Added an enhanced dnsbl check, updated mirrors and license, etc

Fixed syntax error.

LICENSE

@@ -1,6 +1,6 @@
 ISC License
 
-Copyright (c) 2021, acidvegas <acid.vegas@acid.vegas>
+Copyright (c) 2024, acidvegas <acid.vegas@acid.vegas>
 
 Permission to use, copy, modify, and/or distribute this software for any
 purpose with or without fee is hereby granted, provided that the above

README.md

@@ -8,5 +8,4 @@
 
 ___
 
-###### Mirrors
-[acid.vegas](https://git.acid.vegas/proxytools) • [GitHub](https://github.com/acidvegas/proxytools) • [GitLab](https://gitlab.com/acidvegas/proxytools) • [SuperNETs](https://git.supernets.org/acidvegas/proxytools)
+###### Mirrors for this repository: [acid.vegas](https://git.acid.vegas/proxytools) • [SuperNETs](https://git.supernets.org/acidvegas/proxytools) • [GitHub](https://github.com/acidvegas/proxytools) • [GitLab](https://gitlab.com/acidvegas/proxytools) • [Codeberg](https://codeberg.org/acidvegas/proxytools)

cleansocks.py

@@ -1,80 +1,133 @@
 #!/usr/bin/env python
 # CleanSocks - Developed by acidvegas in Python (https://git.acid.vegas/proxytools)
 
-'''
-
-This script will clean a list of proxies by removing duplicates, checking for valid formats (IP:PORT), & testing if the proxies are working
-
-'''
+# This script will clean a list of proxies by removing duplicates, checking for valid formats (IP:PORT), & testing if the proxies are working
+# If a proxy is found working on multiple ports, we will only store the first working port to avoid ip duplication in the clean results.
 
 import argparse
 import asyncio
 import os
 import re
 
-# Globals
-all       = list()
-good      = list()
-print_bad = True
+try:
+	import aiosocks
+except ImportError:
+	raise SystemExit('missing pysocks module (https://pypi.org/project/aiosocks/)')
 
-async def check(semaphore, proxy):
+try:
+	import aiohttp
+except ImportError:
+	raise SystemExit('missing pysocks module (https://pypi.org/project/aiosocks/)')
+
+# Globals
+all  = list()
+good = list()
+
+async def check_http_proxy(semaphore: asyncio.Semaphore, proxy: str):
+	'''
+	Checks if a HTTP proxy is working.
+	
+	:param semaphore: The semaphore to use.
+	:param proxy: The proxy to check.
+	'''
 	async with semaphore:
-		ip, port = proxy.split(':')
+		proxy_ip = proxy.split(':')[0]
+		async with aiohttp.ClientSession() as session:
+			try:
+				async with session.get('https://google.com', proxy=f'http://{proxy}', timeout=args.timeout) as response:
+					if response.status == 200:
+						print('\033[1;32mGOOD\033[0m \033[30m|\033[0m ' + proxy)
+						if proxy_ip not in all:
+							all.append(proxy_ip)
+							good.append(proxy)
+					else:
+						if args.bad:
+							print('\033[1;31mBAD\033[0m  \033[30m|\033[0m ' + proxy)
+			except:
+				if args.bad:
+					print('\033[1;31mBAD\033[0m  \033[30m|\033[0m ' + proxy)
+
+async def check_socks_proxy(semaphore: asyncio.Semaphore, proxy: str):
+	'''
+	Checks if a SOCKS proxy is working.
+	
+	:param semaphore: The semaphore to use.
+	:param proxy: The proxy to check.
+	'''
+	async with semaphore:
+		proxy_ip, proxy_port = proxy.split(':')
 		options = {
-			'proxy'      : aiosocks.Socks5Addr(proxy.split(':')[0], int(proxy.split(':')[1])),
+			'proxy'      : aiosocks.Socks5Addr(proxy_ip, proxy_port),
 			'proxy_auth' : None,
-			'dst'        : ('www.google.com',80),
+			'dst'        : ('www.google.com', 80),
 			'limit'      : 1024,
 			'ssl'        : None,
 			'family'     : 2
 		}
 		try:
-		    await asyncio.wait_for(aiosocks.open_connection(**options), 15)
+			await asyncio.wait_for(aiosocks.open_connection(**options), args.timeout)
 		except:
-			if print_bad:
+			if args.bad:
 				print('\033[1;31mBAD\033[0m  \033[30m|\033[0m ' + proxy)
 		else:
 			print('\033[1;32mGOOD\033[0m \033[30m|\033[0m ' + proxy)
-			if ip not in all:
-				all.append(ip)
+			if proxy_ip not in all:
+				all.append(proxy_ip)
 				good.append(proxy)
 
 async def main(targets):
-	sema = asyncio.BoundedSemaphore(500)
+	'''
+	Starts the main event loop.
+	
+	:param targets: The proxies to check.
+	'''
+	sema = asyncio.BoundedSemaphore(args.threads)
 	jobs = list()
 	for target in targets:
-		jobs.append(asyncio.ensure_future(check(sema, target)))
+		if args.socks:
+			jobs.append(asyncio.ensure_future(check_socks_proxy(sema, target)))
+		else:
+			jobs.append(asyncio.ensure_future(check_http_proxy(sema, target)))
 	await asyncio.gather(*jobs)
 
-# Main
-print('#'*56)
-print('#{0}#'.format(''.center(54)))
-print('#{0}#'.format('CleanSOCKS Proxy Cleaner'.center(54)))
-print('#{0}#'.format('Developed by acidvegas in Python'.center(54)))
-print('#{0}#'.format('https://git.acid.vegas/proxytools'.center(54)))
-print('#{0}#'.format(''.center(54)))
-print('#'*56)
-parser = argparse.ArgumentParser(usage='%(prog)s <input> <output> [options]')
-parser.add_argument('input',           help='file to scan')
-parser.add_argument('output',          help='file to output')
-parser.add_argument('-t', '--threads', help='number of threads      (default: 100)', default=100, type=int)
-parser.add_argument('-x', '--timeout', help='socket timeout seconds (default: 15)',  default=15,  type=int)
-args = parser.parse_args()
-try:
-	import aiosocks
-except ImportError:
-	raise SystemExit('missing pysocks module (https://pypi.org/project/aiosocks/)')
-if not os.path.isfile(args.input):
-	raise SystemExit('no such input file')
-initial = len(open(args.input).readlines())
-proxies = set([proxy for proxy in re.findall('[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+:[0-9]+', open(args.input).read(), re.MULTILINE)])
-if not proxies:
-	raise SystemExit('no proxies found from input file')
-asyncio.run(main(proxies))
-good.sort()
-with open(args.output, 'w') as output_file:
-	output_file.write('\n'.join(good))
-print('\033[34mTotal\033[0m : ' + format(len(proxies),           ',d'))
-print('\033[34mGood\033[0m  : ' + format(len(good),              ',d'))
-print('\033[34mBad\033[0m   : ' + format(len(proxies)-len(good), ',d'))
-print('\033[34mDupe\033[0m  : ' + format(initial-len(proxies),   ',d'))
+
+if __name__ == '__main__':
+	print('#'*56)
+	print('#{0}#'.format(''.center(54)))
+	print('#{0}#'.format('CleanSOCKS Proxy Cleaner'.center(54)))
+	print('#{0}#'.format('Developed by acidvegas in Python'.center(54)))
+	print('#{0}#'.format('https://git.acid.vegas/proxytools'.center(54)))
+	print('#{0}#'.format(''.center(54)))
+	print('#'*56)
+
+	parser = argparse.ArgumentParser(usage='%(prog)s <input> <output> [options]')
+	parser.add_argument('input', help='file to scan')
+	parser.add_argument('output', help='file to output')
+	parser.add_argument('-s', '--socks', action='store_true', help='Check SOCKS proxies (default: HTTP)')
+	parser.add_argument('-b', '--bad', action='store_true', help='Show bad proxies')
+	parser.add_argument('-t', '--threads', help='number of threads      (default: 100)', default=100, type=int)
+	parser.add_argument('-x', '--timeout', help='socket timeout seconds (default:  15)', default=15, type=int)
+	args = parser.parse_args()
+
+	if not os.path.isfile(args.input):
+		raise SystemExit('no such input file')
+
+	initial = len(open(args.input).readlines())
+	proxies = set([proxy for proxy in re.findall(r'[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+:[0-9]+', open(args.input).read(), re.MULTILINE)])
+
+	if not proxies:
+		raise SystemExit('no proxies found from input file')
+
+
+	print('\033[1;32mChecking {0:,} {1} proxies using {2:,} threads... \033[1;30m(Pass the -h or --help argument to change these settings)\033[0m'.format(len(proxies), 'SOCKS' if args.socks else 'HTTP', args.threads))
+	asyncio.run(main(proxies))
+
+	good.sort()
+
+	with open(args.output, 'w') as output_file:
+		output_file.write('\n'.join(good))
+	
+	print('\033[34mTotal\033[0m : ' + format(len(proxies),           ',d'))
+	print('\033[34mGood\033[0m  : ' + format(len(good),              ',d'))
+	print('\033[34mBad\033[0m   : ' + format(len(proxies)-len(good), ',d'))
+	print('\033[34mDupe\033[0m  : ' + format(initial-len(proxies),   ',d'))

dnsbl.py

@@ -0,0 +1,617 @@
+#!/usr/bin/env python
+# DNSBL - Developed by acidvegas in Python (https://git.acid.vegas/proxytools)
+
+import argparse
+import asyncio
+import ipaddress
+import logging
+import os
+
+try:
+    import aiodns
+except ImportError:
+    raise SystemExit('missing required library \'aiodns\' (https://pypi.org/project/aiodns/)')
+
+# ANSI color codes
+RED   = '\033[91m'
+GREEN = '\033[92m'
+GREY  = '\033[90m'
+RESET = '\033[0m'
+
+DNSBL_LIST = [
+    '0outspam.fusionzero.com',
+    '0spam-killlist.fusionzero.com',
+    '0spam.fusionzero.com',
+    '0spamtrust.fusionzero.com',
+    '0spamurl.fusionzero.com',
+    '3y.spam.mrs.kithrup.com',
+    '88.blocklist.zap',
+    'abuse-contacts.abusix.org',
+    'abuse.rfc-clueless.org',
+    'abuse.rfc-ignorant.org',
+    'access.atlbl.net',
+    'access.redhawk.org',
+    'accredit.habeas.com',
+    'admin.bl.kundenserver.de',
+    'all.ascc.dnsbl.bit.nl',
+    'all.dnsbl.bit.nl',
+    'all.rbl.jp',
+    'all.rbl.webiron.net',
+    'all.s5h.net',
+    'all.spam-rbl.fr',
+    'all.spamblock.unit.liu.se',
+    'all.spamrats.com',
+    'all.v6.ascc.dnsbl.bit.nl',
+    'apnic-main.bogons.dnsiplists.completewhois.com',
+    'arin-legacy-classb.bogons.dnsiplists.completewhois.com',
+    'arin-legacy-classc.bogons.dnsiplists.completewhois.com',
+    'arin-main.bogons.dnsiplists.completewhois.com',
+    'asiaspam.spamblocked.com',
+    'asn.routeviews.org',
+    'aspath.routeviews.org',
+    'aspews.dnsbl.sorbs.net',
+    'aspews.ext.sorbs.net',
+    'assholes.madscience.nl',
+    'auth.spamrats.com',
+    'autowork.drbl.ks.cz',
+    'b.barracudacentral.org',
+    'babl.rbl.webiron.net',
+    'backscatter.spameatingmonkey.net',
+    'bad.psky.me',
+    'badconf.rhsbl.sorbs.net',
+    'badnets.spameatingmonkey.net',
+    'ban.zebl.zoneedit.com',
+    'bandwidth-pigs.monkeys.com',
+    'bb.barracudacentral.org',
+    'bitonly.dnsbl.bit.nl',
+    'bl.blocklist.de',
+    'bl.blueshore.net',
+    'bl.borderworlds.dk',
+    'bl.deadbeef.com',
+    'bl.drmx.org',
+    'bl.emailbasura.org',
+    'bl.fmb.la',
+    'bl.ipv6.spameatingmonkey.net',
+    'bl.konstant.no',
+    'bl.mailspike.net',
+    'bl.mailspike.org',
+    'bl.mav.com.br',
+    'bl.mipspace.com',
+    'bl.nszones.com',
+    'bl.rbl-dns.com',
+    'bl.reynolds.net.au',
+    'bl.scientificspam.net',
+    'bl.score.senderscore.com',
+    'bl.shlink.org',
+    'bl.shlink.orgdul.ru',
+    'bl.spamcannibal.org',
+    'bl.spamcop.net',
+    'bl.spameatingmonkey.net',
+    'bl.spamstinks.com',
+    'bl.spamthwart.com',
+    'bl.student.pw.edu.pl',
+    'bl.suomispam.net',
+    'bl.tiopan.com',
+    'bl.tolkien.dk',
+    'black.junkemailfilter.com',
+    'blackhole.compu.net',
+    'blackholes.brainerd.net',
+    'blackholes.easynet.nl',
+    'blackholes.five-ten-sg.com',
+    'blackholes.mail-abuse.org',
+    'blackholes.sandes.dk',
+    'blacklist.fpsn.net',
+    'blacklist.hostkarma.com',
+    'blacklist.informationwave.net',
+    'blacklist.mail.ops.asp.att.net',
+    'blacklist.mailrelay.att.net',
+    'blacklist.sci.kun.nl',
+    'blacklist.sci.ru.nl',
+    'blacklist.sequoia.ops.asp.att.net',
+    'blacklist.woody.ch',
+    'block.ascams.com',
+    'block.blars.org',
+    'block.dnsbl.sorbs.net',
+    'blocked.asgardnet.org',
+    'blocked.hilli.dk',
+    'blocklist.squawk.com',
+    'blocklist2.squawk.com',
+    'bogon.lbl.lagengymnastik.dk',
+    'bogons.cymru.com',
+    'bogons.dnsiplists.completewhois.com',
+    'bogusmx.rfc-clueless.org',
+    'bogusmx.rfc-ignorant.org',
+    'bsb.empty.us',
+    'bsb.spamlookup.net',
+    'cabl.rbl.webiron.net',
+    'cart00ney.surriel.com',
+    'catchspam.com',
+    'cbl.abuseat.org',
+    'cbl.anti-spam.org.cn',
+    'cblless.anti-spam.org.cn',
+    'cblplus.anti-spam.org.cn',
+    'ccess.redhawk.org',
+    'cdl.anti-spam.org.cn',
+    'china.rominet.net',
+    'cidr.bl.mcafee.com',
+    'client-domain.sjesl.monkeys.com',
+    'cml.anti-spam.org.cn',
+    'combined-hib.dnsiplists.completewhois.com',
+    'combined.abuse.ch',
+    'combined.njabl.org',
+    'combined.rbl.msrbl.net',
+    'communicado.fmb.la',
+    'contacts.abuse.net',
+    'country-rirdata.dnsiplists.completewhois.com',
+    'crawler.rbl.webiron.net',
+    'csi.cloudmark.com',
+    'czdynamic.drbl.ks.cz',
+    'db.rurbl.ru',
+    'db.wpbl.info',
+    'dbl.spamhaus.org',
+    'dbl.suomispam.net',
+    'dev.null.dk',
+    'devnull.drbl.be.net.ru',
+    'dialup.blacklist.jippg.org',
+    'dialup.drbl.sandy.ru',
+    'dialups.mail-abuse.org',
+    'dialups.visi.com',
+    'dnsbl-0.uceprotect.net',
+    'dnsbl-1.uceprotect.net',
+    'dnsbl-2.uceprotect.net',
+    'dnsbl-3.uceprotect.net',
+    'dnsbl.abuse.ch',
+    'dnsbl.anticaptcha.net',
+    'dnsbl.antispam.or.id',
+    'dnsbl.aspnet.hu',
+    'dnsbl.calivent.com.pe',
+    'dnsbl.cbn.net.id',
+    'dnsbl.clue-by-4.org',
+    'dnsbl.cobion.com',
+    'dnsbl.cyberlogic.net',
+    'dnsbl.delink.net',
+    'dnsbl.dronebl.org',
+    'dnsbl.forefront.microsoft.com',
+    'dnsbl.httpbl.org',
+    'dnsbl.inps.de',
+    'dnsbl.ioerror.us',
+    'dnsbl.justspam.org',
+    'dnsbl.kempt.net',
+    'dnsbl.madavi.de',
+    'dnsbl.mags.net',
+    'dnsbl.mailshell.net',
+    'dnsbl.mcu.edu.tw',
+    'dnsbl.net.ua',
+    'dnsbl.njabl.org',
+    'dnsbl.pagedirect.net',
+    'dnsbl.proxybl.org',
+    'dnsbl.rangers.eu.org',
+    'dnsbl.rizon.net',
+    'dnsbl.rv-soft.info',
+    'dnsbl.rymsho.ru',
+    'dnsbl.sorbs.net',
+    'dnsbl.spam-champuru.livedoor.com',
+    'dnsbl.spfbl.net',
+    'dnsbl.technoirc.org',
+    'dnsbl.tornevall.org',
+    'dnsbl.webequipped.com',
+    'dnsbl.wpbl.pc9.org',
+    'dnsbl.zapbl.net',
+    'dnsbl6.anticaptcha.net',
+    'dnsblchile.org',
+    'dnsrbl.org',
+    'dnsrbl.swinog.ch',
+    'dnswl.inps.de',
+    'dnswl.leisi.net',
+    'dob.sibl.support-intelligence.net',
+    'drone.abuse.ch',
+    'dronebl.noderebellion.net',
+    'dsn.bl.rfc-ignorant.de',
+    'dsn.rfc-clueless.org',
+    'dsn.rfc-ignorant.org',
+    'dssl.imrss.org',
+    'duinv.aupads.org',
+    'dul.blackhole.cantv.net',
+    'dul.dnsbl.sorbs.net',
+    'dul.dnsbl.sorbs.netdul.ru',
+    'dul.orca.bc.ca',
+    'dul.pacifier.net',
+    'dul.ru',
+    'dyn.nszones.com',
+    'dyna.spamrats.com',
+    'dynablock.easynet.nl',
+    'dynablock.sorbs.net',
+    'dynamic.dnsbl.rangers.eu.org',
+    'dyndns.rbl.jp',
+    'dynip.rothen.com',
+    'elitist.rfc-clueless.org',
+    'endn.bl.reynolds.net.au',
+    'escalations.dnsbl.sorbs.net',
+    'eswlrev.dnsbl.rediris.es',
+    'eurospam.spamblocked.com',
+    'ex.dnsbl.org',
+    'exitnodes.tor.dnsbl.sectoor.de',
+    'exitnodes.tor.dnsbl.sectoor.dehttp.dnsbl.sorbs.net',
+    'feb.spamlab.com',
+    'fnrbl.fast.net',
+    'forbidden.icm.edu.pl',
+    'formmail.relays.monkeys.com',
+    'free.v4bl.org',
+    'fresh.dict.rbl.arix.com',
+    'fresh.sa_slip.rbl.arix.com',
+    'fresh.spameatingmonkey.net',
+    'fresh10.spameatingmonkey.net',
+    'fresh15.spameatingmonkey.net',
+    'fulldom.rfc-clueless.org',
+    'geobl.spameatingmonkey.net',
+    'gl.suomispam.net',
+    'hbl.atlbl.net',
+    'helo-domain.sjesl.monkeys.com',
+    'hijacked.dnsiplists.completewhois.com',
+    'hil.habeas.com',
+    'hong-kong.rominet.net',
+    'hostkarma.junkemailfilter.com',
+    'hostkarma.junkemailfilter.com[brl]',
+    'http.dnsbl.sorbs.net',
+    'httpbl.abuse.ch',
+    'hul.habeas.com',
+    'iadb.isipp.com',
+    'iadb2.isipp.com',
+    'iana-classa.bogons.dnsiplists.completewhois.com',
+    'iddb.isipp.com',
+    'images.rbl.msrbl.net',
+    'in.dnsbl.org',
+    'inputs.orbz.org',
+    'intercept.datapacket.net',
+    'intruders.docs.uu.se',
+    'invalidipwhois.dnsiplists.completewhois.com',
+    'ip.v4bl.org',
+    'ipbl.zeustracker.abuse.ch',
+    'ips.backscatterer.org',
+    'ips.whitelisted.org',
+    'ipv6.all.dnsbl.bit.nl',
+    'ipv6.all.s5h.net',
+    'ipwhois.rfc-ignorant.org',
+    'is-tor.kewlio.net.uk',
+    'ispmx.pofon.foobar.hu',
+    'isps.spamblocked.com',
+    'ix.dnsbl.manitu.net',
+    'korea.rominet.net',
+    'korea.services.net',
+    'ksi.dnsbl.net.au',
+    'l1.apews.org',
+    'l1.apews.rhsbl.sorbs.net',
+    'l1.bbfh.ext.sorbs.net',
+    'l1.spews.dnsbl.sorbs.net',
+    'l2.apews.dnsbl.sorbs.net',
+    'l2.bbfh.ext.sorbs.net',
+    'l2.spews.dnsbl.sorbs.net',
+    'l3.bbfh.ext.sorbs.net',
+    'l4.bbfh.ext.sorbs.net',
+    'lacnic-main.bogons.dnsiplists.completewhois.com',
+    'lacnic.spamblocked.com',
+    'lame.dnsbl.rangers.eu.org',
+    'lbl.lagengymnastik.dk',
+    'list.anonwhois.net',
+    'list.bbfh.org',
+    'list.blogspambl.com',
+    'list.dnswl.org',
+    'list.quorum.to',
+    'mail-abuse.blacklist.jippg.org',
+    'mail.people.it',
+    'manual.orbz.gst-group.co.uk',
+    'misc.dnsbl.sorbs.net',
+    'mr-out.imrss.org',
+    'msgid.bl.gweep.ca',
+    'mtawlrev.dnsbl.rediris.es',
+    'multi.surbl.org',
+    'multi.uribl.com',
+    'netbl.spameatingmonkey.net',
+    'netblock.pedantic.org',
+    'netblockbl.spamgrouper.com',
+    'netblockbl.spamgrouper.to',
+    'netscan.rbl.blockedservers.com',
+    'new.dnsbl.sorbs.net',
+    'new.spam.dnsbl.sorbs.net',
+    'nml.mail-abuse.org',
+    'no-more-funn.moensted.dk',
+    'nobl.junkemailfilter.com',
+    'nomail.rhsbl.sorbs.net',
+    'noptr.spamrats.com',
+    'noservers.dnsbl.sorbs.net',
+    'nospam.ant.pl',
+    'nsbl.fmb.la',
+    'old.dnsbl.sorbs.net',
+    'old.spam.dnsbl.sorbs.net',
+    'omrs.dnsbl.net.au',
+    'opm.tornevall.org',
+    'orbs.dorkslayers.com',
+    'orbz.gst-group.co.uk',
+    'origin.asn.cymru.com',
+    'origin.asn.spameatingmonkey.net',
+    'origin6.asn.cymru.com',
+    'orvedb.aupads.org',
+    'osps.dnsbl.net.au',
+    'osrs.dnsbl.net.au',
+    'outputs.orbz.org',
+    'owfs.dnsbl.net.au',
+    'pacbelldsl.compu.net',
+    'paidaccessviarsync',
+    'pbl.spamhaus.org',
+    'pdl.bl.reynolds.net.au',
+    'peer.asn.cymru.com',
+    'phishing.rbl.msrbl.net',
+    'plus.bondedsender.org',
+    'pm0-no-more.compu.net',
+    'pofon.foobar.hu',
+    'policy.lbl.lagengymnastik.dk',
+    'postmaster.rfc-clueless.org',
+    'postmaster.rfc-ignorant.org',
+    'ppbl.beat.st',
+    'probes.dnsbl.net.au',
+    'probes.dnsbl.net.auproxy.bl.gweep.ca',
+    'problems.dnsbl.sorbs.net',
+    'proxies.blackholes.easynet.nl',
+    'proxies.dnsbl.sorbs.net',
+    'proxies.exsilia.net',
+    'proxies.relays.monkeys.com',
+    'proxy.bl.gweep.ca',
+    'proxy.block.transip.nl',
+    'proxy.drbl.be.net.ru',
+    'psbl.surriel.com',
+    'pss.spambusters.org.ar',
+    'q.mail-abuse.com',
+    'query.bondedsender.org',
+    'query.senderbase.org',
+    'r.mail-abuse.com',
+    'rabl.nuclearelephant.com',
+    'random.bl.gweep.ca',
+    'rbl-plus.mail-abuse.org',
+    'rbl.abuse.ro',
+    'rbl.atlbl.net',
+    'rbl.blakjak.net',
+    'rbl.blockedservers.com',
+    'rbl.bulkfeeds.jp',
+    'rbl.cbn.net.id',
+    'rbl.choon.net',
+    'rbl.dns-servicios.com',
+    'rbl.echelon.pl',
+    'rbl.efnet.org',
+    'rbl.efnethelp.net',
+    'rbl.efnetrbl.org',
+    'rbl.eznettools.com',
+    'rbl.fasthosts.co.uk',
+    'rbl.firstbase.com',
+    'rbl.init1.nl',
+    'rbl.interserver.net',
+    'rbl.iprange.net',
+    'rbl.ipv6wl.eu',
+    'rbl.jp',
+    'rbl.lugh.ch',
+    'rbl.ma.krakow.pl',
+    'rbl.mail-abuse.org',
+    'rbl.megarbl.net',
+    'rbl.ntvinet.net',
+    'rbl.pil.dk',
+    'rbl.polarcomm.net',
+    'rbl.rope.net',
+    'rbl.schulte.org',
+    'rbl.snark.net',
+    'rbl.spamlab.com',
+    'rbl.suresupport.com',
+    'rbl.talkactive.net',
+    'rbl.triumf.ca',
+    'rbl2.triumf.ca',
+    'rdts.bl.reynolds.net.au',
+    'rdts.dnsbl.net.au',
+    'recent.dnsbl.sorbs.net',
+    'recent.spam.dnsbl.sorbs.net',
+    'relayips.rbl.shub-inter.net',
+    'relays.bl.gweep.ca',
+    'relays.bl.kundenserver.de',
+    'relays.dnsbl.sorbs.net',
+    'relays.dorkslayers.com',
+    'relays.mail-abuse.org',
+    'relays.nether.net',
+    'relays.radparker.com',
+    'relays.sandes.dk',
+    'relaywatcher.n13mbl.com',
+    'rep.mailspike.net',
+    'reputation-domain.rbl.scrolloutf1.com',
+    'reputation-ip.rbl.scrolloutf1.com',
+    'reputation-ns.rbl.scrolloutf1.com',
+    'residential.block.transip.nl',
+    'rf.senderbase.org',
+    'rhsbl.rymsho.ru',
+    'rhsbl.scientificspam.net',
+    'rhsbl.sorbs.net',
+    'rhsbl.zapbl.net',
+    'ricn.dnsbl.net.au',
+    'ripe-main.bogons.dnsiplists.completewhois.com',
+    'rmst.dnsbl.net.au',
+    'rot.blackhole.cantv.net',
+    'rsbl.aupads.org',
+    'rwl.choon.net',
+    'sa-accredit.habeas.com',
+    'sa.senderbase.org',
+    'safe.dnsbl.sorbs.net',
+    'sbl-xbl.spamhaus.org',
+    'sbl.nszones.com',
+    'sbl.spamhaus.org',
+    'schizo-bl.kundenserver.de',
+    'score.senderscore.com',
+    'sender-address.sjesl.monkeys.com',
+    'sender-domain-validate.sjesl.monkeys.com',
+    'sender-domain.sjesl.monkeys.com',
+    'service.mailwhitelist.com',
+    'short.fmb.la',
+    'short.rbl.jp',
+    'singlebl.spamgrouper.com',
+    'singular.ttk.pte.hu',
+    'smtp.dnsbl.sorbs.net',
+    'socks.dnsbl.sorbs.net',
+    'sohul.habeas.com',
+    'sorbs.dnsbl.net.au',
+    'spam.abuse.ch',
+    'spam.dnsbl.anonmails.de',
+    'spam.dnsbl.rangers.eu.org',
+    'spam.dnsbl.sorbs.net',
+    'spam.exsilia.net',
+    'spam.lbl.lagengymnastik.dk',
+    'spam.olsentech.net',
+    'spam.pedantic.org',
+    'spam.rbl.blockedservers.com',
+    'spam.rbl.msrbl.net',
+    'spam.shri.net',
+    'spam.spamrats.com',
+    'spam.wonk.org',
+    'spam.wytnij.to',
+    'spam.zapjunk.com',
+    'spamblock.kundenserver.de',
+    'spambot.bls.digibase.ca',
+    'spamdomain.block.transip.nl',
+    'spamdomains.blackholes.easynet.nl',
+    'spamguard.leadmon.net',
+    'spamips.rbl.shub-inter.net',
+    'spamlist.or.kr',
+    'spamrbl.imp.ch',
+    'spamsource.block.transip.nl',
+    'spamsources.fabel.dk',
+    'spamsources.spamblocked.com',
+    'spamsupport.dnsbl.rangers.eu.org',
+    'spbl.bl.winbots.org',
+    'spews.block.transip.nl',
+    'srn.surgate.net',
+    'srnblack.surgate.net',
+    'st.technovision.dk',
+    'stabl.rbl.webiron.net',
+    'stale.dict.rbl.arix.com',
+    'stale.sa_slip.arix.com',
+    'superblock.ascams.com',
+    'swl.spamhaus.org',
+    't3direct.dnsbl.net.au',
+    'taiwan.rominet.net',
+    'tor.dan.me.uk',
+    'tor.dnsbl.sectoor.de',
+    'tor.efnet.org',
+    'torexit.dan.me.uk',
+    'torserver.tor.dnsbl.sectoor.de',
+    'truncate.gbudb.net',
+    'trusted.nether.net',
+    'ubl.lashback.com',
+    'ubl.nszones.com',
+    'ubl.unsubscore.com',
+    'unsure.nether.net',
+    'uribl.abuse.ro',
+    'uribl.pofon.foobar.hu',
+    'uribl.spameatingmonkey.net',
+    'uribl.swinog.ch',
+    'uribl.zeustracker.abuse.ch',
+    'urired.spameatingmonkey.net',
+    'url.rbl.jp',
+    'v4.fullbogons.cymru.com',
+    'v6.fullbogons.cymru.com',
+    'vbl.mookystick.com',
+    'virbl.bit.nl',
+    'virbl.dnsbl.bit.nl',
+    'virus.rbl.jp',
+    'virus.rbl.msrbl.net',
+    'vote.drbl.be.net.ru',
+    'vote.drbl.caravan.ru',
+    'vote.drbl.croco.net',
+    'vote.drbl.dataforce.net',
+    'vote.drbl.gremlin.ru',
+    'vote.drbl.host.kz',
+    'vote.drbldf.dsbl.ru',
+    'vote.rbl.ntvinet.net',
+    'vouch.dwl.spamhaus.org',
+    'wadb.isipp.com',
+    'wbl.triumf.ca',
+    'wdl.bl.reynolds.net.au',
+    'web.dnsbl.sorbs.net',
+    'web.rbl.msrbl.net',
+    'whitelist.sci.kun.nl',
+    'whitelist.surriel.com',
+    'whois.rfc-clueless.org',
+    'whois.rfc-ignorant.org',
+    'wl.mailspike.net',
+    'wl.nszones.com',
+    'wl.shlink.org',
+    'wl.summersault.com',
+    'wl.trusted-forwarder.org',
+    'work.drbl.caravan.ru',
+    'work.drbl.croco.net',
+    'work.drbl.dataforce.net',
+    'work.drbl.gremlin.ru',
+    'work.drbl.host.kz',
+    'work.drbldf.dsbl.ru',
+    'worm.dnsbl.rangers.eu.org',
+    'wormrbl.imp.ch',
+    'worms-bl.kundenserver.de',
+    'wpb.bl.reynolds.net.au',
+    'xbl.selwerd.cx',
+    'xbl.spamhaus.org',
+    'ybl.megacity.org',
+    'z.mailspike.net',
+    'zebl.zoneedit.com',
+    'zen.spamhaus.org',
+    'zombie.dnsbl.sorbs.net',
+    'zta.birdsong.org',
+    'ztl.dorkslayers.com',
+    'zz.countries.nerd.dk'
+]
+
+async def check_dnsbl(ip: str, dnsbl: str, semaphore: asyncio.Semaphore):
+    '''
+    Check if an IP address is blacklisted on a DNSBL.
+    
+    :param ip: IP address to check.
+    :param dnsbl: DNSBL to check.
+    :param semaphore: Semaphore to limit the number of concurrent requests.
+    '''
+    async with semaphore:
+        reversed_ip = '.'.join(reversed(ip.split('.')))
+        try:
+            resolver = aiodns.DNSResolver()
+            lookup = f'{reversed_ip}.{dnsbl}'
+            for item in await resolver.query(lookup, 'TXT'):
+                response = await resolver.query(lookup, 'A')
+                if response:
+                    print(f'{GREEN}{ip} is blacklisted on {dnsbl}: {response[0].host}{RESET}')
+                else:
+                    if args.verbose:
+                        print(f'{RED}{ip} has no reply from {dnsbl}{RESET}')
+        except aiodns.error.DNSError as e:
+            if args.verbose:
+                if e.args[0] == 4:
+                    print(f'{GREY}{ip} is not blacklisted on {dnsbl}{RESET}')
+                else:
+                    print(f'{RED}{ip} errored on {dnsbl} with {lookup}: {e}{RESET}')
+
+async def main(ip, concurrency):
+    semaphore = asyncio.Semaphore(concurrency)
+    tasks = [check_dnsbl(ip, dnsbl, semaphore) for dnsbl in DNSBL_LIST]
+    await asyncio.gather(*tasks)
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description='DNSBL Lookup Tool')
+    parser.add_argument('input', help='IP address or file with IP addresses')
+    parser.add_argument('-c', '--concurrency', type=int, default=50, help='Number of concurrent lookups')
+    parser.add_argument('-v', '--verbose', action='store_true', help='Enable verbose output')
+    args = parser.parse_args()
+
+    try:
+        ipaddress.ip_address(args.input)
+        asyncio.run(main(args.input, args.concurrency))
+    except:
+        if os.path.isfile(args.input):
+            with open(args.input, 'r') as file:
+                for line in file:
+                    ip = line.strip()
+                    try:
+                        ipaddress.ip_address(ip)
+                        asyncio.run(main(args.input, args.concurrency))
+                    except:
+                        logging.warning(f'Invalid IP address: {ip}')
+        else:
+            raise SystemExit(f'Invalid IP address or file: {args.input}')

dronebl/dronebl.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python
+# Copyright (c) 2008 DroneBL contributors
+#
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without modification,
+# are permitted provided that the following conditions are met:
+#
+#      Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#
+#      Redistributions in binary form must reproduce the above copyright notice,
+#      this list of conditions and the following disclaimer in the documentation
+#      and/or other materials provided with the distribution.
+#
+#      Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
+# ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+# ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+class DroneBLClient:
+	"""Class for accessing DroneBL."""
+	def __init__(self, rpckey=None, server="https://dronebl.org/RPC2"):
+		self.server = server
+		self.rpckey = rpckey
+		self.submitList = ""
+
+	def addIP(self, ip, type):
+		"""Adds IP to DroneBL."""
+		self.submitList += "\t<add ip='" + ip + "' type='" + str(type) + "' />\n";
+
+	def lookupIP(self, ip):
+		"""Adds a lookup request to the message."""
+		self.submitList += "\t<lookup ip='" + ip + "' />\n"
+
+	def makeRequest(self):
+		"""Generates the request."""
+		self.request = "<?xml version=\"1.0\"?>\n<request key='" + self.rpckey + "'>\n" + self.submitList + "</request>"
+
+	def showRequest(self):
+		"""Shows the request."""
+		self.makeRequest()
+		print self.request
+
+	def makeConnection(self):
+		"""Connects to the RPC server."""
+		import urllib
+		type, uri = urllib.splittype(self.server)
+		self.__host, self.__handler = urllib.splithost(uri)
+
+		import httplib
+		self.connection = httplib.HTTPConnection(self.__host)
+
+	def postRequest(self):
+		"""Executes the request."""
+		self.makeRequest()
+		self.makeConnection()
+		self.connection.putrequest("POST", self.__handler)
+		self.connection.putheader("Content-Type", "text/xml")
+		self.connection.putheader("Content-Length", str(int(len(self.request))))
+		self.connection.endheaders()
+		self.connection.send(self.request)
+		self.__response = self.connection.getresponse()
+
+	def printResponse(self):
+		"""Display the XML response."""
+		print self.__response.read()
+

dronebl/remove.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+cd "$(dirname "$0")"
+KEY="$(<dronebl.key)"
+
+(
+        echo "<?xml version=\"1.0\"?><request key=\"$KEY\">"
+        while [ -n "$1" ] ; do
+                echo "<lookup ip=\"$1\" />"
+                shift
+        done
+        echo "</request>"
+) \
+|       curl -s --data @- https://dronebl.org/RPC2  \
+|       (xmllint --xpath '/response/result/@id' - 2>/dev/null | sed -n -e 's, id="\([^"]*\)",\1\n,gp') \
+|(
+        echo "<?xml version=\"1.0\"?><request key=\"$KEY\">"
+        while read ID ; do
+                echo "Remove ID $ID" >&2
+                echo "<remove id=\"$ID\" />"
+        done
+        echo "</request>"
+) \
+|       tee -a dronebl-remove.log \
+|       curl -s --data @- https://dronebl.org/RPC2 | tee -a dronebl-remove.log | grep -q "\"success\""
+if [ $? -eq 0 ] ; then
+        echo "DRONEBL: successfully removed $@"
+else
+        echo "DRONEBL: error removing $@"
+fi

dronebl/submit.sh

@@ -0,0 +1,175 @@
+#!/bin/bash
+# syntax: dronebl-submit.sh [bantype [host|IP|datafile [host|IP|datafile [etc.]]]
+# where datafile contains one host or IP per line.
+# This script will sort | uniq datafiles and query for existing active listings, so
+# duplicate entries are no problem.
+#
+# dependencies: bash, wget, standard GNU utils (host / sed / grep / sort / etc)
+#
+# Version history:
+# 2.1 -- fixed a logic error; removed the removal of /tmp/dronebl-*.xml files on error
+# 2.0 -- completely rewritten for RPC2 (although argument syntax is backward-
+# compatible)
+
+RPCKEY="/etc/fail2ban/dronebl.rpckey"  # key, or path to file containing rpckey
+REPORT_TO="https://dronebl.org/RPC2"
+
+### end of user variables ###
+
+if [ ! -w "/tmp" ]; then
+	echo "Unable to write to /tmp.  Please ensure the disk is not full, and that this account has appropriate permissions."
+	exit 1
+fi
+
+if [ -f "$RPCKEY" ]; then 
+	if [ -r "$RPCKEY" ]; then
+		RPCKEY=`cat $RPCKEY`
+	else
+		echo "RPC key in $RPCKEY is unreadable.  Exiting."
+		exit 1
+	fi
+fi
+
+function wash {  # wash <hostname> -- sets $IP by reference
+	ADDR=$1
+	TEST=`echo "${ADDR}." | grep -E "^([0-9]{1,3}\.){4}$"`
+	if [ "$TEST" ]; then
+		VALID=0
+	else
+		VALID=1
+	fi
+
+	if [ "$VALID" = "1" ]; then
+		echo -n "Looking up $ADDR... "
+		ADDR=`host $ADDR | grep -E -o -e '[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}$'`
+		TEST=`echo "${ADDR}." | grep -E "^([0-9]{1,3}\.){4}$"`
+		if [ "$TEST" ]; then
+			echo "$ADDR"
+		else
+			echo "Unable to resolve.  Skipping."
+			return 1
+		fi		
+	fi
+	eval "IP=$ADDR"
+	return 0
+}
+
+function rinse {  # rinse <bantype> -- if bantype is contained in the deprecated list, exit
+	DEPRECATED=( 4 11 12 )
+	for dep in ${DEPRECATED[@]}; do
+		if [ "$BANTYPE" == "$dep" ]; then
+			echo "Bantype $BANTYPE has been deprecated.  The DroneBL is probably not the appropriate listing service for this sort of activity.  Please visit us on irc.atheme.org in #dronebl if you believe otherwise.  Exiting."
+			exit 1
+		fi
+	done
+}
+
+function checkerror {  #checkerror <xmlfile> -- prints error messages from xml and exits
+	ERROR=`grep -i error $1`
+	if [ "$ERROR" ]; then
+		ERROR=`grep '<code>' $1 | sed -r -e 's/<[^>]*>//g' -e 's/^\s*//g'`
+		ERROR="$ERROR: `grep '<message>' $1 | sed -r -e 's/<[^>]*>//g' -e 's/^\s*//g'`"
+		echo "The server returned an error ($ERROR) -- see /tmp/dronebl-query.xml and /tmp/dronebl-response.xml for full details."
+		exit 1
+	fi
+}
+
+if [ "$2" = "" ]; then
+	echo -n 'Syntax:
+'$0' [bantype [host|IP|datafile [host|IP|datafile [etc.]]]]
+
+Types are as follows:
+2 = Sample
+3 = IRC Drone
+4 = Tor exit node (deprecated)
+5 = Bottler
+6 = Unknown spambot or drone
+7 = DDOS Drone
+8 = SOCKS Proxy
+9 = HTTP Proxy
+10 = ProxyChain
+11 = Machines and netblocks compromised or owned by MediaDefender (deprecated)
+12 = Trolls (deprecated)
+13 = Brute force attackers
+14 = Open Wingate
+15 = Open Router
+255 = Unknown
+
+Which type? '
+	read BANTYPE
+	rinse $BANTYPE
+	echo -n "What's the hostname / IP address? "
+	read ADDR
+	wash $ADDR
+	if [ $? ]; then
+		IPLIST[0]=$IP
+	else
+		echo "Unable to resolve $ADDR.  Exiting."
+		exit 1
+	fi
+else
+	rinse $1
+	args=($@)
+	echo "A little housekeeping..."
+	for (( x=1; x<${#args[@]}; x++ )); do
+		if [ "${args[$x]}" != "" ]; then
+			filename="${args[$x]}"
+			if [ ! -r "$filename" ]; then filename="$PWD/${args[$x]}"; fi
+			if [ -r "$filename" ]; then
+				for i in `sort -u $PWD/${args[$x]}`; do
+					wash $i
+					if [ $? ]; then IPLIST[${#IPLIST[@]}]=$IP; fi
+				done
+			else
+				wash ${args[$x]}
+				if [ $? ]; then IPLIST[${#IPLIST[@]}]=$IP; fi
+			fi
+		fi
+	done
+	IPLIST=( `for (( x=0; x<${#IPLIST[@]}; x++ )) ; do echo ${IPLIST[$x]}; done | sort -u` )
+	BANTYPE=$1
+fi
+
+POSTFILE="/tmp/dronebl-query.xml"
+RESPONSEFILE="/tmp/dronebl-response.xml"
+
+echo "Housekeeping finished.  Working with ${#IPLIST[@]} unique, valid addresses."
+if [ ${#IPLIST[@]} -eq 0 ]; then
+	echo "No hosts to report.  Exiting."
+	exit 0
+fi
+
+echo "Checking for exiting entries... "
+echo "<?xml version=\"1.0\"?>
+<request key='"$RPCKEY"'>" >$POSTFILE
+for i in ${IPLIST[@]}; do
+	echo "	<lookup ip='$i' />" >>$POSTFILE
+done
+echo "</request>" >>$POSTFILE
+wget -q --post-file="$POSTFILE" -O "$RESPONSEFILE" --header="Content-Type: text/xml" $REPORT_TO
+checkerror $RESPONSEFILE
+grepfor='type="'$BANTYPE'"'
+for i in `grep 'listed="1"' $RESPONSEFILE | grep $grepfor | grep -E -o -e '[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}' | sort -u`; do
+	IPLIST=( ${IPLIST[@]%%$i} )
+	echo "$i is already active in the DroneBL database as ban type $BANTYPE.  Removing."
+done
+
+if [ ${#IPLIST[@]} -eq 0 ]; then
+	echo "No hosts to report.  Exiting."
+	exit 0
+elif [ ${#IPLIST[@]} -eq 1 ]; then
+	echo -n "Reporting ${IPLIST[@]} as ban type $BANTYPE... "
+else
+	echo -n "Reporting ${#IPLIST[@]} hosts as ban type $BANTYPE... "
+fi
+echo "<?xml version=\"1.0\"?>
+<request key='"$RPCKEY"'>" >$POSTFILE
+for i in ${IPLIST[@]}; do
+	if [ "`echo ${i}. | grep -E '^([0-9]{1,3}\.){4}$'`" != "" ]; then echo "	<add ip='$i' type='$BANTYPE' />" >>$POSTFILE; fi
+done
+echo "</request>" >>$POSTFILE
+wget -q --post-file="$POSTFILE" -O "$RESPONSEFILE" --header="Content-Type: text/xml" $REPORT_TO
+checkerror $RESPONSEFILE
+echo "done."
+rm -f /tmp/dronebl*.xml
+exit 0

floodbl.py

@@ -1,6 +1,9 @@
 #!/usr/bin/env python
 # FloodBL - Developed by acidvegas in Python (https://git.acid.vegas/proxytools)
 
+# This script will check a list of proxies aginst DNS Blackhole (DNSBL) lists to see if they are blackholed.
+# Todo: Add support for asynchronous DNSBL lookups and proper IPv6 support.
+
 import argparse
 import concurrent.futures
 import ipaddress
@@ -48,7 +51,12 @@ blackholes = {
 	}
 }
 
