I\'ve got a large amount of data (a couple gigs) I need to write to a zip file in Python. I can\'t load it all into memory at once to pass to the .writestr method of ZipFil
In case anyone stumbles upon this question, which is still relevant in 2017 for Python 2.7, here's a working solution for a true streaming zip file, with no requirement for the output to be seekable as in the other cases. The secret is to set bit 3 of the general purpose bit flag (see https://pkware.cachefly.net/webdocs/casestudies/APPNOTE.TXT section 4.3.9.1).
Note that this implementation will always create a ZIP64-style file, allowing the streaming to work for arbitrarily large files. It includes an ugly hack to force the zip64 end of central directory record, so be aware it will cause all zipfiles written by your process to become ZIP64-style.
import io
import zipfile
import zlib
import binascii
import struct
class ByteStreamer(io.BytesIO):
'''
Variant on BytesIO which lets you write and consume data while
keeping track of the total filesize written. When data is consumed
it is removed from memory, keeping the memory requirements low.
'''
def __init__(self):
super(ByteStreamer, self).__init__()
self._tellall = 0
def tell(self):
return self._tellall
def write(self, b):
orig_size = super(ByteStreamer, self).tell()
super(ByteStreamer, self).write(b)
new_size = super(ByteStreamer, self).tell()
self._tellall += (new_size - orig_size)
def consume(self):
bytes = self.getvalue()
self.seek(0)
self.truncate(0)
return bytes
class BufferedZipFileWriter(zipfile.ZipFile):
'''
ZipFile writer with true streaming (input and output).
Created zip files are always ZIP64-style because it is the only safe way to stream
potentially large zip files without knowing the full size ahead of time.
Example usage:
>>> def stream():
>>> bzfw = BufferedZip64FileWriter()
>>> for arc_path, buffer in inputs: # buffer is a file-like object which supports read(size)
>>> for chunk in bzfw.streambuffer(arc_path, buffer):
>>> yield chunk
>>> yield bzfw.close()
'''
def __init__(self, compression=zipfile.ZIP_DEFLATED):
self._buffer = ByteStreamer()
super(BufferedZipFileWriter, self).__init__(self._buffer, mode='w', compression=compression, allowZip64=True)
def streambuffer(self, zinfo_or_arcname, buffer, chunksize=2**16):
if not isinstance(zinfo_or_arcname, zipfile.ZipInfo):
zinfo = zipfile.ZipInfo(filename=zinfo_or_arcname,
date_time=time.localtime(time.time())[:6])
zinfo.compress_type = self.compression
zinfo.external_attr = 0o600 << 16 # ?rw-------
else:
zinfo = zinfo_or_arcname
zinfo.file_size = file_size = 0
zinfo.flag_bits = 0x08 # Streaming mode: crc and size come after the data
zinfo.header_offset = self.fp.tell()
self._writecheck(zinfo)
self._didModify = True
zinfo.CRC = CRC = 0
zinfo.compress_size = compress_size = 0
self.fp.write(zinfo.FileHeader())
if zinfo.compress_type == zipfile.ZIP_DEFLATED:
cmpr = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION, zlib.DEFLATED, -15)
else:
cmpr = None
while True:
buf = buffer.read(chunksize)
if not buf:
break
file_size += len(buf)
CRC = binascii.crc32(buf, CRC) & 0xffffffff
if cmpr:
buf = cmpr.compress(buf)
compress_size += len(buf)
self.fp.write(buf)
compressed_bytes = self._buffer.consume()
if compressed_bytes:
yield compressed_bytes
if cmpr:
buf = cmpr.flush()
compress_size += len(buf)
self.fp.write(buf)
zinfo.compress_size = compress_size
compressed_bytes = self._buffer.consume()
if compressed_bytes:
yield compressed_bytes
else:
zinfo.compress_size = file_size
zinfo.CRC = CRC
zinfo.file_size = file_size
# Write CRC and file sizes after the file data
# Always write as zip64 -- only safe way to stream what might become a large zipfile
fmt = '