高级的 文件、文件夹、压缩包 处理模块

shutil.copyfileobj(fsrc, fdst[, length])
复制文件内容(不包含元数据)从类文件对象src到类文件对dst。可选参数length指定缓冲区的大小,负数表示一次性读入。默认会把数据切分成小块拷贝,以免占用太多内存。注意:拷贝是从fsrc的当前文件开始,必须先打开文件

 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)
 f1 = open("a.txt","r",encoding="utf-8")
f2 = open("b.txt","w",encoding="utf-8")
shutil.copyfileobj(f1,f2)

shutil.copyfile(src, dst)
拷贝文件,调用了底函数层copyfileobj(),不用再打开文件,如果是同一个文件,会报错

 def copyfile(src, dst):
"""Copy data from src to dst"""
if _samefile(src, dst):
raise Error("`%s` and `%s` are the same file" % (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) with open(src, 'rb') as fsrc:
with open(dst, 'wb') as fdst:
copyfileobj(fsrc, fdst)
shutil.copyfile("a.txt","b.txt")

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

 def copymode(src, dst):
"""Copy mode bits from src to dst"""
if hasattr(os, 'chmod'):
st = os.stat(src)
mode = stat.S_IMODE(st.st_mode)
os.chmod(dst, mode)

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

 def copystat(src, dst):
"""Copy all stat info (mode bits, atime, mtime, flags) from src to dst"""
st = os.stat(src)
mode = stat.S_IMODE(st.st_mode)
if hasattr(os, 'utime'):
os.utime(dst, (st.st_atime, st.st_mtime))
if hasattr(os, 'chmod'):
os.chmod(dst, mode)
if hasattr(os, 'chflags') and hasattr(st, 'st_flags'):
try:
os.chflags(dst, st.st_flags)
except OSError, why:
for err in 'EOPNOTSUPP', 'ENOTSUP':
if hasattr(errno, err) and why.errno == getattr(errno, err):
break
else:
raise

shutil.copy(src, dst)
拷贝文件和权限

 def copy(src, dst):
"""Copy data and mode bits ("cp 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)
copymode(src, dst)

shutil.copy2(src, dst)
拷贝文件和状态信息,实际上先调用shutil.copy,然后使用copystat

 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)

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*'))

 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):
"""Recursively copy a directory tree using copy2(). 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. 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. XXX Consider this example code rather than the ultimate tool. """
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 symlinks and os.path.islink(srcname):
linkto = os.readlink(srcname)
os.symlink(linkto, dstname)
elif os.path.isdir(srcname):
copytree(srcname, dstname, symlinks, ignore)
else:
# Will raise a SpecialFileError for unsupported file types
copy2(srcname, dstname)
# catch the Error from the recursive copytree so that we can
# continue with other files
except Error, err:
errors.extend(err.args[0])
except EnvironmentError, why:
errors.append((srcname, dstname, str(why)))
try:
copystat(src, dst)
except OSError, why:
if WindowsError is not None and isinstance(why, WindowsError):
# Copying file access times may fail on Windows
pass
else:
errors.append((src, dst, str(why)))
if errors:
raise Error, errors
 shutil.copytree("proj","test2")#把文件夹proj中的目录全部复制到test2中
shutil.copytree("proj","test3",ignore=shutil.ignore_patterns("__init__.py","urls.py"))#除ignore中的两个文件外,把文件夹proj中的目录全部复制到test2中

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

 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 os.listdir, os.remove, or os.rmdir;
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
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 os.error, err:
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 os.error:
mode = 0
if stat.S_ISDIR(mode):
rmtree(fullname, ignore_errors, onerror)
else:
try:
os.remove(fullname)
except os.error, err:
onerror(os.remove, fullname, sys.exc_info())
try:
os.rmdir(path)
except os.error:
onerror(os.rmdir, path, sys.exc_info())
shutil.rmtree("test3")

shutil.move(src, dst)
递归的去移动文件,相当于剪切

 def move(src, dst):
"""Recursively move a file or directory to another location. This is
similar to the Unix "mv" command. 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.
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.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)

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
1
2
3
4
5
6
7
8
9
#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')
 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
shutil.make_archive("crm/test2","zip","test2")

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

TarFile :只打包不压缩

 import zipfile

 # 压缩
z = zipfile.ZipFile('laxi.zip', 'w')
z.write('a.log')
z.write('data.data')
z.close() # 解压
z = zipfile.ZipFile('laxi.zip', 'r')
z.extractall()
z.close() zipfile 压缩解压 zipfile 压缩解压

zipfile 压缩解压

 import tarfile

 # 压缩
tar = tarfile.open('your.tar','w')
tar.add('/Users/wupeiqi/PycharmProjects/bbs2.zip', arcname='bbs2.zip')
tar.add('/Users/wupeiqi/PycharmProjects/cmdb.zip', arcname='cmdb.zip')
tar.close() # 解压
tar = tarfile.open('your.tar','r')
tar.extractall() # 可设置解压地址
tar.close() tarfile 压缩解压 tarfile 压缩解压

