Python学习笔记——基础篇第六周——shutil模块

Posted Yared

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了Python学习笔记——基础篇第六周——shutil模块相关的知识,希望对你有一定的参考价值。

常用模块之shutil

高级的 文件、文件夹、压缩包 处理模块

shutil.copyfileobj(fsrc, fdst[, length])
将文件内容拷贝到另一个文件中,可以部分内容

1 def copyfileobj(fsrc, fdst, length=16*1024):
2     """copy data from file-like object fsrc to file-like object fdst"""
3     while 1:
4         buf = fsrc.read(length)
5         if not buf:
6             break
7         fdst.write(buf)
View Code

shutil.copyfile(src, dst)
拷贝文件

 1 def copyfile(src, dst):
 2     """Copy data from src to dst"""
 3     if _samefile(src, dst):
 4         raise Error("`%s` and `%s` are the same file" % (src, dst))
 5 
 6     for fn in [src, dst]:
 7         try:
 8             st = os.stat(fn)
 9         except OSError:
10             # File most likely does not exist
11             pass
12         else:
13             # XXX What about other special files? (sockets, devices...)
14             if stat.S_ISFIFO(st.st_mode):
15                 raise SpecialFileError("`%s` is a named pipe" % fn)
16 
17     with open(src, \'rb\') as fsrc:
18         with open(dst, \'wb\') as fdst:
19             copyfileobj(fsrc, fdst)
View Code

shutil.copymode(src, dst)
仅拷贝权限。内容、组、用户均不变

1 def copymode(src, dst):
2     """Copy mode bits from src to dst"""
3     if hasattr(os, \'chmod\'):
4         st = os.stat(src)
5         mode = stat.S_IMODE(st.st_mode)
6         os.chmod(dst, mode)
View Code

shutil.copystat(src, dst)
拷贝状态的信息,包括:mode bits, atime, mtime, flags

 1 def copystat(src, dst):
 2     """Copy all stat info (mode bits, atime, mtime, flags) from src to dst"""
 3     st = os.stat(src)
 4     mode = stat.S_IMODE(st.st_mode)
 5     if hasattr(os, \'utime\'):
 6         os.utime(dst, (st.st_atime, st.st_mtime))
 7     if hasattr(os, \'chmod\'):
 8         os.chmod(dst, mode)
 9     if hasattr(os, \'chflags\') and hasattr(st, \'st_flags\'):
10         try:
11             os.chflags(dst, st.st_flags)
12         except OSError, why:
13             for err in \'EOPNOTSUPP\', \'ENOTSUP\':
14                 if hasattr(errno, err) and why.errno == getattr(errno, err):
15                     break
16             else:
17                 raise
View Code

shutil.copy(src, dst)
拷贝文件和权限

 1 def copy(src, dst):
 2     """Copy data and mode bits ("cp src dst").
 3 
 4     The destination may be a directory.
 5 
 6     """
 7     if os.path.isdir(dst):
 8         dst = os.path.join(dst, os.path.basename(src))
 9     copyfile(src, dst)
10     copymode(src, dst)
View Code

shutil.copy2(src, dst)
拷贝文件和状态信息

def copy2(src, dst):
    """Copy data and all stat info ("cp -p src dst").

    The destination may be a directory.

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

shutil.ignore_patterns(*patterns)
shutil.copytree(src, dst, symlinks=False, ignore=None)
递归的去拷贝文件

例如:copytree(source, destination, ignore=ignore_patterns(\'*.pyc\', \'tmp*\'))

 1 def ignore_patterns(*patterns):
 2     """Function that can be used as copytree() ignore parameter.
 3 
 4     Patterns is a sequence of glob-style patterns
 5     that are used to exclude files"""
 6     def _ignore_patterns(path, names):
 7         ignored_names = []
 8         for pattern in patterns:
 9             ignored_names.extend(fnmatch.filter(names, pattern))
10         return set(ignored_names)
11     return _ignore_patterns
12 
13 def copytree(src, dst, symlinks=False, ignore=None):
14     """Recursively copy a directory tree using copy2().
15 
16     The destination directory must not already exist.
17     If exception(s) occur, an Error is raised with a list of reasons.
18 
19     If the optional symlinks flag is true, symbolic links in the
20     source tree result in symbolic links in the destination tree; if
21     it is false, the contents of the files pointed to by symbolic
22     links are copied.
23 
24     The optional ignore argument is a callable. If given, it
25     is called with the `src` parameter, which is the directory
26     being visited by copytree(), and `names` which is the list of
27     `src` contents, as returned by os.listdir():
28 
29         callable(src, names) -> ignored_names
30 
31     Since copytree() is called recursively, the callable will be
32     called once for each directory that is copied. It returns a
33     list of names relative to the `src` directory that should
34     not be copied.
35 
36     XXX Consider this example code rather than the ultimate tool.
37 
38     """
39     names = os.listdir(src)
40     if ignore is not None:
41         ignored_names = ignore(src, names)
42     else:
43         ignored_names = set()
44 
45     os.makedirs(dst)
46     errors = []
47     for name in names:
48         if name in ignored_names:
49             continue
50         srcname = os.path.join(src, name)
51         dstname = os.path.join(dst, name)
52         try:
53             if symlinks and os.path.islink(srcname):
54                 linkto = os.readlink(srcname)
55                 os.symlink(linkto, dstname)
56             elif os.path.isdir(srcname):
57                 copytree(srcname, dstname, symlinks, ignore)
58             else:
59                 # Will raise a SpecialFileError for unsupported file types
60                 copy2(srcname, dstname)
61         # catch the Error from the recursive copytree so that we can
62         # continue with other files
63         except Error, err:
64             errors.extend(err.args[0])
65         except EnvironmentError, why:
66             errors.append((srcname, dstname, str(why)))
67     try:
68         copystat(src, dst)
69     except OSError, why:
70         if WindowsError is not None and isinstance(why, WindowsError):
71             # Copying file access times may fail on Windows
72             pass
73         else:
74             errors.append((src, dst, str(why)))
75     if errors:
76         raise Error, errors
View Code

shutil.rmtree(path[, ignore_errors[, onerror]])
递归的去删除文件

 1 def rmtree(path, ignore_errors=False, onerror=None):
 2     """Recursively delete a directory tree.
 3 
 4     If ignore_errors is set, errors are ignored; otherwise, if onerror
 5     is set, it is called to handle the error with arguments (func,
 6     path, exc_info) where func is os.listdir, os.remove, or os.rmdir;
 7     path is the argument to that function that caused it to fail; and
 8     exc_info is a tuple returned by sys.exc_info().  If ignore_errors
 9     is false and onerror is None, an exception is raised.
10 
11     """
12     if ignore_errors:
13         def onerror(*args):
14             pass
15     elif onerror is None:
16         def onerror(*args):
17             raise
18     try:
19         if os.path.islink(path):
20             # symlinks to directories are forbidden, see bug #1669
21             raise OSError("Cannot call rmtree on a symbolic link")
22     except OSError:
23         onerror(os.path.islink, path, sys.exc_info())
24         # can\'t continue even if onerror hook returns
25         return
26     names = []
27     try:
28         names = os.listdir(path)
29     except os.error, err:
30         onerror(os.listdir, path, sys.exc_info())
31     for name in names:
32         fullname = os.path.join(path, name)
33         try:
34             mode = os.lstat(fullname).st_mode
35         except os.error:
36             mode = 0
37         if stat.S_ISDIR(mode):
38             rmtree(fullname, ignore_errors, onerror)
39         else:
40             try:
41                 os.remove(fullname)
42             except os.error, err:
43                 onerror(os.remove, fullname, sys.exc_info())
44     try:
45         os.rmdir(path)
46     except os.error:
47         onerror(os.rmdir, path, sys.exc_info())
View Code

shutil.move(src, dst)
递归的去移动文件

 1 def move(src, dst):
 2     """Recursively move a file or directory to another location. This is
 3     similar to the Unix "mv" command.
 4 
 5     If the destination is a directory or a symlink to a directory, the source
 6     is moved inside the directory. The destination path must not already
 7     exist.
 8 
 9     If the destination already exists but is not a directory, it may be
10     overwritten depending on os.rename() semantics.
11 
12     If the destination is on our current filesystem, then rename() is used.
13     Otherwise, src is copied to the destination and then removed.
14     A lot more could be done here...  A look at a mv.c shows a lot of
15     the issues this implementation glosses over.
16 
17     """
18     real_dst = dst
19     if os.path.isdir(dst):
20         if _samefile(src, dst):
21             # We might be on a case insensitive filesystem,
22             # perform the rename anyway.
23             os.rename(src, dst)
24             return
25 
26         real_dst = os.path.join(dst, _basename(src))
27         if os.path.exists(real_dst):
28             raise Error, "Destination path \'%s\' already exists" % real_dst
29     try:
30         os.rename(src, real_dst)
31     except OSError:
32         if os.path.isdir(src):
33             if _destinsrc(src, dst):
34                 raise Error, "Cannot move a directory \'%s\' into itself \'%s\'." % (src, dst)
35             copytree(src, real_dst, symlinks=True)
36             rmtree(src)
37         else:
38             copy2(src, real_dst)
39             os.unlink(src)
View Code

#运维时做备份时会用到压缩

shutil.make_archive(base_name, format,...)

