Python文件复制shutil模块

Python中shutil模块主要用于文件操作，如复制，属性判断等

1.copyfileobj，拷贝文件内容，将文件句柄赋给该方法

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

copyfileobj源代码

'''
复制文件内容到另一个文件，需先打开两个文件
语法：shutil.copyfileobj(fsrc, fdst, length=1024)
'''

with open("src.txt", encoding='utf-8') as fsrc:

    with open("dst.txt", 'w', encoding='utf-8') as fdst:

        shutil.copyfileobj(fsrc, fdst)

2.copyfile，拷贝文件，将文件路径赋给该方法即可

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 src:
            with open(dst, 'wb') as dst:
                copyfileobj(src, dst)
    return dst

copyfile源代码

# 拷贝文件，无需先打开两个文件,
# 语法：shutil.copyfile(src, dst)

path_src = 'src'
path_dst = 'dst2'
shutil.copyfile(path_src, path_dst)

3.copymode，仅拷贝文件权限（dst目标文件必须已经存在），将文件路径赋给该方法

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))

copymode源代码

# 仅拷贝文件权限mode，
# 语法：shutil.copymode(src,dst, *, follow_symlinks=True)

shutil.copymode('src', 'dst2')

4.copystat，仅拷贝文件的属性信息stat（dst目标文件必须已经存在），将文件路径赋给该方法

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)

copystat源代码

# 拷贝文件的属性信息stat，包括mode
# 语法：shutil.copystat(src, dst, *, follow_symlinks=True)

shutil.copystat('src', 'dst2')

5.copy，拷贝文件和文件权限mode，将文件路径赋给该方法

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

copy源代码

# 拷贝文件和文件权限mode，
# 语法：shutil.copy(src, dst, *, follow_symlinks=True)

shutil.copy('src', 'dst3')

# 测试
import os
print(os.stat('src'))
print(os.stat('dst3'))

6.copy2，拷贝文件和文件属性信息stat，将文件路径赋给该方法

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

copy2源代码

# 拷贝文件和文件属性stat，包括mode
# 语法：shutil.copy2(src, dst, *, follow_symlinks=True)

shutil.copy2('src', 'dst5')

# 测试
import os
print(os.stat('src'))
print(os.stat('dst5'))

7.ignore_patterns，拷贝目录过程中，忽略/排除某些文件（以元组的形式）

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

ignore_patterns源代码

# shutil.ignore_patterns忽略/排除文件，
# 与shutil.copytree复制目录/递归复制连用，
# 语法：shutil.ignore_patterns(*patterns)，
# shutil.copytree(src, dst, symlinks=False, ignore=None, copy_function=copy2, ignore_dangling_symlinks=False)

shutil.copytree(r'd:/a/', r'd:/b/', ignore=shutil.ignore_patterns('123.txt'))

8._rmtree_unsafe，递归删除目录

def _rmtree_unsafe(path, onerror):
    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
    names = []
    try:
        names = os.listdir(path)
    except OSError:
        onerror(os.listdir, path, sys.exc_info())
    for name in names:
        fullname = os.path.join(path, name)
        try:
            mode = os.lstat(fullname).st_mode
        except OSError:
            mode = 0
        if stat.S_ISDIR(mode):
            _rmtree_unsafe(fullname, onerror)
        else:
            try:
                os.unlink(fullname)
            except OSError:
                onerror(os.unlink, fullname, sys.exc_info())
    try:
        os.rmdir(path)
    except OSError:
        onerror(os.rmdir, path, sys.exc_info())

def _rmtree_safe_fd(topfd, path, onerror):
    names = []
    try:
        names = os.listdir(topfd)
    except OSError as err:
        err.filename = path
        onerror(os.listdir, path, sys.exc_info())
    for name in names:
        fullname = os.path.join(path, name)
        try:
            orig_st = os.stat(name, dir_fd=topfd, follow_symlinks=False)
            mode = orig_st.st_mode
        except OSError:
            mode = 0
        if stat.S_ISDIR(mode):
            try:
                dirfd = os.open(name, os.O_RDONLY, dir_fd=topfd)
            except OSError:
                onerror(os.open, fullname, sys.exc_info())
            else:
                try:
                    if os.path.samestat(orig_st, os.fstat(dirfd)):
                        _rmtree_safe_fd(dirfd, fullname, onerror)
                        try:
                            os.rmdir(name, dir_fd=topfd)
                        except OSError:
                            onerror(os.rmdir, fullname, sys.exc_info())
                    else:
                        try:
                            # This can only happen if someone replaces
                            # a directory with a symlink after the call to
                            # stat.S_ISDIR above.
                            raise OSError("Cannot call rmtree on a symbolic "
                                          "link")
                        except OSError:
                            onerror(os.path.islink, fullname, sys.exc_info())
                finally:
                    os.close(dirfd)
        else:
            try:
                os.unlink(name, dir_fd=topfd)
            except OSError:
                onerror(os.unlink, fullname, sys.exc_info())

_rmtree_unsafe源代码

# 递归删除目录及目录下文件，无论空目录还是非空目录
# 语法：shutil._rmtree_unsafe(path, onerror)

shutil._rmtree_unsafe(r'd:/dudu', 'onerror')

 9.move，递归移动目录或移动文件

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

move源代码

# 递归移动目录和文件
# 语法：shutil.move(src, dst, copy_function=copy2)

shutil.move(r'd:/a', r'd:/b')

10.make_archive，打包压缩文件

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

make_archive源代码

# 打包压缩文件
# 语法：def make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,
#                        dry_run=0, owner=None, group=None, logger=None)

shutil.make_archive('d:/wongdu', 'zip', 'd:/caiyun')
"""
补充说明：
base_name: 打包压缩后路径和文件名，不指定路径，则默认打包压缩到当前目录
format: 打包压缩格式, python3支持zip、tar、gztar
root_dir: 要打包压缩的路径，默认为当前路径
owner、group: 指定压缩包的所有者
logger: 用于记录日志，通常是logging.logger对象
"""