"""
NetDB scraping code 

This is used to obtain a list of IPs from our local NetDB cache. The RegEX needs some work.

Coded by Adrian Crenshaw
Please excuse the sloppiness of the code, I've only recently began to learn Python
http://irongeek.com
"""
#
import sys
import urllib2
import threading
from threading import Thread
import time
from datetime import datetime
import string
import os
import re
#ScanStartedTime = string.replace(string.replace(str(datetime.now())," ", "-"),":","-")
#OutputFile=open('temp-router-ips-' + ScanStartedTime + '.txt', 'wb',1)
OutputFile=open('all-sorted-uniq.txt', 'ab',1)
netdbdir= 'C:\\Windows\\SysWOW64\\config\\systemprofile\\AppData\\Roaming\\I2P\\netDb\\'
for root, dirs, files  in os.walk(netdbdir):
    for afile in files:
        #print "-----"+  afile +"-----"
        InputFile = open(netdbdir + afile,'rb')
        TextBlob= str(InputFile.read())
		#help from http://www.regular-expressions.info/examples.html
        IPsInFile = re.findall('(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)',TextBlob)
        for RouterIP in IPsInFile:
            OutputFile.write(RouterIP + '\n')
        InputFile.close()

OutputFile.close()
TheInput=open("all-sorted-uniq.txt",'r').readlines()
Output= sorted(list(set(TheInput)))
open("all-sorted-uniq.txt",'wb').writelines(Output)