测试是否为zip归档
#!/bin/env python
# -*- coding:utf-8 -*-
import zipfile
for filename in [ 'test.txt', 'test.zip',
'test.jpg', 'test.py' ]:
print '%20s %s' % (filename, zipfile.is_zipfile(filename))
输出：
[root@the5 py]# ls
test.jpg test.py test.txt test.zip
[root@the5 py]# ./test.py
test.txt False
test.zip True
test.jpg False
test.py False
[root@the5 py]#
查询zip归档文件列表
#!/bin/env python
# -*- coding:utf-8 -*-
import zipfile
zf = zipfile.ZipFile('test.zip', 'r')
print zf.namelist()
输出：
[root@the5 py]# ./zipfile_namelist.py
['test.txt']
[root@the5 py]# unzip -t test.zip
Archive: test.zip
testing: test.txt OK
No errors detected in compressed data of test.zip.
输出结果可以看出，与unzip命令得到的文件列表相同，查询更详细的归档信息可以使用如下方式
查询归档详细信息
import datetime
import zipfile
def print_info(archive_name):
zf = zipfile.ZipFile(archive_name)
for info in zf.infolist():
print info.filename
print '\tComment:\t', info.comment
print '\tModified:\t', datetime.datetime(*info.date_time)
print '\tSystem:\t\t', info.create_system, '(0 = Windows, 3 = Unix)'
print '\tZIP version:\t', info.create_version
print '\tCompressed:\t', info.compress_size, 'bytes'
print '\tUncompressed:\t', info.file_size, 'bytes'
print
if __name__ == '__main__':
print_info('IMG_201509.zip')
输出：
[root@the5 py]# ./test3.py
...
IMG_20150929_203432.jpg
Comment:
Modified: 2015-09-29 20:34:32
System: 0 (0 = Windows, 3 = Unix)
ZIP version: 63
Compressed: 5840550 bytes
Uncompressed: 5956792 bytes
IMG_20150930_091243.jpg
Comment:
Modified: 2015-09-30 09:12:42
System: 0 (0 = Windows, 3 = Unix)
ZIP version: 63
Compressed: 2818819 bytes
Uncompressed: 2932052 bytes
...
他会打印出归档中每个文件的详细信息
获取指定文件大小
import zipfile
zf = zipfile.ZipFile('example.zip')
for filename in [ 'README.txt', 'notthere.txt' ]:
try:
info = zf.getinfo(filename)
except KeyError:
print 'ERROR: Did not find %s in zip file' % filename
else:
print '%s is %d bytes' % (info.filename, info.file_size)
输出：
$ python zipfile_getinfo.py
README.txt is 75 bytes
ERROR: Did not find notthere.txt in zip file
提取文件
#!/bin/env python
# -*- coding:utf-8 -*-
import zipfile
zf = zipfile.ZipFile('vivo-201509.zip')
for filename in [ 'IMG_20150929_203432.jpg' ]:
try:
data = zf.read(filename)
except KeyError:
print 'ERROR: Did not find %s in zip file' % filename
else:
print filename
with open('img.jpg', 'wb') as f:
f.write(data)
创建归档
from zipfile_infolist import print_info
import zipfile
print 'creating archive'
zf = zipfile.ZipFile('zipfile_write.zip', mode='w')
try:
print 'adding README.txt'
zf.write('README.txt')
finally:
print 'closing'
zf.close()
print
print_info('zipfile_write.zip')
默认情况下，归档不会对文件进行压缩，只是有打包的作用
想要压缩，需要添加zlib模块
from zipfile_infolist import print_info
import zipfile
try:
import zlib
compression = zipfile.ZIP_DEFLATED
except:
compression = zipfile.ZIP_STORED
modes = { zipfile.ZIP_DEFLATED: 'deflated',
zipfile.ZIP_STORED: 'stored',
}
print 'creating archive'
zf = zipfile.ZipFile('zipfile_write_compression.zip', mode='w')
try:
print 'adding README.txt with compression mode', modes[compression]
zf.write('README.txt', compress_type=compression)
finally:
print 'closing'
zf.close()
print
print_info('zipfile_write_compression.zip')
输出：
$ python zipfile_write_compression.py
creating archive
adding README.txt with compression mode deflated
closing
README.txt
Comment:
Modified: 2007-12-16 10:08:50
System: 3 (0 = Windows, 3 = Unix)
ZIP version: 20
Compressed: 63 bytes
Uncompressed: 75 bytes
打包时文件重命名
from zipfile_infolist import print_info
import zipfile
zf = zipfile.ZipFile('zipfile_write_arcname.zip', mode='w')
try:
zf.write('README.txt', arcname='NOT_README.txt')
finally:
zf.close()
print_info('zipfile_write_arcname.zip')
输出：
$ python zipfile_write_arcname.py
NOT_README.txt
Comment:
Modified: 2007-12-16 10:08:50
System: 3 (0 = Windows, 3 = Unix)
ZIP version: 20
Compressed: 75 bytes
Uncompressed: 75 bytes
打包字符串数据到归档
from zipfile_infolist import print_info
import zipfile
msg = 'This data did not exist in a file before being added to the ZIP file'
zf = zipfile.ZipFile('zipfile_writestr.zip',
mode='w',
compression=zipfile.ZIP_DEFLATED,
)
try:
zf.writestr('from_string.txt', msg)
finally:
zf.close()
print_info('zipfile_writestr.zip')
zf = zipfile.ZipFile('zipfile_writestr.zip', 'r')
print zf.read('from_string.txt')
输出：
$ python zipfile_writestr.py
from_string.txt
Comment:
Modified: 2007-12-16 11:38:14
System: 3 (0 = Windows, 3 = Unix)
ZIP version: 20
Compressed: 62 bytes
Uncompressed: 68 bytes
向归档中追加文件
from zipfile_infolist import print_info
import zipfile
print 'creating archive'
zf = zipfile.ZipFile('zipfile_append.zip', mode='w')
try:
zf.write('README.txt')
finally:
zf.close()
print
print_info('zipfile_append.zip')
print 'appending to the archive'
zf = zipfile.ZipFile('zipfile_append.zip', mode='a')
try:
zf.write('README.txt', arcname='README2.txt')
finally:
zf.close()
print
print_info('zipfile_append.zip')
使用czipfile提升性能
dnf install python-devel
pip install czipfile
使用方法：只需把zipfile的关键字修改为czipfile就可以了
如下输出可知，300多兆大小的照片归档，解压效率差别还是蛮大的，值得使用
[root@the5 py]# du -sh ./vivo-201509.zip
354M ./vivo-201509.zip
[root@the5 py]# time ./test-zipfile.py
real 0m2.203s
user 0m1.464s
sys 0m0.542s
[root@the5 py]# time ./test-czipfile.py
real 0m1.630s
user 0m0.989s
sys 0m0.482s
参考：