import asyncio
from pprint import pprint

import asyncwhois

# pick a domain
domain = 'bitcoin.org'
# domain could also be a URL; asyncwhois uses tldextract to parse the URL
# domain = 'https://www.google.com?q=asyncwhois'

# basic example
query_string, parsed_dict = asyncwhois.whois(domain)
# query_string  # The semi-free text output from the whois server
# parsed_dict   # A dictionary of key:values extracted from `query_string`

# asyncio example
loop = asyncio.get_event_loop()
query_string, parsed_dict = loop.run_until_complete(asyncwhois.aio_whois(domain))

pprint(parsed_dict)
"""
{created: datetime.datetime(2008, 8, 18, 13, 19, 55),
 dnssec: 'unsigned',
 domain_name: 'bitcoin.org',
 expires: datetime.datetime(2029, 8, 18, 13, 19, 55),
 name_servers: ['dns1.registrar-servers.com', 'dns2.registrar-servers.com'],
 registrant_address: 'P.O. Box 0823-03411',
 registrant_city: 'Panama',
 registrant_country: 'PA',
 registrant_name: 'WhoisGuard Protected',
 registrant_organization: 'WhoisGuard, Inc.',
 registrant_state: 'Panama',
 registrant_zipcode: '',
 registrar: 'NAMECHEAP INC',
 status: ['clientTransferProhibited '
          'https://icann.org/epp#clientTransferProhibited'],
 updated: datetime.datetime(2019, 11, 24, 13, 58, 35, 940000)}
 ...
 """

# support for IPv4, IPv6, and ASNs too
ipv4 = "8.8.8.8"
query_string, parsed_dict = asyncwhois.whois(ipv4)
pprint(parsed_dict)
"""
{abuse_address: None,
 abuse_email: '[email protected]',
 abuse_handle: 'ABUSE5250-ARIN',
 abuse_name: 'Abuse',
 abuse_phone: '+1-650-253-0000',
 abuse_rdap_ref: 'https://rdap.arin.net/registry/entity/ABUSE5250-ARIN',
 cidr: '8.8.8.0/24',
 net_handle: 'NET-8-8-8-0-2',
 net_name: 'GOGL',
 net_range: '8.8.8.0 - 8.8.8.255',
 net_type: 'Direct Allocation',
 org_address: '1600 Amphitheatre Parkway',
 org_city: 'Mountain View',
 org_country: 'US',
 org_id: 'GOGL',
 ...
"""

domain = "https://google.com"
query_string, parsed_dict = asyncwhois.rdap(domain)
# OR with asyncio
query_string, parsed_dict = loop.run_until_complete(asyncwhois.aio_rdap(domain))

# Reusable client (caches the RDAP bootstrap server list, so it is faster for doing multiple calls)
client = asyncwhois.DomainClient()
for domain in ["google.com", "tesla.coffee", "bitcoin.org"]:
    query_string, parsed_dict = client.rdap(domain)
    # query_string, parsed_dict = await client.aio_rdap(domain)

# Using a proxy or need to configure something HTTP related? Try reconfiguring the client:
whodap_client = whodap.DNSClient.new_client(
    httpx_client=httpx.Client(proxies="https://proxy:8080")
)
# whodap_client = await whodap.DNSClient.new_aio_client(httpx_client=httpx.AsyncClient(proxies="https://proxy:8080"))
client = asyncwhois.DomainClient(whodap_client=whodap_client)

import whodap

tor_host = "localhost"
tor_port = 9050

# WHOIS
query_string, parsed_dict = asyncwhois.whois(
    "8.8.8.8", proxy_url=f"socks5:https://{tor_host}:{tor_port}"
)

# RDAP
import httpx
from httpx_socks import SyncProxyTransport, AsyncProxyTransport  # EXTERNAL DEPENDENCY for SOCKS Proxies 

transport = SyncProxyTransport.from_url(f"socks5:https://{tor_host}:{tor_port}")
httpx_client = httpx.Client(transport=transport)
whodap_client = whodap.IPv6Client.new_client(httpx_client=httpx_client)
query_string, parsed_dict = asyncwhois.rdap('2001:4860:4860::8888', whodap_client=whodap_client)

transport = AsyncProxyTransport.from_url(f"socks5:https://{tor_user}:{tor_pw}@{tor_host}:{tor_port}")
async with httpx.AsyncClient(transport=transport) as httpx_client:
    whodap_client = await whodap.DNSClient.new_aio_client(httpx_client=httpx_client)
    query_string, parsed_dict = await asyncwhois.aio_rdap('bitcoin.org', whodap_client=whodap_client)

Domain:	google.be
Status:	NOT AVAILABLE
Registered:	Tue Dec 12 2000

Registrant:
    Not shown, please visit www.dnsbelgium.be for webbased whois.

Registrar Technical Contacts:
    Organisation:	MarkMonitor Inc.
    Language:	en
    Phone:	+1.2083895740
    Fax:	+1.2083895771

Registrar:
    Name:	 MarkMonitor Inc.
    Website: http://www.markmonitor.com

Nameservers:
    ns2.google.com
    ns1.google.com
    ns4.google.com
    ns3.google.com

Keys:

Flags:
    clientTransferProhibited
...

class RegexBE(BaseParser):
    _be_expressions = {  # the base class (BaseParser) will handle these regexes
        BaseKeys.CREATED: r'Registered: *(.+)',
        BaseKeys.REGISTRAR: r'Registrar:\n.+Name: *(.+)',
        BaseKeys.REGISTRANT_NAME: r'Registrant:\n *(.+)'
    }
    
    def __init__(self):
        super().__init__()
        self.update_reg_expressions(self._be_expressions)
    
    def parse(self, blob: str) -> Dict[str, Any]:
        # run base class parsing for other keys
        parsed_output = super().parse(blob)
        # custom parsing is needed to extract all the name servers
        ns_match = re.search(r"Name servers: *(.+)Keys: ", blob, re.DOTALL)
        if ns_match:
            parsed_output[BaseKeys.NAME_SERVERS] = [m.strip() for m in ns_match.group(1).split('\n') if m.strip()]
        return parsed_output