Last active
December 14, 2015 07:39
-
-
Save hdf/5051805 to your computer and use it in GitHub Desktop.
ipfilter.dat generating script
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys, urllib2, zlib, os.path | |
urls = ['http://www.bluetack.co.uk/config/ads-trackers-and-bad-pr0n.gz', | |
'http://www.bluetack.co.uk/config/bogon.gz', | |
'http://www.bluetack.co.uk/config/dshield.gz', | |
'http://www.bluetack.co.uk/config/fornonlancomputers.gz', | |
'http://www.bluetack.co.uk/config/hijacked.gz', | |
'http://www.bluetack.co.uk/config/Microsoft.gz', | |
'http://www.bluetack.co.uk/config/spyware.gz', | |
'http://www.bluetack.co.uk/config/iana-multicast.gz', | |
'http://www.bluetack.co.uk/config/iana-private.gz', | |
'http://www.bluetack.co.uk/config/iana-reserved.gz', | |
'http://www.bluetack.co.uk/config/level1.gz'] | |
output = 'ipfilter.dat' | |
ipfilter = [] | |
def ip2int(ip): | |
exp = 3 | |
intip = 0 | |
for quad in ip.split('.'): | |
intip += (int(quad) * (256 ** exp)) | |
exp = exp - 1 | |
return intip | |
def import_old(file): | |
if not os.path.isfile(file): return | |
print "Importing " + file + "..." | |
f = open(file, 'r') | |
lines = f.readlines() | |
f.close() | |
i = 0 | |
while i < len(lines): | |
ip1 = ip2int(lines[i][:15]) | |
ip2 = ip2int(lines[i][18:33]) | |
ipfilter.append([lines[i][:15], lines[i][18:33], lines[i][42:-1].ljust(10), ip1, ip2, ip2-ip1]) | |
i += 1 | |
READ_BLOCK_SIZE = 1024*8 | |
def get_gzipped(url): | |
out = '' | |
request = urllib2.Request(url) | |
request.add_header('Accept-encoding', 'gzip,deflate') | |
response = urllib2.urlopen(request) | |
d = zlib.decompressobj(16+zlib.MAX_WBITS) | |
while True: | |
data = response.read(READ_BLOCK_SIZE) | |
if not data: break | |
out += d.decompress(data) | |
return out | |
def ip_format(ip): | |
return "{0:03d}.{1:03d}.{2:03d}.{3:03d}".format(*map(int, ip.split('.'))) | |
import_old(output) | |
import_old('n' + output) | |
for url in urls: | |
print "Downloading " + url + "..." | |
i = 0 | |
lines = get_gzipped(url).split('\n') | |
print "Processing " + str(len(lines)) + " entries..." | |
for row in lines: | |
if len(row) < 20: break | |
i += 1 | |
sys.stdout.write(str(i) + "/" + str(len(lines)) + " (" + str(int(100/(1.0*len(lines)/i))) + "%)\r") | |
sys.stdout.flush() | |
desc, ips = row.split(':') | |
ips = map(ip_format, ips.split('-')) | |
ip1 = ip2int(ips[0]) | |
ip2 = ip2int(ips[1]) | |
ipfilter.append([ips[0], ips[1], desc[0:10].ljust(10), ip1, ip2, ip2-ip1]) | |
print "Sorting...".ljust(40) | |
ipfilter.sort(key=lambda k: k[5], reverse=True) | |
ipfilter.sort(key=lambda k: k[3]) | |
print "Filtering..." | |
for e in enumerate(ipfilter): | |
sys.stdout.write(str(e[0]+1) + "/" + str(len(ipfilter)) + " (" + str(int(100/(1.0*len(ipfilter)/(e[0]+1)))) + "%)\r") | |
sys.stdout.flush() | |
while e[0] < len(ipfilter)-1 and (e[1][3] == ipfilter[e[0]+1][3] or ipfilter[e[0]+1][4] <= e[1][4]): | |
ipfilter.pop(e[0]+1) | |
print "Writing output...".ljust(40) | |
f = open(output + '_new.txt', 'w') | |
for row in ipfilter: | |
f.write(row[0] + ' - ' + row[1] + ' , 000 , ' + row[2] + "\n") | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment