python之模块之shutil模块

python之模块之shutil模块

shutil

　　-- --High-level file operations  高级的文件操作模块。

　　os模块提供了对目录或者文件的新建/删除/查看文件属性，还提供了对文件以及目录的路径操作。比如说：绝对路径，父目录……  但是，os文件的操作还应该包含移动 复制  打包 压缩 解压等操作，这些os模块都没有提供。

　　而本章所讲的shutil则就是对os中文件操作的补充。--移动 复制  打包 压缩 解压，

 

shutil功能：

1  shutil.copyfileobj(fsrc, fdst[, length=16*1024])    #copy文件内容到另一个文件，可以copy指定大小的内容

#先来看看其源代码。
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)

#注意！ 在其中fsrc，fdst都是文件对象，都需要打开后才能进行复制操作
import shutil
f1=open('name','r')
f2=open('name_copy','w+')
shutil.copyfileobj(f1,f2,length=16*1024)

 

2  shutil.copyfile(src,dst)   #copy文件内容，是不是感觉上面的文件复制很麻烦？还需要自己手动用open函数打开文件，在这里就不需要了，事实上，copyfile调用了copyfileobj

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

查看源代码

shutil.copyfile('name','name_copy_2')
#一句就可以实现复制文件内容

3  shutil.copymode(src,dst)   #仅copy权限，不更改文件内容，组和用户。

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))

查看源代码

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))

查看源代码

4  shutil.copystat(src,dst)    #复制所有的状态信息，包括权限，组，用户，时间等

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)

查看源代码

5  shutil.copy(src,dst)   #复制文件的内容以及权限，先copyfile后copymode

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

查看源代码

6  shutil.copy2(src,dst)    #复制文件的内容以及文件的所有状态信息。先copyfile后copystat

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

查看源代码

 7  shutil.copytree(src, dst, symlinks=False, ignore=None, copy_function=copy2,ignore_dangling_symlinks=False)   #递归的复制文件内容及状态信息

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

查看源代码

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

# version vulnerable to race conditions

查看源代码

8  shutil.rmtree(path, ignore_errors=False, onerror=None)   #递归地删除文件

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)

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

查看源代码

9  shutil.move(src, dst)    #递归的移动文件

def move(src, dst):
    """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.

    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, symlinks=True)
            rmtree(src)
        else:
            copy2(src, real_dst)
            os.unlink(src)
    return real_dst

查看源代码

10  make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,dry_run=0, owner=None, group=None, logger=None)  #压缩打包

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

查看源代码

base_name：    压缩打包后的文件名或者路径名

format：          压缩或者打包格式    "zip", "tar", "bztar"or "gztar"

root_dir :         将哪个目录或者文件打包（也就是源文件）

>>> shutil.make_archive('tarball','gztar',root_dir='copytree_test')

[root@slyoyo python_test]# ls -l
total 12
drwxr-xr-x. 3 root   root   4096 May 14 19:36 copytree_copy
drwxr-xr-x. 3 root   root   4096 May 14 19:36 copytree_test
-rw-r--r--. 1 root   root      0 May 14 21:12 tarball.tar.gz
-rw-r--r--. 1 python python   79 May 14 05:17 test1
-rw-r--r--. 1 root   root      0 May 14 19:10 test2

实例