Question

我正试图读取拉链内的文件，但我得到了 “IOError：[Errno 2]没有这样的文件或目录：” 我怀疑它与os.path.join有关。如果我添加“zname”的print语句，则不包括根目录的完整路径。我创建了一个类似的功能，非常适合未压缩的文件，但我很难理解如何在拉链中使这个工作。任何帮助将不胜感激。我是python的新手，如果我错过了一些明显的东西，请原谅我。

以下是代码和错误消息：

def re_zip():
    zcount = []
    zpattern = ('.zip','.ZIP')
    for root, directories, filenames in os.walk(path):
        for filename in filenames:
            if filename.endswith(zpattern):
                zj = os.path.join(root,filename)
                zf = zipfile.ZipFile(zj)
                for zname in zf.namelist():
                    if zname.endswith(ext):
                        text = open(zname, 'r')
                        hits = 0
                        for line in text:
                            if re.match(regex, line):
                                hits = hits + 1
                        zcount.append(hits)
                        print (zname + " , " + str(hits))
                        output.write(str(hits) + " , " + zname + "\n")
                        text.close()    
    return(sum(zcount))

Traceback (most recent call last):
  File "re_count.py", line 80, in <module>
    total = re_match() + re_zip() + re_tar()
  File "re_count.py", line 45, in re_zip
    text = open(zname, 'r')
IOError: [Errno 2] No such file or directory: 'within_zip/folder/myfile.xml'

通过将text = open（zname，'r'）更改为text = zf.open（zname，'r'）来修复re_zip（）

现在我正在尝试使用tar gz文件。我得到了tar或tar.gz的相同错误。我相信tar模块应该处理两者。

def re_tar():
tcount = []
tars = ('tar','gz','tgz','TAR','GZ')
for root, directories, filenames in os.walk(path):
    for filename in filenames:
        if filename.endswith(tars):
            tj = os.path.join(root,filename)
            tf = tarfile.open(tj)
            for tarinfo in tf.getmembers():
                tname = tarinfo.name
                if tname.endswith(ext):
                    text = tf.open(tname, 'r')
                    hits = 0
                    for line in text:
                        if re.match(regex, line):
                            hits = hits + 1
                    tcount.append(hits)
                    print (tname + " , " + str(hits))
                    output.write(str(hits) + " , " + tname + "\n")
                    text.close() 
            tf.close()   
return(sum(tcount))

  File "re_count_v2.py", line 68, in re_tar
    text = tf.open(tname, 'r')
  File "C:\Users\username\AppData\Local\Continuum\Anaconda2\lib\tarfile.py", line 1673, in open
    return func(name, "r", fileobj, **kwargs)
  File "C:\Users\username\AppData\Local\Continuum\Anaconda2\lib\tarfile.py", line 1738, in gzopen
    fileobj = gzip.GzipFile(name, mode, compresslevel, fileobj)
  File "C:\Users\username\AppData\Local\Continuum\Anaconda2\lib\gzip.py", line 94, in __init__
    fileobj = self.myfileobj = __builtin__.open(filename, mode or 'rb')
IOError: [Errno 2] No such file or directory: 'httpopenaccessikuedutr8080oai_.scol11413101_1.xml'

Answer 1

与os.listdir()类似，namelist()方法仅返回没有root的文件名。您无法使用通常的open()函数，而是使用zipfile.open()方法，如下所示：

text = zf.open(zname)

无法在zips和gz中打开文件

1 个答案: