路徑，

　　如：wenjianming　　　　==>保存至當前路徑

　　如：/users/kevin/wenjianming　　==>保存至/users/kevin/

　　format：壓縮包種類，「zip」,"tar",「bztar」,"gztar"

　　root_dir：要壓縮的文件夾路徑（默認當前目錄）

 　　owner=None, group=None, logger=None  用戶（默認當前），組（默認當前），用於記錄日誌，一般是logging.Logger對象

　　使用方法

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", "gztar",
    "bztar", or "xztar".  Or any other registered format.

    '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) from None

    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

View Code

　　shutil 對壓縮包的處理是調用了ZipFile和TarFile兩個模塊來進行的。

　　壓縮（當前的）

import zipfile

# 壓縮
z = zipfile.ZipFile('kevin.zip', 'w')
z.write('a.log')
z.write('data.data')
z.close()

# 解壓
z = zipfile.ZipFile('kevin.zip', 'r')
z.extractall()
z.close()

View Code

　　打包（只打包不壓縮（全部的））

import  tarfile

# 壓縮
tar = tarfile.open('kevin.tar', 'w')
tar.add('/users/Kevin/Pycharmprojects/kevin.zip', arcname=kevin.zip)
tar.add('/users/Kevin/Pycharmprojects/roc.zip', arcname=roc.zip)
tar.close()

# 解壓
tar = tarfile.open('kevin.tar', 'r')
tar.extractall()    # 可設置解壓地址
tar.close()

View Code