Como faço para compactar gzip uma string em Python?
gzip.GzipFile
existe, mas isso é para objetos de arquivo - e quanto a strings simples?
Como faço para compactar gzip uma string em Python?
gzip.GzipFile
existe, mas isso é para objetos de arquivo - e quanto a strings simples?
gzip string in python
e é muito razoável IMO. Deve ser reaberto.
Respostas:
Se você quiser produzir uma gzip
string binária totalmente compatível, com o cabeçalho, etc., você pode usar gzip.GzipFile
junto com StringIO
:
try:
from StringIO import StringIO # Python 2.7
except ImportError:
from io import StringIO # Python 3.x
import gzip
out = StringIO()
with gzip.GzipFile(fileobj=out, mode="w") as f:
f.write("This is mike number one, isn't this a lot of fun?")
out.getvalue()
# returns '\x1f\x8b\x08\x00\xbd\xbe\xe8N\x02\xff\x0b\xc9\xc8,V\x00\xa2\xdc\xcc\xecT\x85\xbc\xd2\xdc\xa4\xd4"\x85\xfc\xbcT\x1d\xa0X\x9ez\x89B\tH:Q!\'\xbfD!?M!\xad4\xcf\x1e\x00w\xd4\xea\xf41\x00\x00\x00'
f = gzip.GzipFile(StringIO.StringIO(text)); result = f.read(); f.close(); return result
import zlib; my_string = "hello world"; my_bytes = zlib.compress(my_string.encode('utf-8')); my_hex = my_bytes.hex(); my_bytes2 = bytes.fromhex(my_hex); my_string2 = zlib.decompress(my_bytes); assert my_string == my_string2;
A maneira mais fácil é a zlib
codificação :
compressed_value = s.encode("zlib")
Então você descompacta com:
plain_string_again = compressed_value.decode("zlib")
s
é um objeto 2.x do Python do tipo str
.
s.encode('rot13')
,s.encode( 'base64' )
plain_string_again = compressed_value.decode("zlib")
str
em Python 3) e strings de byte (tipo bytes
). str
os objetos têm um encode()
método que retorna um bytes
objeto e os bytes
objetos têm um decode()
método que retorna a str
. O zlib
codec é especial porque pode ser convertido de bytes
para bytes
, portanto, não se encaixa nessa estrutura. Você pode usar codecs.encode(b, "zlib")
e codecs.decode(b, "slib")
para um bytes
objeto b
.
Versão Python3 da resposta de Sven Marnach de 2011:
import gzip
exampleString = 'abcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijmortenpunnerudengelstadrocksklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuvabcdefghijklmnopqrstuv123'
compressed_value = gzip.compress(bytes(exampleString,'utf-8'))
plain_string_again = gzip.decompress(compressed_value)
zlib
ainda é usado, gzip
realmente usa zlib
, consulte: docs.python.org/3/library/zlib.html e docs.python.org/3/library/gzip.html#module-gzip
Para quem deseja compactar um dataframe Pandas no formato JSON:
Testado com Python 3.6 e Pandas 0.23
import sys
import zlib, lzma, bz2
import math
def convert_size(size_bytes):
if size_bytes == 0:
return "0B"
size_name = ("B", "KB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB")
i = int(math.floor(math.log(size_bytes, 1024)))
p = math.pow(1024, i)
s = round(size_bytes / p, 2)
return "%s %s" % (s, size_name[i])
dataframe = pd.read_csv('...') # your CSV file
dataframe_json = dataframe.to_json(orient='split')
data = dataframe_json.encode()
compressed_data = bz2.compress(data)
decompressed_data = bz2.decompress(compressed_data).decode()
dataframe_aux = pd.read_json(decompressed_data, orient='split')
#Original data size: 10982455 10.47 MB
#Encoded data size: 10982439 10.47 MB
#Compressed data size: 1276457 1.22 MB (lzma, slow), 2087131 1.99 MB (zlib, fast), 1410908 1.35 MB (bz2, fast)
#Decompressed data size: 10982455 10.47 MB
print('Original data size: ', sys.getsizeof(dataframe_json), convert_size(sys.getsizeof(dataframe_json)))
print('Encoded data size: ', sys.getsizeof(data), convert_size(sys.getsizeof(data)))
print('Compressed data size: ', sys.getsizeof(compressed_data), convert_size(sys.getsizeof(compressed_data)))
print('Decompressed data size: ', sys.getsizeof(decompressed_data), convert_size(sys.getsizeof(decompressed_data)))
print(dataframe.head())
print(dataframe_aux.head())
s = "a long string of characters"
g = gzip.open('gzipfilename.gz', 'w', 5) # ('filename', 'read/write mode', compression level)
g.write(s)
g.close()
StringIO
mas não explica realmente como fazê-lo. Então, fazer essa pergunta aqui é totalmente válido, IMHO. No entanto, mais algumas tentativas antes de nos perguntar e nos contar sobre eles teriam sido legais.