这将允许您迭代行。它部分源自我在另一个问题的答案中找到的一些代码。
在该时间点（
pylzma-0.5.0），该
py7zlib模块未实现允许将存档成员作为字节流或字符流读取的API-其
ArchiveFile类仅提供了一次
read()解压缩并返回成员中未压缩数据的功能。鉴于此，最好的办法是通过Python生成器使用该缓冲区作为缓冲区迭代地返回字节或行。
下面是后者的操作，但是如果问题是存档 成员 文件本身很大，则可能没有帮助。
下面的代码应在Python 3.x和2.7中均可使用。
import ioimport osimport py7zlibclass SevenZFileError(py7zlib.ArchiveError): passclass 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 'rn' 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().depre() for line in io.StringIO(data, newline=newline): yield lineif __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))