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/wupeiqi/www =>保存至/Users/wupeiqi/
  • 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
#将 /Users/wupeiqi/Downloads/test 下的文件打包放置当前程序目录
 
import shutil
ret = shutil.make_archive("wwwwwwwwww", \'gztar\', root_dir=\'/Users/wupeiqi/Downloads/test\')
 
 
#将 /Users/wupeiqi/Downloads/test 下的文件打包放置 /Users/wupeiqi/目录
import shutil
ret = shutil.make_archive("/Users/wupeiqi/wwwwwwwwww", \'gztar\', root_dir=\'/Users/wupeiqi/Downloads/test\')
 1 def make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,
 2                  dry_run=0, owner=None, group=None, logger=None):
 3     """Create an archive file (eg. zip or tar).
 4 
 5     \'base_name\' is the name of the file to create, minus any format-specific
 6     extension; \'format\' is the archive format: one of "zip", "tar", "bztar"
 7     or "gztar".
 8 
 9     \'root_dir\' is a directory that will be the root directory of the
10     archive; ie. we typically chdir into \'root_dir\' before creating the
11     archive.  \'base_dir\' is the directory where we start archiving from;
12     ie. \'base_dir\' will be the common prefix of all files and
13     directories in the archive.  \'root_dir\' and \'base_dir\' both default
14     to the current directory.  Returns the name of the archive file.
15 
16     \'owner\' and \'group\' are used when creating a tar archive. By default,
17     uses the current owner and group.
18     """
19     save_cwd = os.getcwd()
20     if root_dir is not None:
21         if logger is not None:
22             logger.debug("changing into \'%s\'", root_dir)
23         base_name = os.path.abspath(base_name)
24         if not dry_run:
25             os.chdir(root_dir)
26 
27     if base_dir is None:
28         base_dir = os.curdir
29 
30     kwargs = {\'dry_run\': dry_run, \'logger\': logger}
31 
32     try:
33         format_info = _ARCHIVE_FORMATS[format]
34     except KeyError:
35         raise ValueError, "unknown archive format \'%s\'" % format
36 
37     func = format_info[0]
38     for arg, val in format_info[1]:
39         kwargs[arg] = val
40 
41     if format != \'zip\':
42         kwargs[\'owner\'] = owner
43         kwargs[\'group\'] = group
44 
45     try:
46         filename = func(base_name, base_dir, **kwargs)
47     finally:
48         if root_dir is not None:
49             if logger is not None:
50                 logger.debug("changing back to \'%s\'", save_cwd)
51             os.chdir(save_cwd)
52 
53     return filename
View Code

shutil 对压缩包的处理是调用 ZipFile 和 TarFile 两个模块来进行的,详细:

 1 import zipfile
 2 
 3 # 压缩
 4 z = zipfile.ZipFile(\'laxi.zip\', \'w\')
 5 z.write(\'a.log\')
 6 z.write(\'data.data\')
 7 z.close()
 8 
 9 # 解压
10 z = zipfile.ZipFile(\'laxi.zip\', \'r\')
11 z.extractall()
12 z.close()
zipfile 压缩解压
 1 import tarfile
 2 
 3 # 压缩
 4 tar = tarfile.open(\'your.tar\',\'w\')
 5 tar.add(\'/Users/wupeiqi/PycharmProjects/bbs2.zip\', arcname=\'bbs2.zip\')
 6 tar.add(\'/Users/wupeiqi/PycharmProjects/cmdb.zip\', arcname=\'cmdb.zip\')
 7 tar.close()
 8 
 9 # 解压
10 tar = tarfile.open(\'your.tar\',\'r\')
11 tar.extractall()  # 可设置解压地址
12 tar.close()
tarfile 压缩解压
  1 class ZipFile(object):
  2     """ Class with methods to open, read, write, close, list zip files.
  3 
  4     z = ZipFile(file, mode="r", compression=ZIP_STORED, allowZip64=False)
  5 
  6     file: Either the path to the file, or a file-like object.
  7           If it is a path, the file will be opened and closed by ZipFile.
  8     mode: The mode can be either read "r", write "w" or append "a".
  9     compression: ZIP_STORED (no compression) or ZIP_DEFLATED (requires zlib).
 10     allowZip64: if True ZipFile will create files with ZIP64 extensions when
 11                 needed, otherwise it will raise an exception when this would
 12                 be necessary.
 13 
 14     """
 15 
 16     fp = None                   # Set here since __del__ checks it
 17 
 18     def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=False):
 19         """Open the ZIP file with mode read "r", write "w" or append "a"."""
 20         if mode not in ("r", "w", "a"):
 21             raise RuntimeError(\'ZipFile() requires mode "r", "w", or "a"\')
 22 
 23         if compression == ZIP_STORED:
 24             pass
 25         elif compression == ZIP_DEFLATED:
 26             if 

以上是关于Python学习笔记——基础篇第六周——shutil模块的主要内容,如果未能解决你的问题,请参考以下文章

Python学习笔记——基础篇第六周——Subprocess模块

Python学习笔记——基础篇第六周——面向对象

Python学习笔记——基础篇第六周——hashlib模块

Python学习笔记——基础篇第六周——模块

Python学习笔记——基础篇第六周——PyYAML & configparser模块

Python学习笔记第六周