程序员最近都爱上了这个网站  程序员们快来瞅瞅吧！  it98k网:it98k.com

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

import zlib, sys
 
filename_in = "data"
filename_out = "compressed_data"
 
with open(filename_in, mode="rb") as fin, open(filename_out, mode="wb") as fout:
    data = fin.read()
    compressed_data = zlib.compress(data, zlib.Z_BEST_COMPRESSION)
    print(f"Original size: {sys.getsizeof(data)}")
    # Original size: 1000033
    print(f"Compressed size: {sys.getsizeof(compressed_data)}")
    # Compressed size: 1024
 
    fout.write(compressed_data)
 
with open(filename_out, mode="rb") as fin:
    data = fin.read()
    compressed_data = zlib.decompress(data)
    print(f"Compressed size: {sys.getsizeof(data)}")
    # Compressed size: 1024
    print(f"Decompressed size: {sys.getsizeof(compressed_data)}")
    # Decompressed size: 1000033

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17

import bz2, os, sys
 
filename_in = "data"
filename_out = "compressed_data.bz2"
 
with open(filename_in, mode="rb") as fin, bz2.open(filename_out, "wb") as fout:
    fout.write(fin.read())
 
print(f"Uncompressed size: {os.stat(filename_in).st_size}")
# Uncompressed size: 1000000
print(f"Compressed size: {os.stat(filename_out).st_size}")
# Compressed size: 48
 
with bz2.open(filename_out, "rb") as fin:
    data = fin.read()
    print(f"Decompressed size: {sys.getsizeof(data)}")
    # Decompressed size: 1000033

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

import lzma, os
lzc = lzma.LZMACompressor()
 
# cat /usr/share/dict/words | sort -R | head -c 1MB > data
filename_in = "data"
filename_out = "compressed_data.xz"
 
with open(filename_in, mode="r") as fin, open(filename_out, "wb") as fout:
    for chunk in fin.read(1024):
        compressed_chunk = lzc.compress(chunk.encode("ascii"))
        fout.write(compressed_chunk)
    fout.write(lzc.flush())
 
print(f"Uncompressed size: {os.stat(filename_in).st_size}")
# Uncompressed size: 972398
print(f"Compressed size: {os.stat(filename_out).st_size}")
# Compressed size: 736
 
with lzma.open(filename_out, "r") as fin:
    words = fin.read().decode("utf-8").split()
    print(words[:5])
    # ['dabbing', 'hauled', "seediness's", 'Iroquoian', 'vibe']

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18

import os, sys, shutil, gzip
 
filename_in = "data"
filename_out = "compressed_data.tar.gz"
 
with open(filename_in, "rb") as fin, gzip.open(filename_out, "wb") as fout:
    # Reads the file by chunks to avoid exhausting memory
    shutil.copyfileobj(fin, fout)
 
print(f"Uncompressed size: {os.stat(filename_in).st_size}")
# Uncompressed size: 1000000
print(f"Compressed size: {os.stat(filename_out).st_size}")
# Compressed size: 1023
 
with gzip.open(filename_out, "rb") as fin:
    data = fin.read()
    print(f"Decompressed size: {sys.getsizeof(data)}")
    # Decompressed size: 1000033

1
2
3
4
5
6
7
8
9
10
11
12
13
14

python3 -m gzip -h
usage: gzip.py [-h] [--fast | --best | -d] [file [file ...]]
...
 
ls -l data*
-rw-rw-r-- 1 martin martin 1000000 aug 22 18:48 data
 
# Use fast compression on file "data"
python3 -m gzip --fast data
 
# File named "data.gz" was generated:
ls -l data*
-rw-rw-r-- 1 martin martin 1000000 aug 22 18:48 data
-rw-rw-r-- 1 martin martin    1008 aug 22 20:50 data.gz

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33

import zipfile
 
# shuf -n5 /usr/share/dict/words > words.txt
files = ["words1.txt", "words2.txt", "words3.txt", "words4.txt", "words5.txt"]
archive = "archive.zip"
password = b"verysecret"
 
with zipfile.ZipFile(archive, "w") as zf:
    for file in files:
        zf.write(file)
 
    zf.setpassword(password)
 
with zipfile.ZipFile(archive, "r") as zf:
    crc_test = zf.testzip()
    if crc_test is not None:
        print(f"Bad CRC or file headers: {crc_test}")
 
    info = zf.infolist()  # also zf.namelist()
    print(info)  
    # See all attributes at https://docs.python.org/3/library/zipfile.html#zipinfo-objects
    # [ <ZipInfo filename='words1.txt' filemode='-rw-r--r--' file_size=37>,
    #   <ZipInfo filename='words2.txt' filemode='-rw-r--r--' file_size=47>,
    #   ... ]
 
    file = info[0]
    with zf.open(file) as f:
        print(f.read().decode())
        # Olav
        # teakettles
        # ...
 
    zf.extract(file, "/tmp", pwd=password)  # also zf.extractall()

1
2
3
4

with zipfile.ZipFile(archive, "a") as zf:
    zf.write("words6.txt")
    print(zf.namelist())
    # ['words1.txt', 'words2.txt', 'words3.txt', 'words4.txt', 'words5.txt', 'words6.txt']

1
2
3
4
5
6
7

python3 -m zipfile -c arch.zip words1.txt words2.txt  # Create
python3 -m zipfile -t arch.zip  # Test
Done testing
 
python3 -m zipfile -e arch.zip /tmp  # Extract
ls /tmp/words*
/tmp/words1.txt  /tmp/words2.txt

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29

import tarfile
 
files = ["words1.txt", "words2.txt", "words3.txt", "words4.txt"]
archive = "archive.tar.gz"
 
with tarfile.open(archive, "w:gz") as tar:
    for file in files:
        tar.add(file)  # can also be dir (added recursively), symlink, etc
 
    print(f"archive contains: {tar.getmembers()}")
    # [<TarInfo 'words1.txt' at 0x7f71ed74f8e0>,
    #  <TarInfo 'words2.txt' at 0x7f71ed74f9a8>
    #  ... ]
 
    info = tar.gettarinfo("words1.txt")  # Other Linux attributes - https://docs.python.org/3/library/tarfile.html#tarinfo-objects
    print(f"{tar.name} contains {info.name} with permissions {oct(info.mode)[-3:]}, size: {info.size} and owner: {info.uid}:{info.gid}")
    # .../archive.tar contains words1.txt with permissions 644, size: 37 and owner: 500:500
 
    def change_permissions(tarinfo):
        tarinfo.mode = 0o100600  # -rw-------.
        return tarinfo
    
    tar.add("words5.txt", filter=change_permissions)
 
    tar.list()
    # -rw-r--r-- martin/martin   37 2021-08-23 09:01:56 words1.txt
    # -rw-r--r-- martin/martin   47 2021-08-23 09:02:06 words2.txt
    # ...
    # -rw------- martin/martin   42 2021-08-23 09:02:22 words5.txt

1
2
3
4

with tarfile.open(archive, "r:gz") as tar:
    member = tar.getmember("words3.txt")
    if member.isfile():
        tar.extract(member, "/tmp/")