tarfile 压缩解压

 class ZipFile(object):
""" Class with methods to open, read, write, close, list zip files. z = ZipFile(file, mode="r", compression=ZIP_STORED, allowZip64=False) file: Either the path to the file, or a file-like object.
If it is a path, the file will be opened and closed by ZipFile.
mode: The mode can be either read "r", write "w" or append "a".
compression: ZIP_STORED (no compression) or ZIP_DEFLATED (requires zlib).
allowZip64: if True ZipFile will create files with ZIP64 extensions when
needed, otherwise it will raise an exception when this would
be necessary. """ fp = None # Set here since __del__ checks it def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=False):
"""Open the ZIP file with mode read "r", write "w" or append "a"."""
if mode not in ("r", "w", "a"):
raise RuntimeError('ZipFile() requires mode "r", "w", or "a"') if compression == ZIP_STORED:
pass
elif compression == ZIP_DEFLATED:
if not zlib:
raise RuntimeError,\
"Compression requires the (missing) zlib module"
else:
raise RuntimeError, "That compression method is not supported" self._allowZip64 = allowZip64
self._didModify = False
self.debug = 0 # Level of printing: 0 through 3
self.NameToInfo = {} # Find file info given name
self.filelist = [] # List of ZipInfo instances for archive
self.compression = compression # Method of compression
self.mode = key = mode.replace('b', '')[0]
self.pwd = None
self._comment = '' # Check if we were passed a file-like object
if isinstance(file, basestring):
self._filePassed = 0
self.filename = file
modeDict = {'r' : 'rb', 'w': 'wb', 'a' : 'r+b'}
try:
self.fp = open(file, modeDict[mode])
except IOError:
if mode == 'a':
mode = key = 'w'
self.fp = open(file, modeDict[mode])
else:
raise
else:
self._filePassed = 1
self.fp = file
self.filename = getattr(file, 'name', None) try:
if key == 'r':
self._RealGetContents()
elif key == 'w':
# set the modified flag so central directory gets written
# even if no files are added to the archive
self._didModify = True
elif key == 'a':
try:
# See if file is a zip file
self._RealGetContents()
# seek to start of directory and overwrite
self.fp.seek(self.start_dir, 0)
except BadZipfile:
# file is not a zip file, just append
self.fp.seek(0, 2) # set the modified flag so central directory gets written
# even if no files are added to the archive
self._didModify = True
else:
raise RuntimeError('Mode must be "r", "w" or "a"')
except:
fp = self.fp
self.fp = None
if not self._filePassed:
fp.close()
raise def __enter__(self):
return self def __exit__(self, type, value, traceback):
self.close() def _RealGetContents(self):
"""Read in the table of contents for the ZIP file."""
fp = self.fp
try:
endrec = _EndRecData(fp)
except IOError:
raise BadZipfile("File is not a zip file")
if not endrec:
raise BadZipfile, "File is not a zip file"
if self.debug > 1:
print endrec
size_cd = endrec[_ECD_SIZE] # bytes in central directory
offset_cd = endrec[_ECD_OFFSET] # offset of central directory
self._comment = endrec[_ECD_COMMENT] # archive comment # "concat" is zero, unless zip was concatenated to another file
concat = endrec[_ECD_LOCATION] - size_cd - offset_cd
if endrec[_ECD_SIGNATURE] == stringEndArchive64:
# If Zip64 extension structures are present, account for them
concat -= (sizeEndCentDir64 + sizeEndCentDir64Locator) if self.debug > 2:
inferred = concat + offset_cd
print "given, inferred, offset", offset_cd, inferred, concat
# self.start_dir: Position of start of central directory
self.start_dir = offset_cd + concat
fp.seek(self.start_dir, 0)
data = fp.read(size_cd)
fp = cStringIO.StringIO(data)
total = 0
while total < size_cd:
centdir = fp.read(sizeCentralDir)
if len(centdir) != sizeCentralDir:
raise BadZipfile("Truncated central directory")
centdir = struct.unpack(structCentralDir, centdir)
if centdir[_CD_SIGNATURE] != stringCentralDir:
raise BadZipfile("Bad magic number for central directory")
if self.debug > 2:
print centdir
filename = fp.read(centdir[_CD_FILENAME_LENGTH])
# Create ZipInfo instance to store file information
x = ZipInfo(filename)
x.extra = fp.read(centdir[_CD_EXTRA_FIELD_LENGTH])
x.comment = fp.read(centdir[_CD_COMMENT_LENGTH])
x.header_offset = centdir[_CD_LOCAL_HEADER_OFFSET]
(x.create_version, x.create_system, x.extract_version, x.reserved,
x.flag_bits, x.compress_type, t, d,
x.CRC, x.compress_size, x.file_size) = centdir[1:12]
x.volume, x.internal_attr, x.external_attr = centdir[15:18]
# Convert date/time code to (year, month, day, hour, min, sec)
x._raw_time = t
x.date_time = ( (d>>9)+1980, (d>>5)&0xF, d&0x1F,
t>>11, (t>>5)&0x3F, (t&0x1F) * 2 ) x._decodeExtra()
x.header_offset = x.header_offset + concat
x.filename = x._decodeFilename()
self.filelist.append(x)
self.NameToInfo[x.filename] = x # update total bytes read from central directory
total = (total + sizeCentralDir + centdir[_CD_FILENAME_LENGTH]
+ centdir[_CD_EXTRA_FIELD_LENGTH]
+ centdir[_CD_COMMENT_LENGTH]) if self.debug > 2:
print "total", total def namelist(self):
"""Return a list of file names in the archive."""
l = []
for data in self.filelist:
l.append(data.filename)
return l def infolist(self):
"""Return a list of class ZipInfo instances for files in the
archive."""
return self.filelist def printdir(self):
"""Print a table of contents for the zip file."""
print "%-46s %19s %12s" % ("File Name", "Modified ", "Size")
for zinfo in self.filelist:
date = "%d-%02d-%02d %02d:%02d:%02d" % zinfo.date_time[:6]
print "%-46s %s %12d" % (zinfo.filename, date, zinfo.file_size) def testzip(self):
"""Read all the files and check the CRC."""
chunk_size = 2 ** 20
for zinfo in self.filelist:
try:
# Read by chunks, to avoid an OverflowError or a
# MemoryError with very large embedded files.
with self.open(zinfo.filename, "r") as f:
while f.read(chunk_size): # Check CRC-32
pass
except BadZipfile:
return zinfo.filename def getinfo(self, name):
"""Return the instance of ZipInfo given 'name'."""
info = self.NameToInfo.get(name)
if info is None:
raise KeyError(
'There is no item named %r in the archive' % name) return info def setpassword(self, pwd):
"""Set default password for encrypted files."""
self.pwd = pwd @property
def comment(self):
"""The comment text associated with the ZIP file."""
return self._comment @comment.setter
def comment(self, comment):
# check for valid comment length
if len(comment) > ZIP_MAX_COMMENT:
import warnings
warnings.warn('Archive comment is too long; truncating to %d bytes'
% ZIP_MAX_COMMENT, stacklevel=2)
comment = comment[:ZIP_MAX_COMMENT]
self._comment = comment
self._didModify = True def read(self, name, pwd=None):
"""Return file bytes (as a string) for name."""
return self.open(name, "r", pwd).read() def open(self, name, mode="r", pwd=None):
"""Return file-like object for 'name'."""
if mode not in ("r", "U", "rU"):
raise RuntimeError, 'open() requires mode "r", "U", or "rU"'
if not self.fp:
raise RuntimeError, \
"Attempt to read ZIP archive that was already closed" # Only open a new file for instances where we were not
# given a file object in the constructor
if self._filePassed:
zef_file = self.fp
should_close = False
else:
zef_file = open(self.filename, 'rb')
should_close = True try:
# Make sure we have an info object
if isinstance(name, ZipInfo):
# 'name' is already an info object
zinfo = name
else:
# Get info object for name
zinfo = self.getinfo(name) zef_file.seek(zinfo.header_offset, 0) # Skip the file header:
fheader = zef_file.read(sizeFileHeader)
if len(fheader) != sizeFileHeader:
raise BadZipfile("Truncated file header")
fheader = struct.unpack(structFileHeader, fheader)
if fheader[_FH_SIGNATURE] != stringFileHeader:
raise BadZipfile("Bad magic number for file header") fname = zef_file.read(fheader[_FH_FILENAME_LENGTH])
if fheader[_FH_EXTRA_FIELD_LENGTH]:
zef_file.read(fheader[_FH_EXTRA_FIELD_LENGTH]) if fname != zinfo.orig_filename:
raise BadZipfile, \
'File name in directory "%s" and header "%s" differ.' % (
zinfo.orig_filename, fname) # check for encrypted flag & handle password
is_encrypted = zinfo.flag_bits & 0x1
zd = None
if is_encrypted:
if not pwd:
pwd = self.pwd
if not pwd:
raise RuntimeError, "File %s is encrypted, " \
"password required for extraction" % name zd = _ZipDecrypter(pwd)
# The first 12 bytes in the cypher stream is an encryption header
# used to strengthen the algorithm. The first 11 bytes are
# completely random, while the 12th contains the MSB of the CRC,
# or the MSB of the file time depending on the header type
# and is used to check the correctness of the password.
bytes = zef_file.read(12)
h = map(zd, bytes[0:12])
if zinfo.flag_bits & 0x8:
# compare against the file type from extended local headers
check_byte = (zinfo._raw_time >> 8) & 0xff
else:
# compare against the CRC otherwise
check_byte = (zinfo.CRC >> 24) & 0xff
if ord(h[11]) != check_byte:
raise RuntimeError("Bad password for file", name) return ZipExtFile(zef_file, mode, zinfo, zd,
close_fileobj=should_close)
except:
if should_close:
zef_file.close()
raise def extract(self, member, path=None, pwd=None):
"""Extract a member from the archive to the current working directory,
using its full name. Its file information is extracted as accurately
as possible. `member' may be a filename or a ZipInfo object. You can
specify a different directory using `path'.
"""
if not isinstance(member, ZipInfo):
member = self.getinfo(member) if path is None:
path = os.getcwd() return self._extract_member(member, path, pwd) def extractall(self, path=None, members=None, pwd=None):
"""Extract all members from the archive to the current working
directory. `path' specifies a different directory to extract to.
`members' is optional and must be a subset of the list returned
by namelist().
"""
if members is None:
members = self.namelist() for zipinfo in members:
self.extract(zipinfo, path, pwd) def _extract_member(self, member, targetpath, pwd):
"""Extract the ZipInfo object 'member' to a physical
file on the path targetpath.
"""
# build the destination pathname, replacing
# forward slashes to platform specific separators.
arcname = member.filename.replace('/', os.path.sep) if os.path.altsep:
arcname = arcname.replace(os.path.altsep, os.path.sep)
# interpret absolute pathname as relative, remove drive letter or
# UNC path, redundant separators, "." and ".." components.
arcname = os.path.splitdrive(arcname)[1]
arcname = os.path.sep.join(x for x in arcname.split(os.path.sep)
if x not in ('', os.path.curdir, os.path.pardir))
if os.path.sep == '\\':
# filter illegal characters on Windows
illegal = ':<>|"?*'
if isinstance(arcname, unicode):
table = {ord(c): ord('_') for c in illegal}
else:
table = string.maketrans(illegal, '_' * len(illegal))
arcname = arcname.translate(table)
# remove trailing dots
arcname = (x.rstrip('.') for x in arcname.split(os.path.sep))
arcname = os.path.sep.join(x for x in arcname if x) targetpath = os.path.join(targetpath, arcname)
targetpath = os.path.normpath(targetpath) # Create all upper directories if necessary.
upperdirs = os.path.dirname(targetpath)
if upperdirs and not os.path.exists(upperdirs):
os.makedirs(upperdirs) if member.filename[-1] == '/':
if not os.path.isdir(targetpath):
os.mkdir(targetpath)
return targetpath with self.open(member, pwd=pwd) as source, \
file(targetpath, "wb") as target:
shutil.copyfileobj(source, target) return targetpath def _writecheck(self, zinfo):
"""Check for errors before writing a file to the archive."""
if zinfo.filename in self.NameToInfo:
import warnings
warnings.warn('Duplicate name: %r' % zinfo.filename, stacklevel=3)
if self.mode not in ("w", "a"):
raise RuntimeError, 'write() requires mode "w" or "a"'
if not self.fp:
raise RuntimeError, \
"Attempt to write ZIP archive that was already closed"
if zinfo.compress_type == ZIP_DEFLATED and not zlib:
raise RuntimeError, \
"Compression requires the (missing) zlib module"
if zinfo.compress_type not in (ZIP_STORED, ZIP_DEFLATED):
raise RuntimeError, \
"That compression method is not supported"
if not self._allowZip64:
requires_zip64 = None
if len(self.filelist) >= ZIP_FILECOUNT_LIMIT:
requires_zip64 = "Files count"
elif zinfo.file_size > ZIP64_LIMIT:
requires_zip64 = "Filesize"
elif zinfo.header_offset > ZIP64_LIMIT:
requires_zip64 = "Zipfile size"
if requires_zip64:
raise LargeZipFile(requires_zip64 +
" would require ZIP64 extensions") def write(self, filename, arcname=None, compress_type=None):
"""Put the bytes from filename into the archive under the name
arcname."""
if not self.fp:
raise RuntimeError(
"Attempt to write to ZIP archive that was already closed") st = os.stat(filename)
isdir = stat.S_ISDIR(st.st_mode)
mtime = time.localtime(st.st_mtime)
date_time = mtime[0:6]
# Create ZipInfo instance to store file information
if arcname is None:
arcname = filename
arcname = os.path.normpath(os.path.splitdrive(arcname)[1])
while arcname[0] in (os.sep, os.altsep):
arcname = arcname[1:]
if isdir:
arcname += '/'
zinfo = ZipInfo(arcname, date_time)
zinfo.external_attr = (st[0] & 0xFFFF) << 16L # Unix attributes
if compress_type is None:
zinfo.compress_type = self.compression
else:
zinfo.compress_type = compress_type zinfo.file_size = st.st_size
zinfo.flag_bits = 0x00
zinfo.header_offset = self.fp.tell() # Start of header bytes self._writecheck(zinfo)
self._didModify = True if isdir:
zinfo.file_size = 0
zinfo.compress_size = 0
zinfo.CRC = 0
zinfo.external_attr |= 0x10 # MS-DOS directory flag
self.filelist.append(zinfo)
self.NameToInfo[zinfo.filename] = zinfo
self.fp.write(zinfo.FileHeader(False))
return with open(filename, "rb") as fp:
# Must overwrite CRC and sizes with correct data later
zinfo.CRC = CRC = 0
zinfo.compress_size = compress_size = 0
# Compressed size can be larger than uncompressed size
zip64 = self._allowZip64 and \
zinfo.file_size * 1.05 > ZIP64_LIMIT
self.fp.write(zinfo.FileHeader(zip64))
if zinfo.compress_type == ZIP_DEFLATED:
cmpr = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
zlib.DEFLATED, -15)
else:
cmpr = None
file_size = 0
while 1:
buf = fp.read(1024 * 8)
if not buf:
break
file_size = file_size + len(buf)
CRC = crc32(buf, CRC) & 0xffffffff
if cmpr:
buf = cmpr.compress(buf)
compress_size = compress_size + len(buf)
self.fp.write(buf)
if cmpr:
buf = cmpr.flush()
compress_size = compress_size + len(buf)
self.fp.write(buf)
zinfo.compress_size = compress_size
else:
zinfo.compress_size = file_size
zinfo.CRC = CRC
zinfo.file_size = file_size
if not zip64 and self._allowZip64:
if file_size > ZIP64_LIMIT:
raise RuntimeError('File size has increased during compressing')
if compress_size > ZIP64_LIMIT:
raise RuntimeError('Compressed size larger than uncompressed size')
# Seek backwards and write file header (which will now include
# correct CRC and file sizes)
position = self.fp.tell() # Preserve current position in file
self.fp.seek(zinfo.header_offset, 0)
self.fp.write(zinfo.FileHeader(zip64))
self.fp.seek(position, 0)
self.filelist.append(zinfo)
self.NameToInfo[zinfo.filename] = zinfo def writestr(self, zinfo_or_arcname, bytes, compress_type=None):
"""Write a file into the archive. The contents is the string
'bytes'. 'zinfo_or_arcname' is either a ZipInfo instance or
the name of the file in the archive."""
if not isinstance(zinfo_or_arcname, ZipInfo):
zinfo = ZipInfo(filename=zinfo_or_arcname,
date_time=time.localtime(time.time())[:6]) zinfo.compress_type = self.compression
if zinfo.filename[-1] == '/':
zinfo.external_attr = 0o40775 << 16 # drwxrwxr-x
zinfo.external_attr |= 0x10 # MS-DOS directory flag
else:
zinfo.external_attr = 0o600 << 16 # ?rw-------
else:
zinfo = zinfo_or_arcname if not self.fp:
raise RuntimeError(
"Attempt to write to ZIP archive that was already closed") if compress_type is not None:
zinfo.compress_type = compress_type zinfo.file_size = len(bytes) # Uncompressed size
zinfo.header_offset = self.fp.tell() # Start of header bytes
self._writecheck(zinfo)
self._didModify = True
zinfo.CRC = crc32(bytes) & 0xffffffff # CRC-32 checksum
if zinfo.compress_type == ZIP_DEFLATED:
co = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
zlib.DEFLATED, -15)
bytes = co.compress(bytes) + co.flush()
zinfo.compress_size = len(bytes) # Compressed size
else:
zinfo.compress_size = zinfo.file_size
zip64 = zinfo.file_size > ZIP64_LIMIT or \
zinfo.compress_size > ZIP64_LIMIT
if zip64 and not self._allowZip64:
raise LargeZipFile("Filesize would require ZIP64 extensions")
self.fp.write(zinfo.FileHeader(zip64))
self.fp.write(bytes)
if zinfo.flag_bits & 0x08:
# Write CRC and file sizes after the file data
fmt = '<LQQ' if zip64 else '<LLL'
self.fp.write(struct.pack(fmt, zinfo.CRC, zinfo.compress_size,
zinfo.file_size))
self.fp.flush()
self.filelist.append(zinfo)
self.NameToInfo[zinfo.filename] = zinfo def __del__(self):
"""Call the "close()" method in case the user forgot."""
self.close() def close(self):
"""Close the file, and for mode "w" and "a" write the ending
records."""
if self.fp is None:
return try:
if self.mode in ("w", "a") and self._didModify: # write ending records
pos1 = self.fp.tell()
for zinfo in self.filelist: # write central directory
dt = zinfo.date_time
dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2]
dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2)
extra = []
if zinfo.file_size > ZIP64_LIMIT \
or zinfo.compress_size > ZIP64_LIMIT:
extra.append(zinfo.file_size)
extra.append(zinfo.compress_size)
file_size = 0xffffffff
compress_size = 0xffffffff
else:
file_size = zinfo.file_size
compress_size = zinfo.compress_size if zinfo.header_offset > ZIP64_LIMIT:
extra.append(zinfo.header_offset)
header_offset = 0xffffffffL
else:
header_offset = zinfo.header_offset extra_data = zinfo.extra
if extra:
# Append a ZIP64 field to the extra's
extra_data = struct.pack(
'<HH' + 'Q'*len(extra),
1, 8*len(extra), *extra) + extra_data extract_version = max(45, zinfo.extract_version)
create_version = max(45, zinfo.create_version)
else:
extract_version = zinfo.extract_version
create_version = zinfo.create_version try:
filename, flag_bits = zinfo._encodeFilenameFlags()
centdir = struct.pack(structCentralDir,
stringCentralDir, create_version,
zinfo.create_system, extract_version, zinfo.reserved,
flag_bits, zinfo.compress_type, dostime, dosdate,
zinfo.CRC, compress_size, file_size,
len(filename), len(extra_data), len(zinfo.comment),
0, zinfo.internal_attr, zinfo.external_attr,
header_offset)
except DeprecationWarning:
print >>sys.stderr, (structCentralDir,
stringCentralDir, create_version,
zinfo.create_system, extract_version, zinfo.reserved,
zinfo.flag_bits, zinfo.compress_type, dostime, dosdate,
zinfo.CRC, compress_size, file_size,
len(zinfo.filename), len(extra_data), len(zinfo.comment),
0, zinfo.internal_attr, zinfo.external_attr,
header_offset)
raise
self.fp.write(centdir)
self.fp.write(filename)
self.fp.write(extra_data)
self.fp.write(zinfo.comment) pos2 = self.fp.tell()
# Write end-of-zip-archive record
centDirCount = len(self.filelist)
centDirSize = pos2 - pos1
centDirOffset = pos1
requires_zip64 = None
if centDirCount > ZIP_FILECOUNT_LIMIT:
requires_zip64 = "Files count"
elif centDirOffset > ZIP64_LIMIT:
requires_zip64 = "Central directory offset"
elif centDirSize > ZIP64_LIMIT:
requires_zip64 = "Central directory size"
if requires_zip64:
# Need to write the ZIP64 end-of-archive records
if not self._allowZip64:
raise LargeZipFile(requires_zip64 +
" would require ZIP64 extensions")
zip64endrec = struct.pack(
structEndArchive64, stringEndArchive64,
44, 45, 45, 0, 0, centDirCount, centDirCount,
centDirSize, centDirOffset)
self.fp.write(zip64endrec) zip64locrec = struct.pack(
structEndArchive64Locator,
stringEndArchive64Locator, 0, pos2, 1)
self.fp.write(zip64locrec)
centDirCount = min(centDirCount, 0xFFFF)
centDirSize = min(centDirSize, 0xFFFFFFFF)
centDirOffset = min(centDirOffset, 0xFFFFFFFF) endrec = struct.pack(structEndArchive, stringEndArchive,
0, 0, centDirCount, centDirCount,
centDirSize, centDirOffset, len(self._comment))
self.fp.write(endrec)
self.fp.write(self._comment)
self.fp.flush()
finally:
fp = self.fp
self.fp = None
if not self._filePassed:
fp.close() ZipFile ZipFile

