Created
April 12, 2012 15:09
-
-
Save tonylukasavage/2368003 to your computer and use it in GitHub Desktop.
Trying to unzip large files
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Make sure you add the -Xmx512M options or jython will throw a heap exception | |
# METHOD 1 | |
import zipfile, os, sys | |
z = zipfile.ZipFile(sys.argv[1]) | |
for name in z.namelist(): | |
destdir = os.path.dirname(name) | |
if not os.path.isdir(destdir) : | |
os.makedirs(destdir) | |
print name | |
data = z.read(name) | |
outfile = open(name, 'wb') | |
outfile.write(data) | |
outfile.close() | |
z.close() | |
# METHOD 2 | |
import zipfile | |
import zlib | |
import os | |
import sys | |
src = open( sys.argv[1], "rb" ) | |
zf = zipfile.ZipFile( src ) | |
for m in zf.infolist(): | |
destdir = os.path.dirname(m.filename) | |
if not os.path.isdir(destdir) : | |
os.makedirs(destdir) | |
# Examine the header | |
print m.filename, m.header_offset, m.compress_size, repr(m.extra), repr(m.comment) | |
src.seek( m.header_offset ) | |
src.read( 30 ) # Good to use struct to unpack this. | |
nm= src.read( len(m.filename) ) | |
if len(m.extra) > 0: ex= src.read( len(m.extra) ) | |
if len(m.comment) > 0: cm= src.read( len(m.comment) ) | |
# Build a decompression object | |
decomp= zlib.decompressobj(-15) | |
# This can be done with a loop reading blocks | |
out= open( m.filename, "wb" ) | |
result= decomp.decompress( src.read( m.compress_size ) ) | |
out.write( result ) | |
result = decomp.flush() | |
out.write( result ) | |
# end of the loop | |
out.close() | |
zf.close() | |
src.close() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment