这将允许您迭代行。它部分源自我在 answer 中找到的一些代码,用于另一个问题。
在这个时间点 (pylzma-0.5.0),py7zlib 模块没有实现允许存档成员作为字节或字符流读取的 API — 它的 ArchiveFile 类仅提供 @987654325 @函数一次解压缩并返回成员中的未压缩数据。鉴于此,可以做的最好的事情是通过 Python 生成器使用它作为缓冲区迭代地返回字节或行。
以下是后者,但如果问题是存档 member 文件本身很大,则可能无济于事。
下面的代码应该可以在 Python 3.x 和 2.7 中运行。
import io
import os
import py7zlib
class SevenZFileError(py7zlib.ArchiveError):
pass
class SevenZFile(object):
@classmethod
def is_7zfile(cls, filepath):
""" Determine if filepath points to a valid 7z archive. """
is7z = False
fp = None
try:
fp = open(filepath, 'rb')
archive = py7zlib.Archive7z(fp)
_ = len(archive.getnames())
is7z = True
finally:
if fp: fp.close()
return is7z
def __init__(self, filepath):
fp = open(filepath, 'rb')
self.filepath = filepath
self.archive = py7zlib.Archive7z(fp)
def __contains__(self, name):
return name in self.archive.getnames()
def readlines(self, name, newline=''):
r""" Iterator of lines from named archive member.
`newline` controls how line endings are handled.
It can be None, '', '\n', '\r', and '\r\n' and works the same way as it does
in StringIO. Note however that the default value is different and is to enable
universal newlines mode, but line endings are returned untranslated.
"""
archivefile = self.archive.getmember(name)
if not archivefile:
raise SevenZFileError('archive member %r not found in %r' %
(name, self.filepath))
# Decompress entire member and return its contents iteratively.
data = archivefile.read().decode()
for line in io.StringIO(data, newline=newline):
yield line
if __name__ == '__main__':
import csv
if SevenZFile.is_7zfile('testing.csv.7z'):
sevenZfile = SevenZFile('testing.csv.7z')
if 'testing.csv' not in sevenZfile:
print('testing.csv is not a member of testing.csv.7z')
else:
reader = csv.reader(sevenZfile.readlines('testing.csv'))
for row in reader:
print(', '.join(row))