Question

I am trying to write a program that would read all files in a folder and output all of their contents into one single file. The files are ziped with the .gz extension. I managed to read one file but not all its contents and not the rest of the files. Here is my code:

import glob, gzip, re
import pickle

filed = open('Logs.txt', 'w')


logfilenames = glob.glob('*.gz')




logformat = re.compile(r'^\S+ \S+ \S+ \[([\w:/]+\s[+\-]\d{4})\] "(\S+) (\S+) .*" (\d+) (\d+) "([^"]*)" "[^"]*"')
with gzip.GzipFile(logfilenames[0],'r') as f:
    for i in glob.glob('*.gz'):
        txtline = f.readline()
        parsedline = logformat.match(txtline)
        print "time={t} size={s} url={u}".format(t=parsedline.group(1), s=parsedline.group(5), u=parsedline.group(3))

        pickle.dump(["time={t} size={s} url={u}".format(t=parsedline.group(1), s=parsedline.group(5), u=parsedline.group(3))],filed)

filed.close()

Answer 1

Try this (didn’t touch your regular expression):

import glob, gzip, re
import cPickle

logformat = re.compile(r'^\S+ \S+ \S+ \[([\w:/]+\s[+\-]\d{4})\] "(\S+) (\S+) .*" (\d+) (\d+) "([^"]*)" "[^"]*"')

with open('Logs.txt', 'w') as f_out:
    for i in glob.glob('*.gz'):
        with gzip.GzipFile(i,'r') as f_in:
            for txtline in f_in:
                parsedline = logformat.match(txtline)
                if parsedline:
                    f_out.write("time={t} size={s} url={u}".format(t=parsedline.group(1), s=parsedline.group(5), u=parsedline.group(3)))