MobaXterm_regex.md

MobaXterm session export data extraction

Below regex pattern help to extract needful information from Portable export of SSH sessions. Although not complete, can help data extraction from export file.

SSH_pattern = r'(?<Servername>[\w. ()]+)=#(?<Type>\d+)#0%(?<IP>[\w.]+)%(?<port>\d+)%%%([\w.-]+)%([\d-]+)%%%([\w.-]+)%%\d%([\w.-]+)%([\w

Take a look at .mxtsessions file format

Pandas data extraction

import pandas as pd
import re
from os import chdir
chdir(r'/Mobaxterm/')

moba_ssh_text = r'MobaXterm Sessions.mxtsessions'
text = open(moba_ssh_text).readlines()

regex_pat = r"((?P<Servername>[\w. ()]+)=#(?P<Type>\d+)#0%(?P<IP>[\w.]+)%(?P<port>\d+)%%%([\w.-]+)%([\d-]+)%%%([\w.-]+)%%\d%([\w.-]+)%([\w.-]+)%%%([\w.-]+)%([\w.-]+)%([\w.-]+)%([\w.-]+)%%\d+%%\d%\d%\d#)"

df = pd.DataFrame(text)
df = df[0].str.extract(pat=regex_pat, expand=True)

df = df.dropna()
df.drop(columns=[0], inplace=True)

Text play for data extraction

import re

regex = r"(?<Servername>[\w. ()]+)=#(?<Type>\d+)#0%(?<IP>[\w.]+)%(?<port>\d+)%%%([\w.-]+)%([\d-]+)%%%([\w.-]+)%%\d%([\w.-]+)%([\w.-]+)%%%([\w.-]+)%([\w.-]+)%([\w.-]+)%([\w.-]+)%%\d+%%\d%\d%\d#"

test_str = ("1.2.3.47=#109#0%1.2.3.47%22%%%-1%-1%%%22%%0%-1%0%%%-1%0%0%0%%1080%%0%0%1#MobaFont%10%0%0%0%15%236,236,236%0,0,0%180,180,192%0%-1%0%%xterm%-1%0%0,0,0%54,54,54%255,96,96%255,128,128%96,255,96%128,255,128%255,255,54%255,255,128%96,96,255%128,128,255%255,54,255%255,128,255%54,255,255%128,255,255%236,236,236%255,255,255%80%24%0%1%-1%<none>%%0#0# #-1\n"
	"10.11.12.13=#109#0%10.11.12.13%6379%%%-1%-1%%%22%%0%-1%0%%%-1%0%0%0%%1080%%0%0%1#MobaFont%10%0%0%0%15%236,236,236%0,0,0%180,180,192%0%-1%0%%xterm%-1%0%0,0,0%54,54,54%255,96,96%255,128,128%96,255,96%128,255,128%255,255,54%255,255,128%96,96,255%128,128,255%255,54,255%255,128,255%54,255,255%128,255,255%236,236,236%255,255,255%80%24%0%1%-1%<none>%%0#0# #-1\n")

matches = re.finditer(regex, test_str, re.MULTILINE)

for matchNum, match in enumerate(matches, start=1):
    
    print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
    
    for groupNum in range(0, len(match.groups())):
        groupNum = groupNum + 1
        
        print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))