Python Shutil模块(文件操作)

文件对象覆盖

# 将文件对象1覆盖到文件对象2
shutil.copyfileobj(文件对象1, 文件对象2)

# 源码
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)

文件名覆盖

# 将文件1覆盖到文件2
shutil.copyfile(文件1.txt, 文件2.txt)

# 源码
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

拷贝文件权限、内容组及用户不变

# 将文件1拷贝到文件2,文件权限、内容组及用户不变
shutil.copymode(文件1,文件2)

# 源码
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))

拷贝权限

# 拷贝权限
shutil.copystat(文件1,文件2)

# 源码
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)

拷贝文件及权限

# 拷贝文件及权限
shutil.copy(文件1, 文件2)

# 源码
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

拷贝文件及状态信息

# 拷贝文件及状态信息
shutil.copy2(文件1, 文件2)

# 源码
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

递归拷贝多个目录到指定目录下。

# 递归拷贝多个目录
shutil.copytree(源目录, 目标目录)

# 源码
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

附:递归的去拷贝文件
例如:copytree(source, destination, ignore=ignore_patterns(‘*.pyc’, ‘tmp*’))

递归删除目录下的目录及文件。

# 递归删除目录下的目录及文件
shutil.rmtree(目标目录)

# 源码
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)

移动文件

# 递归移动文件
shutil.move(源文件, 目标路径)

# 源码
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

压缩文件

# 压缩
shutil.make_archive(文件|文件夹, 格式, 目标路径)

# 源码
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

创建压缩包并返回文件路径,例如:zip、tar

  • base_name: 压缩包的文件名,也可以是压缩包的路径。只是文件名时,则保存至当前目录,否则保存至指定路径,
    如:www                        =>保存至当前路径
    如:/Users/www =>保存至/Users/
  • format: 压缩包种类,“zip”, “tar”, “bztar”,“gztar”
  • root_dir: 要压缩的文件夹路径(默认当前目录)
  • owner: 用户,默认当前用户
  • group: 组,默认当前组
  • logger: 用于记录日志,通常是logging.Logger对象

zipfile 压缩解压

def _make_zipfile(base_name, base_dir, verbose=0, dry_run=0, logger=None):
    """Create a zip file from all the files under 'base_dir'.

    The output zip file will be named 'base_name' + ".zip".  Uses either the
    "zipfile" Python module (if available) or the InfoZIP "zip" utility
    (if installed and found on the default search path).  If neither tool is
    available, raises ExecError.  Returns the name of the output zip
    file.
    """
    import zipfile

    zip_filename = base_name + ".zip"
    archive_dir = os.path.dirname(base_name)

    if archive_dir and not os.path.exists(archive_dir):
        if logger is not None:
            logger.info("creating %s", archive_dir)
        if not dry_run:
            os.makedirs(archive_dir)

    if logger is not None:
        logger.info("creating '%s' and adding '%s' to it",
                    zip_filename, base_dir)

    if not dry_run:
        with zipfile.ZipFile(zip_filename, "w",
                             compression=zipfile.ZIP_DEFLATED) as zf:
            for dirpath, dirnames, filenames in os.walk(base_dir):
                for name in filenames:
                    path = os.path.normpath(os.path.join(dirpath, name))
                    if os.path.isfile(path):
                        zf.write(path, path)
                        if logger is not None:
                            logger.info("adding '%s'", path)

    return zip_filename

tarfile 压缩解压

def _make_tarball(base_name, base_dir, compress="gzip", verbose=0, dry_run=0,
                  owner=None, group=None, logger=None):
    """Create a (possibly compressed) tar file from all the files under
    'base_dir'.

    'compress' must be "gzip" (the default), "bzip2", "xz", or None.

    'owner' and 'group' can be used to define an owner and a group for the
    archive that is being built. If not provided, the current owner and group
    will be used.

    The output tar file will be named 'base_name' +  ".tar", possibly plus
    the appropriate compression extension (".gz", ".bz2", or ".xz").

    Returns the output filename.
    """
    tar_compression = {'gzip': 'gz', None: ''}
    compress_ext = {'gzip': '.gz'}

    if _BZ2_SUPPORTED:
        tar_compression['bzip2'] = 'bz2'
        compress_ext['bzip2'] = '.bz2'

    if _LZMA_SUPPORTED:
        tar_compression['xz'] = 'xz'
        compress_ext['xz'] = '.xz'

    # flags for compression program, each element of list will be an argument
    if compress is not None and compress not in compress_ext:
        raise ValueError("bad value for 'compress', or compression format not "
                         "supported : {0}".format(compress))

    archive_name = base_name + '.tar' + compress_ext.get(compress, '')
    archive_dir = os.path.dirname(archive_name)

    if archive_dir and not os.path.exists(archive_dir):
        if logger is not None:
            logger.info("creating %s", archive_dir)
        if not dry_run:
            os.makedirs(archive_dir)

    # creating the tarball
    if logger is not None:
        logger.info('Creating tar archive')

    uid = _get_uid(owner)
    gid = _get_gid(group)

    def _set_uid_gid(tarinfo):
        if gid is not None:
            tarinfo.gid = gid
            tarinfo.gname = group
        if uid is not None:
            tarinfo.uid = uid
            tarinfo.uname = owner
        return tarinfo

    if not dry_run:
        tar = tarfile.open(archive_name, 'w|%s' % tar_compression[compress])
        try:
            tar.add(base_dir, filter=_set_uid_gid)
        finally:
            tar.close()

    return archive_name
点赞

发表评论

电子邮件地址不会被公开。 必填项已用*标注

Title - Artist
0:00