Create a zip file from a generator in Python?

Question

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

Answer 1

The only solution is to rewrite the method it uses for zipping files to read from a buffer. It would be trivial to add this to the standard libraries; I'm kind of amazed it hasn't been done yet. I gather there's a lot of agreement the entire interface needs to be overhauled, and that seems to be blocking any incremental improvements.

import zipfile, zlib, binascii, struct
class BufferedZipFile(zipfile.ZipFile):
    def writebuffered(self, zipinfo, buffer):
        zinfo = zipinfo

        zinfo.file_size = file_size = 0
        zinfo.flag_bits = 0x00
        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(1024 * 8)
            if not buf:
                break

            file_size = file_size + len(buf)
            CRC = binascii.crc32(buf, CRC) & 0xffffffff
            if cmpr:
                buf = cmpr.compress(buf)
                compress_size = compress_size + len(buf)

            self.fp.write(buf)

        if cmpr:
            buf = cmpr.flush()
            compress_size = compress_size + len(buf)
            self.fp.write(buf)
            zinfo.compress_size = compress_size
        else:
            zinfo.compress_size = file_size

        zinfo.CRC = CRC
        zinfo.file_size = file_size

        position = self.fp.tell()
        self.fp.seek(zinfo.header_offset + 14, 0)
        self.fp.write(struct.pack("