PYTHON

python gzip

# GZIP compress bytes
import gzip

s_in = b"some random text"
s_out = gzip.compress(s_in)


# GZIP decompress bytes
import gzip

s_in = b"some random text"
s_out = gzip.compress(s_in)
print(s_out)
print(gzip.decompress(s_out))



# GZIP compress file
import gzip
import shutil

with open('/mypath/file.txt', 'rb') as f_in:
    with gzip.open('/mypath/file.txt.gz', 'wb') as f_out:
        shutil.copyfileobj(f_in, f_out)

# GZIP Decompress file
import gzip
import shutil
with gzip.open('file.txt.gz', 'rb') as f_in:
    with open('file.txt', 'wb') as f_out:
        shutil.copyfileobj(f_in, f_out)

# GZIP Compress file from command line

python3.10 -m gzip --fast test.txt # fast compression
python3.10 -m gzip --best test.txt # best compression


# GZIP Decompress file from command line
python3.10 -m gzip -d test.txt.gz

python gzip file

import gzip
f_in = open('/home/joe/file.txt')
f_out = gzip.open('/home/joe/file.txt.gz', 'wb')
f_out.writelines(f_in)
f_out.close()
f_in.close()

python gzip a file

import gzip
import shutil
with open('/home/joe/file.txt', 'rb') as f_in:
    with gzip.open('/home/joe/file.txt.gz', 'wb') as f_out:
        shutil.copyfileobj(f_in, f_out)

download gzip file python

def download_dataset(url, target_path="data/", keep_download=True, overwrite_download=False):
	"""Downloads dataset from a url.
	url: string, a dataset path
	target_path: string, path where data will be downloaded
	keep_download: boolean, keeps the original file after extraction
	overwrite_download: boolean, stops download if dataset already exists
	"""
	if url == "" or url is None:
		raise Exception(EMPTY_URL_ERROR)

	filename = get_filename(url)
	file_location = get_file_location(target_path, filename)

	os.makedirs(data_dir, exist_ok=True)

	if os.path.exists(file_location) and not overwrite_download:
		print(f"File already exists at {file_location}. Use: 'overwrite_download=True' to 
overwrite download")
		extract_file(target_path, filename)
		return

	print(f"Downloading file from {url} to {file_location}.")
	# Download
	with open(file_location, 'wb') as f:
		with requests.get(url, allow_redirects=True, stream=True) as resp:
			for chunk in resp.iter_content(chunk_size = 512):  #chunk_size in bytes
				if chunk:
					f.write(chunk)

	print("Finished downloading.")
	print("Extracting the file now ...")
	extract_file(target_path, filename)

	if not keep_download:
		os.remove(file_location)