ZipFile

 class TarFile(object):
"""The TarFile Class provides an interface to tar archives.
""" debug = 0 # May be set from 0 (no msgs) to 3 (all msgs) dereference = False # If true, add content of linked file to the
# tar file, else the link. ignore_zeros = False # If true, skips empty or invalid blocks and
# continues processing. errorlevel = 1 # If 0, fatal errors only appear in debug
# messages (if debug >= 0). If > 0, errors
# are passed to the caller as exceptions. format = DEFAULT_FORMAT # The format to use when creating an archive. encoding = ENCODING # Encoding for 8-bit character strings. errors = None # Error handler for unicode conversion. tarinfo = TarInfo # The default TarInfo class to use. fileobject = ExFileObject # The default ExFileObject class to use. def __init__(self, name=None, mode="r", fileobj=None, format=None,
tarinfo=None, dereference=None, ignore_zeros=None, encoding=None,
errors=None, pax_headers=None, debug=None, errorlevel=None):
"""Open an (uncompressed) tar archive `name'. `mode' is either 'r' to
read from an existing archive, 'a' to append data to an existing
file or 'w' to create a new file overwriting an existing one. `mode'
defaults to 'r'.
If `fileobj' is given, it is used for reading or writing data. If it
can be determined, `mode' is overridden by `fileobj's mode.
`fileobj' is not closed, when TarFile is closed.
"""
modes = {"r": "rb", "a": "r+b", "w": "wb"}
if mode not in modes:
raise ValueError("mode must be 'r', 'a' or 'w'")
self.mode = mode
self._mode = modes[mode] if not fileobj:
if self.mode == "a" and not os.path.exists(name):
# Create nonexistent files in append mode.
self.mode = "w"
self._mode = "wb"
fileobj = bltn_open(name, self._mode)
self._extfileobj = False
else:
if name is None and hasattr(fileobj, "name"):
name = fileobj.name
if hasattr(fileobj, "mode"):
self._mode = fileobj.mode
self._extfileobj = True
self.name = os.path.abspath(name) if name else None
self.fileobj = fileobj # Init attributes.
if format is not None:
self.format = format
if tarinfo is not None:
self.tarinfo = tarinfo
if dereference is not None:
self.dereference = dereference
if ignore_zeros is not None:
self.ignore_zeros = ignore_zeros
if encoding is not None:
self.encoding = encoding if errors is not None:
self.errors = errors
elif mode == "r":
self.errors = "utf-8"
else:
self.errors = "strict" if pax_headers is not None and self.format == PAX_FORMAT:
self.pax_headers = pax_headers
else:
self.pax_headers = {} if debug is not None:
self.debug = debug
if errorlevel is not None:
self.errorlevel = errorlevel # Init datastructures.
self.closed = False
self.members = [] # list of members as TarInfo objects
self._loaded = False # flag if all members have been read
self.offset = self.fileobj.tell()
# current position in the archive file
self.inodes = {} # dictionary caching the inodes of
# archive members already added try:
if self.mode == "r":
self.firstmember = None
self.firstmember = self.next() if self.mode == "a":
# Move to the end of the archive,
# before the first empty block.
while True:
self.fileobj.seek(self.offset)
try:
tarinfo = self.tarinfo.fromtarfile(self)
self.members.append(tarinfo)
except EOFHeaderError:
self.fileobj.seek(self.offset)
break
except HeaderError, e:
raise ReadError(str(e)) if self.mode in "aw":
self._loaded = True if self.pax_headers:
buf = self.tarinfo.create_pax_global_header(self.pax_headers.copy())
self.fileobj.write(buf)
self.offset += len(buf)
except:
if not self._extfileobj:
self.fileobj.close()
self.closed = True
raise def _getposix(self):
return self.format == USTAR_FORMAT
def _setposix(self, value):
import warnings
warnings.warn("use the format attribute instead", DeprecationWarning,
2)
if value:
self.format = USTAR_FORMAT
else:
self.format = GNU_FORMAT
posix = property(_getposix, _setposix) #--------------------------------------------------------------------------
# Below are the classmethods which act as alternate constructors to the
# TarFile class. The open() method is the only one that is needed for
# public use; it is the "super"-constructor and is able to select an
# adequate "sub"-constructor for a particular compression using the mapping
# from OPEN_METH.
#
# This concept allows one to subclass TarFile without losing the comfort of
# the super-constructor. A sub-constructor is registered and made available
# by adding it to the mapping in OPEN_METH. @classmethod
def open(cls, name=None, mode="r", fileobj=None, bufsize=RECORDSIZE, **kwargs):
"""Open a tar archive for reading, writing or appending. Return
an appropriate TarFile class. mode:
'r' or 'r:*' open for reading with transparent compression
'r:' open for reading exclusively uncompressed
'r:gz' open for reading with gzip compression
'r:bz2' open for reading with bzip2 compression
'a' or 'a:' open for appending, creating the file if necessary
'w' or 'w:' open for writing without compression
'w:gz' open for writing with gzip compression
'w:bz2' open for writing with bzip2 compression 'r|*' open a stream of tar blocks with transparent compression
'r|' open an uncompressed stream of tar blocks for reading
'r|gz' open a gzip compressed stream of tar blocks
'r|bz2' open a bzip2 compressed stream of tar blocks
'w|' open an uncompressed stream for writing
'w|gz' open a gzip compressed stream for writing
'w|bz2' open a bzip2 compressed stream for writing
""" if not name and not fileobj:
raise ValueError("nothing to open") if mode in ("r", "r:*"):
# Find out which *open() is appropriate for opening the file.
for comptype in cls.OPEN_METH:
func = getattr(cls, cls.OPEN_METH[comptype])
if fileobj is not None:
saved_pos = fileobj.tell()
try:
return func(name, "r", fileobj, **kwargs)
except (ReadError, CompressionError), e:
if fileobj is not None:
fileobj.seek(saved_pos)
continue
raise ReadError("file could not be opened successfully") elif ":" in mode:
filemode, comptype = mode.split(":", 1)
filemode = filemode or "r"
comptype = comptype or "tar" # Select the *open() function according to
# given compression.
if comptype in cls.OPEN_METH:
func = getattr(cls, cls.OPEN_METH[comptype])
else:
raise CompressionError("unknown compression type %r" % comptype)
return func(name, filemode, fileobj, **kwargs) elif "|" in mode:
filemode, comptype = mode.split("|", 1)
filemode = filemode or "r"
comptype = comptype or "tar" if filemode not in ("r", "w"):
raise ValueError("mode must be 'r' or 'w'") stream = _Stream(name, filemode, comptype, fileobj, bufsize)
try:
t = cls(name, filemode, stream, **kwargs)
except:
stream.close()
raise
t._extfileobj = False
return t elif mode in ("a", "w"):
return cls.taropen(name, mode, fileobj, **kwargs) raise ValueError("undiscernible mode") @classmethod
def taropen(cls, name, mode="r", fileobj=None, **kwargs):
"""Open uncompressed tar archive name for reading or writing.
"""
if mode not in ("r", "a", "w"):
raise ValueError("mode must be 'r', 'a' or 'w'")
return cls(name, mode, fileobj, **kwargs) @classmethod
def gzopen(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs):
"""Open gzip compressed tar archive name for reading or writing.
Appending is not allowed.
"""
if mode not in ("r", "w"):
raise ValueError("mode must be 'r' or 'w'") try:
import gzip
gzip.GzipFile
except (ImportError, AttributeError):
raise CompressionError("gzip module is not available") try:
fileobj = gzip.GzipFile(name, mode, compresslevel, fileobj)
except OSError:
if fileobj is not None and mode == 'r':
raise ReadError("not a gzip file")
raise try:
t = cls.taropen(name, mode, fileobj, **kwargs)
except IOError:
fileobj.close()
if mode == 'r':
raise ReadError("not a gzip file")
raise
except:
fileobj.close()
raise
t._extfileobj = False
return t @classmethod
def bz2open(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs):
"""Open bzip2 compressed tar archive name for reading or writing.
Appending is not allowed.
"""
if mode not in ("r", "w"):
raise ValueError("mode must be 'r' or 'w'.") try:
import bz2
except ImportError:
raise CompressionError("bz2 module is not available") if fileobj is not None:
fileobj = _BZ2Proxy(fileobj, mode)
else:
fileobj = bz2.BZ2File(name, mode, compresslevel=compresslevel) try:
t = cls.taropen(name, mode, fileobj, **kwargs)
except (IOError, EOFError):
fileobj.close()
if mode == 'r':
raise ReadError("not a bzip2 file")
raise
except:
fileobj.close()
raise
t._extfileobj = False
return t # All *open() methods are registered here.
OPEN_METH = {
"tar": "taropen", # uncompressed tar
"gz": "gzopen", # gzip compressed tar
"bz2": "bz2open" # bzip2 compressed tar
} #--------------------------------------------------------------------------
# The public methods which TarFile provides: def close(self):
"""Close the TarFile. In write-mode, two finishing zero blocks are
appended to the archive.
"""
if self.closed:
return if self.mode in "aw":
self.fileobj.write(NUL * (BLOCKSIZE * 2))
self.offset += (BLOCKSIZE * 2)
# fill up the end with zero-blocks
# (like option -b20 for tar does)
blocks, remainder = divmod(self.offset, RECORDSIZE)
if remainder > 0:
self.fileobj.write(NUL * (RECORDSIZE - remainder)) if not self._extfileobj:
self.fileobj.close()
self.closed = True def getmember(self, name):
"""Return a TarInfo object for member `name'. If `name' can not be
found in the archive, KeyError is raised. If a member occurs more
than once in the archive, its last occurrence is assumed to be the
most up-to-date version.
"""
tarinfo = self._getmember(name)
if tarinfo is None:
raise KeyError("filename %r not found" % name)
return tarinfo def getmembers(self):
"""Return the members of the archive as a list of TarInfo objects. The
list has the same order as the members in the archive.
"""
self._check()
if not self._loaded: # if we want to obtain a list of
self._load() # all members, we first have to
# scan the whole archive.
return self.members def getnames(self):
"""Return the members of the archive as a list of their names. It has
the same order as the list returned by getmembers().
"""
return [tarinfo.name for tarinfo in self.getmembers()] def gettarinfo(self, name=None, arcname=None, fileobj=None):
"""Create a TarInfo object for either the file `name' or the file
object `fileobj' (using os.fstat on its file descriptor). You can
modify some of the TarInfo's attributes before you add it using
addfile(). If given, `arcname' specifies an alternative name for the
file in the archive.
"""
self._check("aw") # When fileobj is given, replace name by
# fileobj's real name.
if fileobj is not None:
name = fileobj.name # Building the name of the member in the archive.
# Backward slashes are converted to forward slashes,
# Absolute paths are turned to relative paths.
if arcname is None:
arcname = name
drv, arcname = os.path.splitdrive(arcname)
arcname = arcname.replace(os.sep, "/")
arcname = arcname.lstrip("/") # Now, fill the TarInfo object with
# information specific for the file.
tarinfo = self.tarinfo()
tarinfo.tarfile = self # Use os.stat or os.lstat, depending on platform
# and if symlinks shall be resolved.
if fileobj is None:
if hasattr(os, "lstat") and not self.dereference:
statres = os.lstat(name)
else:
statres = os.stat(name)
else:
statres = os.fstat(fileobj.fileno())
linkname = "" stmd = statres.st_mode
if stat.S_ISREG(stmd):
inode = (statres.st_ino, statres.st_dev)
if not self.dereference and statres.st_nlink > 1 and \
inode in self.inodes and arcname != self.inodes[inode]:
# Is it a hardlink to an already
# archived file?
type = LNKTYPE
linkname = self.inodes[inode]
else:
# The inode is added only if its valid.
# For win32 it is always 0.
type = REGTYPE
if inode[0]:
self.inodes[inode] = arcname
elif stat.S_ISDIR(stmd):
type = DIRTYPE
elif stat.S_ISFIFO(stmd):
type = FIFOTYPE
elif stat.S_ISLNK(stmd):
type = SYMTYPE
linkname = os.readlink(name)
elif stat.S_ISCHR(stmd):
type = CHRTYPE
elif stat.S_ISBLK(stmd):
type = BLKTYPE
else:
return None # Fill the TarInfo object with all
# information we can get.
tarinfo.name = arcname
tarinfo.mode = stmd
tarinfo.uid = statres.st_uid
tarinfo.gid = statres.st_gid
if type == REGTYPE:
tarinfo.size = statres.st_size
else:
tarinfo.size = 0L
tarinfo.mtime = statres.st_mtime
tarinfo.type = type
tarinfo.linkname = linkname
if pwd:
try:
tarinfo.uname = pwd.getpwuid(tarinfo.uid)[0]
except KeyError:
pass
if grp:
try:
tarinfo.gname = grp.getgrgid(tarinfo.gid)[0]
except KeyError:
pass if type in (CHRTYPE, BLKTYPE):
if hasattr(os, "major") and hasattr(os, "minor"):
tarinfo.devmajor = os.major(statres.st_rdev)
tarinfo.devminor = os.minor(statres.st_rdev)
return tarinfo def list(self, verbose=True):
"""Print a table of contents to sys.stdout. If `verbose' is False, only
the names of the members are printed. If it is True, an `ls -l'-like
output is produced.
"""
self._check() for tarinfo in self:
if verbose:
print filemode(tarinfo.mode),
print "%s/%s" % (tarinfo.uname or tarinfo.uid,
tarinfo.gname or tarinfo.gid),
if tarinfo.ischr() or tarinfo.isblk():
print "%10s" % ("%d,%d" \
% (tarinfo.devmajor, tarinfo.devminor)),
else:
print "%10d" % tarinfo.size,
print "%d-%02d-%02d %02d:%02d:%02d" \
% time.localtime(tarinfo.mtime)[:6], print tarinfo.name + ("/" if tarinfo.isdir() else ""), if verbose:
if tarinfo.issym():
print "->", tarinfo.linkname,
if tarinfo.islnk():
print "link to", tarinfo.linkname,
print def add(self, name, arcname=None, recursive=True, exclude=None, filter=None):
"""Add the file `name' to the archive. `name' may be any type of file
(directory, fifo, symbolic link, etc.). If given, `arcname'
specifies an alternative name for the file in the archive.
Directories are added recursively by default. This can be avoided by
setting `recursive' to False. `exclude' is a function that should
return True for each filename to be excluded. `filter' is a function
that expects a TarInfo object argument and returns the changed
TarInfo object, if it returns None the TarInfo object will be
excluded from the archive.
"""
self._check("aw") if arcname is None:
arcname = name # Exclude pathnames.
if exclude is not None:
import warnings
warnings.warn("use the filter argument instead",
DeprecationWarning, 2)
if exclude(name):
self._dbg(2, "tarfile: Excluded %r" % name)
return # Skip if somebody tries to archive the archive...
if self.name is not None and os.path.abspath(name) == self.name:
self._dbg(2, "tarfile: Skipped %r" % name)
return self._dbg(1, name) # Create a TarInfo object from the file.
tarinfo = self.gettarinfo(name, arcname) if tarinfo is None:
self._dbg(1, "tarfile: Unsupported type %r" % name)
return # Change or exclude the TarInfo object.
if filter is not None:
tarinfo = filter(tarinfo)
if tarinfo is None:
self._dbg(2, "tarfile: Excluded %r" % name)
return # Append the tar header and data to the archive.
if tarinfo.isreg():
with bltn_open(name, "rb") as f:
self.addfile(tarinfo, f) elif tarinfo.isdir():
self.addfile(tarinfo)
if recursive:
for f in os.listdir(name):
self.add(os.path.join(name, f), os.path.join(arcname, f),
recursive, exclude, filter) else:
self.addfile(tarinfo) def addfile(self, tarinfo, fileobj=None):
"""Add the TarInfo object `tarinfo' to the archive. If `fileobj' is
given, tarinfo.size bytes are read from it and added to the archive.
You can create TarInfo objects using gettarinfo().
On Windows platforms, `fileobj' should always be opened with mode
'rb' to avoid irritation about the file size.
"""
self._check("aw") tarinfo = copy.copy(tarinfo) buf = tarinfo.tobuf(self.format, self.encoding, self.errors)
self.fileobj.write(buf)
self.offset += len(buf) # If there's data to follow, append it.
if fileobj is not None:
copyfileobj(fileobj, self.fileobj, tarinfo.size)
blocks, remainder = divmod(tarinfo.size, BLOCKSIZE)
if remainder > 0:
self.fileobj.write(NUL * (BLOCKSIZE - remainder))
blocks += 1
self.offset += blocks * BLOCKSIZE self.members.append(tarinfo) def extractall(self, path=".", members=None):
"""Extract all members from the archive to the current working
directory and set owner, modification time and permissions on
directories afterwards. `path' specifies a different directory
to extract to. `members' is optional and must be a subset of the
list returned by getmembers().
"""
directories = [] if members is None:
members = self for tarinfo in members:
if tarinfo.isdir():
# Extract directories with a safe mode.
directories.append(tarinfo)
tarinfo = copy.copy(tarinfo)
tarinfo.mode = 0700
self.extract(tarinfo, path) # Reverse sort directories.
directories.sort(key=operator.attrgetter('name'))
directories.reverse() # Set correct owner, mtime and filemode on directories.
for tarinfo in directories:
dirpath = os.path.join(path, tarinfo.name)
try:
self.chown(tarinfo, dirpath)
self.utime(tarinfo, dirpath)
self.chmod(tarinfo, dirpath)
except ExtractError, e:
if self.errorlevel > 1:
raise
else:
self._dbg(1, "tarfile: %s" % e) def extract(self, member, path=""):
"""Extract a member from the archive to the current working directory,
using its full name. Its file information is extracted as accurately
as possible. `member' may be a filename or a TarInfo object. You can
specify a different directory using `path'.
"""
self._check("r") if isinstance(member, basestring):
tarinfo = self.getmember(member)
else:
tarinfo = member # Prepare the link target for makelink().
if tarinfo.islnk():
tarinfo._link_target = os.path.join(path, tarinfo.linkname) try:
self._extract_member(tarinfo, os.path.join(path, tarinfo.name))
except EnvironmentError, e:
if self.errorlevel > 0:
raise
else:
if e.filename is None:
self._dbg(1, "tarfile: %s" % e.strerror)
else:
self._dbg(1, "tarfile: %s %r" % (e.strerror, e.filename))
except ExtractError, e:
if self.errorlevel > 1:
raise
else:
self._dbg(1, "tarfile: %s" % e) def extractfile(self, member):
"""Extract a member from the archive as a file object. `member' may be
a filename or a TarInfo object. If `member' is a regular file, a
file-like object is returned. If `member' is a link, a file-like
object is constructed from the link's target. If `member' is none of
the above, None is returned.
The file-like object is read-only and provides the following
methods: read(), readline(), readlines(), seek() and tell()
"""
self._check("r") if isinstance(member, basestring):
tarinfo = self.getmember(member)
else:
tarinfo = member if tarinfo.isreg():
return self.fileobject(self, tarinfo) elif tarinfo.type not in SUPPORTED_TYPES:
# If a member's type is unknown, it is treated as a
# regular file.
return self.fileobject(self, tarinfo) elif tarinfo.islnk() or tarinfo.issym():
if isinstance(self.fileobj, _Stream):
# A small but ugly workaround for the case that someone tries
# to extract a (sym)link as a file-object from a non-seekable
# stream of tar blocks.
raise StreamError("cannot extract (sym)link as file object")
else:
# A (sym)link's file object is its target's file object.
return self.extractfile(self._find_link_target(tarinfo))
else:
# If there's no data associated with the member (directory, chrdev,
# blkdev, etc.), return None instead of a file object.
return None def _extract_member(self, tarinfo, targetpath):
"""Extract the TarInfo object tarinfo to a physical
file called targetpath.
"""
# Fetch the TarInfo object for the given name
# and build the destination pathname, replacing
# forward slashes to platform specific separators.
targetpath = targetpath.rstrip("/")
targetpath = targetpath.replace("/", os.sep) # Create all upper directories.
upperdirs = os.path.dirname(targetpath)
if upperdirs and not os.path.exists(upperdirs):
# Create directories that are not part of the archive with
# default permissions.
os.makedirs(upperdirs) if tarinfo.islnk() or tarinfo.issym():
self._dbg(1, "%s -> %s" % (tarinfo.name, tarinfo.linkname))
else:
self._dbg(1, tarinfo.name) if tarinfo.isreg():
self.makefile(tarinfo, targetpath)
elif tarinfo.isdir():
self.makedir(tarinfo, targetpath)
elif tarinfo.isfifo():
self.makefifo(tarinfo, targetpath)
elif tarinfo.ischr() or tarinfo.isblk():
self.makedev(tarinfo, targetpath)
elif tarinfo.islnk() or tarinfo.issym():
self.makelink(tarinfo, targetpath)
elif tarinfo.type not in SUPPORTED_TYPES:
self.makeunknown(tarinfo, targetpath)
else:
self.makefile(tarinfo, targetpath) self.chown(tarinfo, targetpath)
if not tarinfo.issym():
self.chmod(tarinfo, targetpath)
self.utime(tarinfo, targetpath) #--------------------------------------------------------------------------
# Below are the different file methods. They are called via
# _extract_member() when extract() is called. They can be replaced in a
# subclass to implement other functionality. def makedir(self, tarinfo, targetpath):
"""Make a directory called targetpath.
"""
try:
# Use a safe mode for the directory, the real mode is set
# later in _extract_member().
os.mkdir(targetpath, 0700)
except EnvironmentError, e:
if e.errno != errno.EEXIST:
raise def makefile(self, tarinfo, targetpath):
"""Make a file called targetpath.
"""
source = self.extractfile(tarinfo)
try:
with bltn_open(targetpath, "wb") as target:
copyfileobj(source, target)
finally:
source.close() def makeunknown(self, tarinfo, targetpath):
"""Make a file from a TarInfo object with an unknown type
at targetpath.
"""
self.makefile(tarinfo, targetpath)
self._dbg(1, "tarfile: Unknown file type %r, " \
"extracted as regular file." % tarinfo.type) def makefifo(self, tarinfo, targetpath):
"""Make a fifo called targetpath.
"""
if hasattr(os, "mkfifo"):
os.mkfifo(targetpath)
else:
raise ExtractError("fifo not supported by system") def makedev(self, tarinfo, targetpath):
"""Make a character or block device called targetpath.
"""
if not hasattr(os, "mknod") or not hasattr(os, "makedev"):
raise ExtractError("special devices not supported by system") mode = tarinfo.mode
if tarinfo.isblk():
mode |= stat.S_IFBLK
else:
mode |= stat.S_IFCHR os.mknod(targetpath, mode,
os.makedev(tarinfo.devmajor, tarinfo.devminor)) def makelink(self, tarinfo, targetpath):
"""Make a (symbolic) link called targetpath. If it cannot be created
(platform limitation), we try to make a copy of the referenced file
instead of a link.
"""
if hasattr(os, "symlink") and hasattr(os, "link"):
# For systems that support symbolic and hard links.
if tarinfo.issym():
if os.path.lexists(targetpath):
os.unlink(targetpath)
os.symlink(tarinfo.linkname, targetpath)
else:
# See extract().
if os.path.exists(tarinfo._link_target):
if os.path.lexists(targetpath):
os.unlink(targetpath)
os.link(tarinfo._link_target, targetpath)
else:
self._extract_member(self._find_link_target(tarinfo), targetpath)
else:
try:
self._extract_member(self._find_link_target(tarinfo), targetpath)
except KeyError:
raise ExtractError("unable to resolve link inside archive") def chown(self, tarinfo, targetpath):
"""Set owner of targetpath according to tarinfo.
"""
if pwd and hasattr(os, "geteuid") and os.geteuid() == 0:
# We have to be root to do so.
try:
g = grp.getgrnam(tarinfo.gname)[2]
except KeyError:
g = tarinfo.gid
try:
u = pwd.getpwnam(tarinfo.uname)[2]
except KeyError:
u = tarinfo.uid
try:
if tarinfo.issym() and hasattr(os, "lchown"):
os.lchown(targetpath, u, g)
else:
if sys.platform != "os2emx":
os.chown(targetpath, u, g)
except EnvironmentError, e:
raise ExtractError("could not change owner") def chmod(self, tarinfo, targetpath):
"""Set file permissions of targetpath according to tarinfo.
"""
if hasattr(os, 'chmod'):
try:
os.chmod(targetpath, tarinfo.mode)
except EnvironmentError, e:
raise ExtractError("could not change mode") def utime(self, tarinfo, targetpath):
"""Set modification time of targetpath according to tarinfo.
"""
if not hasattr(os, 'utime'):
return
try:
os.utime(targetpath, (tarinfo.mtime, tarinfo.mtime))
except EnvironmentError, e:
raise ExtractError("could not change modification time") #--------------------------------------------------------------------------
def next(self):
"""Return the next member of the archive as a TarInfo object, when
TarFile is opened for reading. Return None if there is no more
available.
"""
self._check("ra")
if self.firstmember is not None:
m = self.firstmember
self.firstmember = None
return m # Read the next block.
self.fileobj.seek(self.offset)
tarinfo = None
while True:
try:
tarinfo = self.tarinfo.fromtarfile(self)
except EOFHeaderError, e:
if self.ignore_zeros:
self._dbg(2, "0x%X: %s" % (self.offset, e))
self.offset += BLOCKSIZE
continue
except InvalidHeaderError, e:
if self.ignore_zeros:
self._dbg(2, "0x%X: %s" % (self.offset, e))
self.offset += BLOCKSIZE
continue
elif self.offset == 0:
raise ReadError(str(e))
except EmptyHeaderError:
if self.offset == 0:
raise ReadError("empty file")
except TruncatedHeaderError, e:
if self.offset == 0:
raise ReadError(str(e))
except SubsequentHeaderError, e:
raise ReadError(str(e))
break if tarinfo is not None:
self.members.append(tarinfo)
else:
self._loaded = True return tarinfo #--------------------------------------------------------------------------
# Little helper methods: def _getmember(self, name, tarinfo=None, normalize=False):
"""Find an archive member by name from bottom to top.
If tarinfo is given, it is used as the starting point.
"""
# Ensure that all members have been loaded.
members = self.getmembers() # Limit the member search list up to tarinfo.
if tarinfo is not None:
members = members[:members.index(tarinfo)] if normalize:
name = os.path.normpath(name) for member in reversed(members):
if normalize:
member_name = os.path.normpath(member.name)
else:
member_name = member.name if name == member_name:
return member def _load(self):
"""Read through the entire archive file and look for readable
members.
"""
while True:
tarinfo = self.next()
if tarinfo is None:
break
self._loaded = True def _check(self, mode=None):
"""Check if TarFile is still open, and if the operation's mode
corresponds to TarFile's mode.
"""
if self.closed:
raise IOError("%s is closed" % self.__class__.__name__)
if mode is not None and self.mode not in mode:
raise IOError("bad operation for mode %r" % self.mode) def _find_link_target(self, tarinfo):
"""Find the target member of a symlink or hardlink member in the
archive.
"""
if tarinfo.issym():
# Always search the entire archive.
linkname = "/".join(filter(None, (os.path.dirname(tarinfo.name), tarinfo.linkname)))
limit = None
else:
# Search the archive before the link, because a hard link is
# just a reference to an already archived file.
linkname = tarinfo.linkname
limit = tarinfo member = self._getmember(linkname, tarinfo=limit, normalize=True)
if member is None:
raise KeyError("linkname %r not found" % linkname)
return member def __iter__(self):
"""Provide an iterator object.
"""
if self._loaded:
return iter(self.members)
else:
return TarIter(self) def _dbg(self, level, msg):
"""Write debugging output to sys.stderr.
"""
if level <= self.debug:
print >> sys.stderr, msg def __enter__(self):
self._check()
return self def __exit__(self, type, value, traceback):
if type is None:
self.close()
else:
# An exception occurred. We must not call close() because
# it would try to write end-of-archive blocks and padding.
if not self._extfileobj:
self.fileobj.close()
self.closed = True
# class TarFile TarFile TarFile

