Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import re, sys, geoip
- with open("gy.txt", "r") as ins:
- array = []
- for line in ins:
- array.append(line)
- total = len(array)
- print "Total: " + str(total)
- ipfil = []
- for i in range(total):
- ips = re.findall( r'[0-9]+(?:\.[0-9]+){3}', array[i] )
- ok = len(ips)
- if ok == 1:
- ipfil.append(ips)
- print "Identifiable IP's: " + str(len(ipfil))
- urlest = total - len(ipfil)
- print "URL Amount Estimate: " + str(urlest)
- govc = 0
- for i in range(total):
- if ".gov" in array[i]:
- govc = govc + 1
- print "Estimated GOV Domains: " + str(govc)
- countries = (
- '', 'AP', 'EU', 'AD', 'AE', 'AF', 'AG', 'AI', 'AL', 'AM', 'AN', 'AO', 'AQ',
- 'AR', 'AS', 'AT', 'AU', 'AW', 'AZ', 'BA', 'BB', 'BD', 'BE', 'BF', 'BG', 'BH',
- 'BI', 'BJ', 'BM', 'BN', 'BO', 'BR', 'BS', 'BT', 'BV', 'BW', 'BY', 'BZ', 'CA',
- 'CC', 'CD', 'CF', 'CG', 'CH', 'CI', 'CK', 'CL', 'CM', 'CN', 'CO', 'CR', 'CU',
- 'CV', 'CX', 'CY', 'CZ', 'DE', 'DJ', 'DK', 'DM', 'DO', 'DZ', 'EC', 'EE', 'EG',
- 'EH', 'ER', 'ES', 'ET', 'FI', 'FJ', 'FK', 'FM', 'FO', 'FR', 'FX', 'GA', 'GB',
- 'GD', 'GE', 'GF', 'GH', 'GI', 'GL', 'GM', 'GN', 'GP', 'GQ', 'GR', 'GS', 'GT',
- 'GU', 'GW', 'GY', 'HK', 'HM', 'HN', 'HR', 'HT', 'HU', 'ID', 'IE', 'IL', 'IN',
- 'IO', 'IQ', 'IR', 'IS', 'IT', 'JM', 'JO', 'JP', 'KE', 'KG', 'KH', 'KI', 'KM',
- 'KN', 'KP', 'KR', 'KW', 'KY', 'KZ', 'LA', 'LB', 'LC', 'LI', 'LK', 'LR', 'LS',
- 'LT', 'LU', 'LV', 'LY', 'MA', 'MC', 'MD', 'MG', 'MH', 'MK', 'ML', 'MM', 'MN',
- 'MO', 'MP', 'MQ', 'MR', 'MS', 'MT', 'MU', 'MV', 'MW', 'MX', 'MY', 'MZ', 'NA',
- 'NC', 'NE', 'NF', 'NG', 'NI', 'NL', 'NO', 'NP', 'NR', 'NU', 'NZ', 'OM', 'PA',
- 'PE', 'PF', 'PG', 'PH', 'PK', 'PL', 'PM', 'PN', 'PR', 'PS', 'PT', 'PW', 'PY',
- 'QA', 'RE', 'RO', 'RU', 'RW', 'SA', 'SB', 'SC', 'SD', 'SE', 'SG', 'SH', 'SI',
- 'SJ', 'SK', 'SL', 'SM', 'SN', 'SO', 'SR', 'ST', 'SV', 'SY', 'SZ', 'TC', 'TD',
- 'TF', 'TG', 'TH', 'TJ', 'TK', 'TM', 'TN', 'TO', 'TL', 'TR', 'TT', 'TV', 'TW',
- 'TZ', 'UA', 'UG', 'UM', 'US', 'UY', 'UZ', 'VA', 'VC', 'VE', 'VG', 'VI', 'VN',
- 'VU', 'WF', 'WS', 'YE', 'YT', 'RS', 'ZA', 'ZM', 'ME', 'ZW', 'A1', 'A2', 'O1',
- 'AX', 'GG', 'IM', 'JE', 'BL', 'MF')
- #ip to country#
- '''countryc = [0]*253
- for i in range(len(ipfil)):
- print i
- if i == 100000:
- print "100000"
- elif i == 25000:
- print "250000"
- elif i == 50000:
- print "50000"
- ip = ''.join(ipfil[i])
- for i in range(len(countries)):
- if str(geoip.country(ip)) in str(countries[i]):
- countryc[i] = countryc[i] +1
- with open ("countries.txt", "w") as myfile:
- myfile.write(str(countryc))'''
- #format#
- '''with open("countries.txt", "r") as ins:
- for line in ins:
- splita = line.split(",")
- for i in range(253):
- construct = ''.join([countries[i], "=>", str(splita[i]).replace(" ", "")])
- print construct'''
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement