Python ungzipping stream of bytes?
Question:
Here is the situation:
-
I get gzipped xml documents from Amazon S3
import boto
from boto.s3.connection import S3Connection
from boto.s3.key import Key
conn = S3Connection('access Id', 'secret access key')
b = conn.get_bucket('mydev.myorg')
k = Key(b)
k.key('documents/document.xml.gz')
-
I read them in file as
import gzip
f = open('/tmp/p', 'w')
k.get_file(f)
f.close()
r = gzip.open('/tmp/p', 'rb')
file_content = r.read()
r.close()
Question
How can I ungzip the streams directly and read the contents?
I do not want to create temp files, they don’t look good.
Answers:
Yes, you can use the zlib
module to decompress byte streams:
import zlib
def stream_gzip_decompress(stream):
dec = zlib.decompressobj(32 + zlib.MAX_WBITS) # offset 32 to skip the header
for chunk in stream:
rv = dec.decompress(chunk)
if rv:
yield rv
The offset of 32 signals to the zlib
header that the gzip header is expected but skipped.
The S3 key object is an iterator, so you can do:
for data in stream_gzip_decompress(k):
# do something with the decompressed data
You can try PIPE and read contents without downloading file
import subprocess
c = subprocess.Popen(['-c','zcat -c <gzip file name>'], shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
for row in c.stdout:
print row
In addition “/dev/fd/” + str(c.stdout.fileno()) will provide you FIFO file name (Named pipe) which can be passed to other program.
I had to do the same thing and this is how I did it:
import gzip
f = StringIO.StringIO()
k.get_file(f)
f.seek(0) #This is crucial
gzf = gzip.GzipFile(fileobj=f)
file_content = gzf.read()
For Python3x and boto3-
So I used BytesIO to read the compressed file into a buffer object, then I used zipfile to open the decompressed stream as uncompressed data and I was able to get the datum line by line.
import io
import zipfile
import boto3
import sys
s3 = boto3.resource('s3', 'us-east-1')
def stream_zip_file():
count = 0
obj = s3.Object(
bucket_name='MonkeyBusiness',
key='/Daily/Business/Banana/{current-date}/banana.zip'
)
buffer = io.BytesIO(obj.get()["Body"].read())
print (buffer)
z = zipfile.ZipFile(buffer)
foo2 = z.open(z.infolist()[0])
print(sys.getsizeof(foo2))
line_counter = 0
for _ in foo2:
line_counter += 1
print (line_counter)
z.close()
if __name__ == '__main__':
stream_zip_file()
Here is the situation:
-
I get gzipped xml documents from Amazon S3
import boto from boto.s3.connection import S3Connection from boto.s3.key import Key conn = S3Connection('access Id', 'secret access key') b = conn.get_bucket('mydev.myorg') k = Key(b) k.key('documents/document.xml.gz')
-
I read them in file as
import gzip f = open('/tmp/p', 'w') k.get_file(f) f.close() r = gzip.open('/tmp/p', 'rb') file_content = r.read() r.close()
Question
How can I ungzip the streams directly and read the contents?
I do not want to create temp files, they don’t look good.
Yes, you can use the zlib
module to decompress byte streams:
import zlib
def stream_gzip_decompress(stream):
dec = zlib.decompressobj(32 + zlib.MAX_WBITS) # offset 32 to skip the header
for chunk in stream:
rv = dec.decompress(chunk)
if rv:
yield rv
The offset of 32 signals to the zlib
header that the gzip header is expected but skipped.
The S3 key object is an iterator, so you can do:
for data in stream_gzip_decompress(k):
# do something with the decompressed data
You can try PIPE and read contents without downloading file
import subprocess
c = subprocess.Popen(['-c','zcat -c <gzip file name>'], shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
for row in c.stdout:
print row
In addition “/dev/fd/” + str(c.stdout.fileno()) will provide you FIFO file name (Named pipe) which can be passed to other program.
I had to do the same thing and this is how I did it:
import gzip
f = StringIO.StringIO()
k.get_file(f)
f.seek(0) #This is crucial
gzf = gzip.GzipFile(fileobj=f)
file_content = gzf.read()
For Python3x and boto3-
So I used BytesIO to read the compressed file into a buffer object, then I used zipfile to open the decompressed stream as uncompressed data and I was able to get the datum line by line.
import io
import zipfile
import boto3
import sys
s3 = boto3.resource('s3', 'us-east-1')
def stream_zip_file():
count = 0
obj = s3.Object(
bucket_name='MonkeyBusiness',
key='/Daily/Business/Banana/{current-date}/banana.zip'
)
buffer = io.BytesIO(obj.get()["Body"].read())
print (buffer)
z = zipfile.ZipFile(buffer)
foo2 = z.open(z.infolist()[0])
print(sys.getsizeof(foo2))
line_counter = 0
for _ in foo2:
line_counter += 1
print (line_counter)
z.close()
if __name__ == '__main__':
stream_zip_file()