如何使用 python tarfile 模块将文件附加到 tar 文件?

How to append a file to a tar file use python tarfile module?

我想将文件附加到 tar 文件。例如test.tar.gz中的文件是a.png, b.png, c.png。我有一个名为 a.png 的新 png 文件,我想将 a.png 附加到 test.tar.gz 并覆盖 test.tar.gz 中的旧文件 a.png。我的代码:

import tarfile
a = tarfile.open('test.tar.gz', 'w:gz')
a.add('a.png')
a.close()

然后,test.tar.gz 中的所有文件都消失了,但是 a.png,如果我将代码更改为:

import tarfile
a = tarfile.open('test.tar.gz', 'a:')# or a:gz
a.add('a.png')
a.close()

程序崩溃,错误日志:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/lib/python2.7/tarfile.py", line 1678, in open
    return func(name, filemode, fileobj, **kwargs)
  File "/usr/lib/python2.7/tarfile.py", line 1705, in taropen
    return cls(name, mode, fileobj, **kwargs)
  File "/usr/lib/python2.7/tarfile.py", line 1588, in __init__
    raise ReadError(str(e))
tarfile.ReadError: invalid header

我的错误是什么,我该怎么办?

更新。根据文档,gz 文件无法在 a 模式下打开。如果是这样,在现有存档中添加或更新文件的最佳方式是什么?

来自 tarfile documentation:

Note that 'a:gz' or 'a:bz2' is not possible. If mode is not suitable to open a certain (compressed) file for reading, ReadError is raised. Use mode 'r' to avoid this. If a compression method is not supported, CompressionError is raised.

所以我猜你应该使用gzip library解压,在tarfile中使用a:模式添加文件,然后使用gzip再次压缩。

David Dale asks:

Update. From the documentation, it follows that gz files cannot be open in a mode. If so, what is the best way to add or update files in an existing archive?

简答:

  1. 解压缩/解压缩存档
  2. 替换/添加文件
  3. 重新打包/压缩存档

我尝试使用 gzip's and tarfile 和 file/stream 接口在内存中执行此操作,但未能成功 运行ning - tarball 无论如何都必须重写,因为替换文件显然是不可能的。所以最好只解压整个档案。

tar, gzip.

上的维基百科

脚本,如果直接 运行,也会尝试生成测试图像 "a.png, b.png, c.png, new.png"(需要 Pillow)和初始存档 "test.tar.gz"(如果它们不存在)。然后它将存档解压缩到临时目录中,用 "new.png" 的内容覆盖 "a.png",并打包所有文件,覆盖原始存档。 以下是单独的文件:


当然脚本的功能也可以运行在交互模式下依次执行,以便有机会查看文件。假设脚本的文件名是 "t.py":

>>> from t import *
>>> make_images()
>>> make_archive()
>>> replace_file()
Workaround

开始吧(精华部分在replace_file()):

#!python3
#coding=utf-8
"""
Replace a file in a .tar.gz archive via temporary files
   
"""

import sys        #
import pathlib    # https://docs.python.org/3/library/pathlib.html
import tempfile   # https://docs.python.org/3/library/tempfile.html
import tarfile    # https://docs.python.org/3/library/tarfile.html
#import gzip      # https://docs.python.org/3/library/gzip.html

gfn = "test.tar.gz"
iext = ".png"

replace = "a"+iext
replacement = "new"+iext

def make_images():
    """Generate 4 test images with Pillow (PIL fork, http://pillow.readthedocs.io/)"""
    try:
        from PIL import Image, ImageDraw, ImageFont
        font = ImageFont.truetype("arial.ttf", 50)

        for k,v in {"a":"red", "b":"green", "c":"blue", "new":"orange"}.items():
            img = Image.new('RGB', (100, 100), color=v)
            d = ImageDraw.Draw(img)
            d.text((0, 0), k, fill=(0, 0, 0), font=font)
            img.save(k+iext)
    except Exception as e:
        print(e, file=sys.stderr)
        print("Could not create image files", file=sys.stderr)
        print("(pip install pillow)", file=sys.stderr)

def make_archive():
    """Create gzip compressed tar file with the three images"""
    try:
        t = tarfile.open(gfn, 'w:gz')
        for f in 'abc':
            t.add(f+iext)
        t.close()
    except Exception as e:
        print(e, file=sys.stderr)
        print("Could not create archive", file=sys.stderr)

def make_files():
    """Generate sample images and archive"""
    mi = False
    for f in ['a','b','c','new']:
        p = pathlib.Path(f+iext)
        if not p.is_file():
            mi = True
    if mi:
        make_images()
    if not pathlib.Path(gfn).is_file():
        make_archive()

def add_file_not():
    """Might even corrupt the existing file?"""
    print("Not possible: tarfile with \"a:gz\" - failing now:", file=sys.stderr)
    try:
        a = tarfile.open(gfn, 'a:gz')  # not possible!
        a.add(replacement, arcname=replace)
        a.close()
    except Exception as e:
        print(e, file=sys.stderr)

def replace_file():
    """Extract archive to temporary directory, replace file, replace archive """
    print("Workaround", file=sys.stderr)

    # tempdir
    with tempfile.TemporaryDirectory() as td:
        # dirname to Path
        tdp = pathlib.Path(td)

        # extract archive to temporry directory
        with tarfile.open(gfn) as r:
            r.extractall(td)

        # print(list(tdp.iterdir()), file=sys.stderr)

        # replace target in temporary directory
        (tdp/replace).write_bytes( pathlib.Path(replacement).read_bytes() )

        # replace archive, from all files in tempdir
        with tarfile.open(gfn, "w:gz") as w:
            for f in tdp.iterdir():
                w.add(f, arcname=f.name)
    #done

def test():
    """as the name suggests, this just runs some tests ;-)"""
    make_files()
    #add_file_not()
    replace_file()

if __name__ == "__main__":
    test()

如果你想添加文件而不是替换它们,显然只需省略替换临时文件的行,并将附加文件复制到临时目录中。确保 pathlib.Path.iterdir 然后 "sees" 将新文件添加到新存档中。


我把它放在了一个更有用的函数中:

def targz_add(targz=None, src=None, dst=None, replace=False):
    """Add <src> file(s) to <targz> file, optionally replacing existing file(s).
    Uses temporary directory to modify archive contents.
    TODO: complete error handling...
    """
    import sys, pathlib, tempfile, tarfile

    # ensure targz exists
    tp = pathlib.Path(targz)
    if not tp.is_file():
        sys.stderr.write("Target '{}' does not exist!\n".format(tp) )
        return 1

    # src path(s)
    if not src:
        sys.stderr.write("No files given.\n")
        return 1
    # ensure iterable of string(s)
    if not isinstance(src, (tuple, list, set)):
        src = [src]
    # ensure path(s) exist
    srcp = []
    for s in src:
        sp = pathlib.Path(s)
        if not sp.is_file():
            sys.stderr.write("Source '{}' does not exist.\n".format(sp) )
        else:
            srcp.append(sp)

    if not srcp:
        sys.stderr.write("None of the files exist.\n")
        return 1

    # dst path(s) (filenames in archive)
    dstp = []
    if not dst:
        # default: use filename only
        dstp = [sp.name for sp in srcp]
    else:
        if callable(dst):
            # map dst to each Path, ensure results are Path
            dstp = [pathlib.Path(c) for c in map(dst, srcp)]
        elif not isinstance(dst, (tuple, list, set)):
            # ensure iterable of string(s)
            dstp = [pathlib.Path(dst).name]
        elif isinstance(dst, (tuple, list, set)):
            # convert each string to Path
            dstp = [pathlib.Path(d) for d in dst]
        else:
            # TODO directly support iterable of (src,dst) tuples
            sys.stderr.write("Please fix me, I cannot handle the destination(s) '{}'\n".format(dst) )
            return 1

    if not dstp:
        sys.stderr.write("None of the files exist.\n")
        return 1

    # combine src and dst paths
    sdp = zip(srcp, dstp) # iterator of tuples

    # temporary directory
    with tempfile.TemporaryDirectory() as tempdir:
        tempdirp = pathlib.Path(tempdir)

        # extract original archive to temporry directory
        with tarfile.open(tp) as r:
            r.extractall(tempdirp)

        # copy source(s) to target in temporary directory, optionally replacing it
        for s,d in sdp:
            dp = tempdirp/d

            # TODO extend to allow flag individually
            if not dp.is_file or replace:
                sys.stderr.write("Writing '{1}' (from '{0}')\n".format(s,d) )
                dp.write_bytes( s.read_bytes() )
            else:
                sys.stderr.write("Skipping '{1}' (from '{0}')\n".format(s,d) )

        # replace original archive with new archive from all files in tempdir
        with tarfile.open(tp, "w:gz") as w:
            for f in tempdirp.iterdir():
                w.add(f, arcname=f.name)

    return None

还有几个"tests"例如:

# targz_add("test.tar.gz", "new.png", "a.png")
# targz_add("test.tar.gz", "new.png", "a.png", replace=True)
# targz_add("test.tar.gz", ["new.png"], "a.png")
# targz_add("test.tar.gz", "new.png", ["a.png"], replace=True)
targz_add("test.tar.gz", "new.png", lambda x:str(x).replace("new","a"), replace=True)

shutil 也支持存档,但不添加文件到一个:

https://docs.python.org/3/library/shutil.html#archiving-operations

New in version 3.2.
Changed in version 3.5: Added support for the xztar format.
High-level utilities to create and read compressed and archived files are also provided. They rely on the zipfile and tarfile modules.


这里是添加一个文件,方法是使用io.BytesIO提取到内存,添加并压缩:

import io
import gzip
import tarfile

gfn = "test.tar.gz"
replace = "a.png"
replacement = "new.png"

print("reading {}".format(gfn))
m = io.BytesIO()
with gzip.open(gfn) as g:
    m.write(g.read())

print("opening tar in memory")
m.seek(0)
with tarfile.open(fileobj=m, mode="a") as t:
    t.list()
    print("adding {} as {}".format(replacement, replace))
    t.add(replacement, arcname=replace)
    t.list()

print("writing {}".format(gfn))
m.seek(0)
with gzip.open(gfn, "wb") as g:
    g.write(m.read())

它打印

reading test.tar.gz
opening tar in memory
?rw-rw-rw- 0/0        877 2018-04-11 07:38:57 a.png 
?rw-rw-rw- 0/0        827 2018-04-11 07:38:57 b.png 
?rw-rw-rw- 0/0        787 2018-04-11 07:38:57 c.png 
adding new.png as a.png
?rw-rw-rw- 0/0        877 2018-04-11 07:38:57 a.png 
?rw-rw-rw- 0/0        827 2018-04-11 07:38:57 b.png 
?rw-rw-rw- 0/0        787 2018-04-11 07:38:57 c.png 
-rw-rw-rw- 0/0       2108 2018-04-11 07:38:57 a.png 
writing test.tar.gz

欢迎优化!