Ran into a situation where an external vendor started sending csv files gzipped. The trouble was they started zipping only larger files. Since the system that ingested the files would break on a gz file I needed a routine to unzip the gz files and leave the non-zipped files alone.
def unzip_if_necessary(self, filename):
print "unzip_if_necessary: " + filename
f = open(filename)
# Read magic number (the first 2 bytes) and rewind.
magic_number = f.read(2)
f.seek(0)
f.close()
if magic_number == '\x1f\x8b':
print "gzip file"
data = ''
# with gzip.GzipFile(fileobj=f) as f:
with gzip.open(filename, 'rb') as f:
data = f.read()
print "Writing to " + filename
with open(filename, "w") as f:
f.write(data)
else:
print "csv file"