# -*- coding: utf-8 -*-
from __future__ import print_function
from __future__ import absolute_import
from __future__ import unicode_literals
from __future__ import division
from future import standard_library
standard_library.install_aliases()
from builtins import *
import re
import sys
import os
import subprocess
import socket
from .parser import WhoisEntry
from .whois import NICClient
# thanks to https://www.regextester.com/104038
IPV4_OR_V6 = re.compile(r"((^\s*((([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5]))\s*$)|(^\s*((([0-9A-Fa-f]{1,4}:){7}([0-9A-Fa-f]{1,4}|:))|(([0-9A-Fa-f]{1,4}:){6}(:[0-9A-Fa-f]{1,4}|((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){5}(((:[0-9A-Fa-f]{1,4}){1,2})|:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){4}(((:[0-9A-Fa-f]{1,4}){1,3})|((:[0-9A-Fa-f]{1,4})?:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){3}(((:[0-9A-Fa-f]{1,4}){1,4})|((:[0-9A-Fa-f]{1,4}){0,2}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){2}(((:[0-9A-Fa-f]{1,4}){1,5})|((:[0-9A-Fa-f]{1,4}){0,3}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){1}(((:[0-9A-Fa-f]{1,4}){1,6})|((:[0-9A-Fa-f]{1,4}){0,4}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(:(((:[0-9A-Fa-f]{1,4}){1,7})|((:[0-9A-Fa-f]{1,4}){0,5}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:)))(%.+)?\s*$))")
def whois(url, command=False, flags=0):
# clean domain to expose netloc
ip_match = IPV4_OR_V6.match(url)
if ip_match:
domain = url
try:
result = socket.gethostbyaddr(url)
except socket.herror as e:
pass
else:
domain = extract_domain(result[0])
else:
domain = extract_domain(url)
if command:
# try native whois command
r = subprocess.Popen(['whois', domain], stdout=subprocess.PIPE)
text = r.stdout.read().decode()
else:
# try builtin client
nic_client = NICClient()
text = nic_client.whois_lookup(None, domain.encode('idna'), flags)
return WhoisEntry.load(domain, text)
suffixes = None
def extract_domain(url):
"""Extract the domain from the given URL
>>> print(extract_domain('http://www.google.com.au/tos.html'))
google.com.au
>>> print(extract_domain('abc.def.com'))
def.com
>>> print(extract_domain(u'www.公司.hk'))
公司.hk
>>> print(extract_domain('chambagri.fr'))
chambagri.fr
>>> print(extract_domain('www.webscraping.com'))
webscraping.com
>>> print(extract_domain('198.252.206.140'))
stackoverflow.com
>>> print(extract_domain('102.112.2O7.net'))
2o7.net
>>> print(extract_domain('globoesporte.globo.com'))
globo.com
>>> print(extract_domain('1-0-1-1-1-0-1-1-1-1-1-1-1-.0-0-0-0-0-0-0-0-0-0-0-0-0-10-0-0-0-0-0-0-0-0-0-0-0-0-0.info'))
0-0-0-0-0-0-0-0-0-0-0-0-0-10-0-0-0-0-0-0-0-0-0-0-0-0-0.info
>>> print(extract_domain('2607:f8b0:4006:802::200e'))
1e100.net
>>> print(extract_domain('172.217.3.110'))
1e100.net
"""
if IPV4_OR_V6.match(url):
# this is an IP address
return socket.gethostbyaddr(url)[0]
# load known TLD suffixes
global suffixes
if not suffixes:
# downloaded from https://publicsuffix.org/list/public_suffix_list.dat
tlds_path = os.path.join(os.getcwd(), os.path.dirname(__file__), 'data', 'public_suffix_list.dat')
with open(tlds_path, encoding='utf-8') as tlds_fp:
suffixes = set(line.encode('utf-8') for line in tlds_fp.read().splitlines() if line and not line.startswith('//'))
if not isinstance(url, str):
url = url.decode('utf-8')
url = re.sub('^.*://', '', url)
url = url.split('/')[0].lower()
# find the longest suffix match
domain = b''
for section in reversed(url.split('.')):
if domain:
domain = b'.' + domain
domain = section.encode('utf-8') + domain
if domain not in suffixes:
break
return domain.decode('utf-8')
if __name__ == '__main__':
try:
url = sys.argv[1]
except IndexError:
print('Usage: %s url' % sys.argv[0])
else:
print(whois(url))
