Hello i have a small python script its job is to read data from a TXT file and sort it in a specific remove duplicate and remove none sense data and put it back in another TXT file this format MAC IP Number Device
import re
f = open('frame.txt', 'r')
d = open('Result1.txt', 'w')
mac=""
ip=""
phoneName=""
phoneTel=""
lmac=""
lip=""
lphoneName=""
lphoneTel=""
lines=f.readlines()
s=0
p=0
for line in lines:
matchObj = re.search( '(?<=Src: )[0-9a-z]{2}:[0-9a-z]{2}:[0-9a-z]{2}:[0-9a-z]{2}:[0-9a-z]{2}:[0-9a-z]{2}', line, re.M|re.I)
if(matchObj):
mac=matchObj.group(0)+"\t"
matchObj = re.search( '(?<=Src: )([0-9]+)(?:\.[0-9]+){3}', line, re.M|re.I)
if(matchObj):
ip=matchObj.group(0)+"\t"
if(s==1):
s=0
matchObj = re.search( '(?<=Value: )\d+',line,re.M|re.I)
if(matchObj):
phoneName=matchObj.group(0)+"\t"
if(p==1):
p=0
matchObj = re.search( '(?<=Value: ).+',line,re.M|re.I)
if(matchObj):
phoneTel=matchObj.group(0)+"\t"
matchObj = re.search( '(?<=Key: user \(218)', line, re.M|re.I)
if(matchObj):
s=1
matchObj = re.search( '(?<=Key: resource \(165)', line, re.M|re.I)
if(matchObj):
p=1
if(mac!="" and ip!="" and phoneName!="" and phoneTel!="" and mac!=lmac and ip!=lip and phoneName!=lphoneName and phoneTel!=lphoneTel):
d.write(mac+" " +ip+" "+ phoneName+" "+ phoneTel)
lmac=mac
lip=ip
lphoneName=phoneName
lphoneTel=phoneTel
d.write("\n")
matchObj = re.search( 'Frame \d+', line, re.M|re.I)
if(matchObj):
mac=""
ip=""
phoneName=""
phoneTel=""
d.close()
f.close()
here the code the problem is that the code need to process HUGE amount of data that might reach 100GB and when I'm doing so the program freezes and kill itself any idea how to fix this problem thank you so much!
awk. What does your file look like?