TarFile

shutil——高级的 文件、文件夹、压缩包 处理模块的更多相关文章

  1. shutil模块(高级的文件、文件夹、压缩包处理模块)

    shutil 模块 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 import shutil s ...

  2. shutil 模块 高级的文件、文件夹、压缩包 处理模块

    高级的文件.文件夹.压缩包 处理模块 # 将文件内容拷贝到另一个文件中 shutil.copyfileobj(fsrc, fdst[, length]) import shutil shutil.co ...

  3. shutil模块——高级的文件、文件夹、压缩包处理模块

    将文件内容拷贝到另一个文件 shutil.copyfileobj('fsrc', 'fdst', 'length') 方法源码: def copyfileobj(fsrc, fdst, length= ...

  4. python3之shutil高级文件操作

    1.shutil高级文件操作模块 shutil模块提供了大量的文件的高级操作.特别针对文件拷贝和删除,主要功能为目录和文件操作以及压缩操作.对单个文件的操作也可参见os模块. 2.shutil模块的拷 ...

  5. python模块之shutil高级文件操作

    简介 shutil模块提供了大量的文件的高级操作.特别针对文件拷贝和删除,主要功能为目录和文件操作以及压缩操作.对单个文件的操作也可参见os模块. 注意即便是更高级别的文件复制函数(shutil.co ...

  6. Python(文件、文件夹压缩处理模块,shelve持久化模块,xml处理模块、ConfigParser文档配置模块、hashlib加密模块,subprocess系统交互模块 log模块)

    OS模块 提供对操作系统进行调用的接口 os.getcwd() 获取当前工作目录,即当前python脚本工作的目录路径 os.chdir("dirname")  改变当前脚本工作目 ...

  7. SharpZipLib 文件/文件夹压缩

    一.ZipFile ZipFile类用于选择文件或文件夹进行压缩生成压缩包. 常用属性: 属性 说明 Count 文件数目(注意是在ComitUpdat之后才有) Password 压缩包密码 Siz ...

  8. linux压缩文件(夹) zip uzip命令的用法

    压缩文件(夹) # 压缩列举的文件,格式如下: zip 压缩包名称 文件1 文件2 文件3 ... # 压缩test.txt, a.out文件,并取名为abc.zip $ zip abc.zip te ...

  9. C# 文件/文件夹压缩

    一.ZipFile ZipFile类用于选择文件或文件夹进行压缩生成压缩包. 常用属性: 属性 说明 Count 文件数目(注意是在ComitUpdat之后才有) Password 压缩包密码 Siz ...

随机推荐

  1. Godaddy虚拟主机新建mysql数据库 2019最新

    第一次用狗爹,完全摸不着路子. 网站本地已搭建,不知道数据库是在哪里上传. 百度搜索结果都是四五年前的旧内容,耽误时间. 还是问客服,Godaddy的客服确实不赖 godaddy虚拟主机如何新建数据库 ...

  2. ubuntu server 16.04安装GPU服务器

    1 Ubuntu16.04 系统安装过程中,需要勾选openssh-server 方便远程连接 2 必须安装gcc 与g++ 3 安装显卡驱动 NVIDIA-Linux-x86_64-367.57.r ...

  3. SQL Server 填充因子

    在创建聚集索引时,表中的数据按照索引列中的值的顺序存储在数据库的数据页中.在表中插入新的数据行或更改索引列中的值时,Microsoft®   SQL   Server™   2000   可能必须重新 ...

  4. Python+selenium之获取请求信息

    basicConfig()所捕获的log信息.不过其开启的debug模式只能捕获到客户端像服务器发送的post()请求,而无法获取服务器所返回的应答信息. from random import ran ...

  5. IT界程序员几大恶习能立即让你变穷,你有吗?

    IT软件开发,确实是各行业中薪水排名靠前的职业,月薪在八千以上的Java程序员多不胜数,但是不知有没有以下几种恶习?如果粘上一种,哪怕你薪水几万,估计最后也是囊中羞涩:综上所述列举以下几点,亲们自己对 ...

  6. Winform C# 编程 1

    http://b6ec263c.wiz03.com/share/s/2SX2oY0nX4f32CY5ax1bapaL01Wmfc0B-QfB2pS1y13peTbq

  7. UVALive 3026 Period (KMP算法简介)

    kmp的代码很短,但是不太容易理解,还是先说明一下这个算法过程吧. 朴素的字符串匹配大家都懂,但是效率不高,原因在哪里? 匹配过程没有充分利用已经匹配好的模版的信息,比如说, i是文本串当前字符的下标 ...

  8. 小技巧:unicode RLO

    unicode 控制字符 RLO 可以将位于其后的文字翻转. 于是可以被病毒利用. 如图 重命名文件,在gpj前插入unicode RLO,之后若不小心,可能会被欺骗,误以为是jpg文件. 如果修改程 ...

  9. 个人对spring的IOC+DI的封装

    暂时支持8种基本数据类型,String类型,引用类型,List的注入. 核心代码 package day01; import java.lang.reflect.Field;import java.l ...

  10. Deepgreen DB 是什么(含Deepgreen和Greenplum下载地址)

    Deepgreen官网下载地址:http://vitessedata.com/products/deepgreen-db/download/ 不需要注册 Greenplum官网下载地址:https:/ ...