-def check(proxy):
+def check(proxy: str):
+	'''
+	Check if a proxy is blackholed.
+
+	:param proxy: the proxy to check in the format of ip:port
+	'''
 	proxy_ip     = proxy.split(':')[0]
 	formatted_ip = ipaddress.ip_address(proxy_ip).reverse_pointer
 	for blackhole in blackholes:
@@ -72,32 +80,41 @@ def check(proxy):
 	if proxy not in bad:
 		good.append(proxy)
 
-# Main
-print('#'*56)
-print('#{0}#'.format(''.center(54)))
-print('#{0}#'.format('FloodBL Blackhole Checker'.center(54)))
-print('#{0}#'.format('Developed by acidvegas in Python'.center(54)))
-print('#{0}#'.format('https://git.acid.vegas/proxytools'.center(54)))
-print('#{0}#'.format(''.center(54)))
-print('#'*56)
-parser = argparse.ArgumentParser(usage='%(prog)s <input> <output> [options]')
-parser.add_argument('input',           help='file to scan')
-parser.add_argument('output',          help='file to output')
-parser.add_argument('-t', '--threads', help='number of threads (default: 100)', default=100, type=int)
-args = parser.parse_args()
-if not os.path.isfile(args.input):
-	raise SystemExit('no such input file')
-initial = len(open(args.input).readlines())
-proxies = set([proxy.split(':')[0] for proxy in re.findall('[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+:[0-9]+', open(args.input).read(), re.MULTILINE)]) # TODO: handle IPv6 better
-if not proxies:
-	raise SystemExit('no proxies found from input file')
-with concurrent.futures.ThreadPoolExecutor(max_workers=args.threads) as executor:
-	checks = {executor.submit(check, proxy): proxy for proxy in proxies}
-	for future in concurrent.futures.as_completed(checks):
-		checks[future]
-good.sort()
-with open(args.output, 'w') as output_file:
-	output_file.write('\n'.join(good))
-print('\033[34mTotal\033[0m : ' + format(len(proxies),           ',d'))
-print('\033[34mGood\033[0m  : ' + format(len(good),              ',d'))
-print('\033[34mBad\033[0m   : ' + format(len(proxies)-len(good), ',d'))
+
+if __name__ == '__main__':
+	print('#'*56)
+	print('#{0}#'.format(''.center(54)))
+	print('#{0}#'.format('FloodBL Blackhole Checker'.center(54)))
+	print('#{0}#'.format('Developed by acidvegas in Python'.center(54)))
+	print('#{0}#'.format('https://git.acid.vegas/proxytools'.center(54)))
+	print('#{0}#'.format(''.center(54)))
+	print('#'*56)
+
+	parser = argparse.ArgumentParser(usage='%(prog)s <input> <output> [options]')
+	parser.add_argument('input',           help='file to scan')
+	parser.add_argument('output',          help='file to output')
+	parser.add_argument('-t', '--threads', help='number of threads (default: 100)', default=100, type=int)
+	args = parser.parse_args()
+
+	if not os.path.isfile(args.input):
+		raise SystemExit('no such input file')
+
+	initial = len(open(args.input).readlines())
+	proxies = set([proxy.split(':')[0] for proxy in re.findall('[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+:[0-9]+', open(args.input).read(), re.MULTILINE)]) # TODO: handle IPv6 better
+
+	if not proxies:
+		raise SystemExit('no proxies found from input file')
+
+	with concurrent.futures.ThreadPoolExecutor(max_workers=args.threads) as executor:
+		checks = {executor.submit(check, proxy): proxy for proxy in proxies}
+		for future in concurrent.futures.as_completed(checks):
+			checks[future]
+
+	good.sort()
+
+	with open(args.output, 'w') as output_file:
+		output_file.write('\n'.join(good))
+
+	print('\033[34mTotal\033[0m : ' + format(len(proxies),           ',d'))
+	print('\033[34mGood\033[0m  : ' + format(len(good),              ',d'))
+	print('\033[34mBad\033[0m   : ' + format(len(proxies)-len(good), ',d'))

proxy_sources.txt

@@ -0,0 +1,57 @@
+	https://api.openproxylist.xyz/socks4.txt
+	https://api.openproxylist.xyz/socks5.txt
+	https://api.proxyscrape.com/?request=displayproxies&proxytype=socks4
+	https://api.proxyscrape.com/v2/?request=displayproxies&protocol=socks4
+	https://api.proxyscrape.com/?request=displayproxies&proxytype=socks5
+	https://api.proxyscrape.com/v2/?request=displayproxies&protocol=socks5
+	https://proxy-list.download/api/v1/get?type=socks4
+	https://proxy-list.download/api/v1/get?type=socks5
+	https://proxyscan.io/download?type=socks4
+	https://proxyscan.io/download?type=socks5
+	https://proxyspace.pro/socks4.txt
+	https://proxyspace.pro/socks5.txt
+	https://raw.githubusercontent.com/ALIILAPRO/Proxy/main/socks4.txt
+	https://raw.githubusercontent.com/ALIILAPRO/Proxy/main/socks5.txt
+	https://raw.githubusercontent.com/B4RC0DE-TM/proxy-list/main/SOCKS4.txt
+	https://raw.githubusercontent.com/B4RC0DE-TM/proxy-list/main/SOCKS5.txt
+	https://raw.githubusercontent.com/hookzof/socks5_list/master/proxy.txt
+	https://raw.githubusercontent.com/HyperBeats/proxy-list/main/socks4.txt
+	https://raw.githubusercontent.com/HyperBeats/proxy-list/main/socks5.txt
+	https://raw.githubusercontent.com/jetkai/proxy-list/main/online-proxies/txt/proxies-socks4.txt
+	https://raw.githubusercontent.com/jetkai/proxy-list/main/online-proxies/txt/proxies-socks5.txt
+	https://raw.githubusercontent.com/manuGMG/proxy-365/main/SOCKS4.txt
+	https://raw.githubusercontent.com/manuGMG/proxy-365/main/SOCKS5.txt
+	https://raw.githubusercontent.com/mmpx12/proxy-list/master/socks4.txt
+	https://raw.githubusercontent.com/mmpx12/proxy-list/master/socks5.txt
+	https://raw.githubusercontent.com/monosans/proxy-list/main/proxies/socks4.txt
+	https://raw.githubusercontent.com/monosans/proxy-list/main/proxies/socks5.txt
+	https://raw.githubusercontent.com/monosans/proxy-list/main/proxies_anonymous/socks4.txt
+	https://raw.githubusercontent.com/monosans/proxy-list/main/proxies_anonymous/socks5.txt
+	https://raw.githubusercontent.com/MuRongPIG/Proxy-Master/main/socks4.txt
+	https://raw.githubusercontent.com/MuRongPIG/Proxy-Master/main/socks5.txt
+	https://raw.githubusercontent.com/officialputuid/KangProxy/KangProxy/socks5/socks4.txt
+	https://raw.githubusercontent.com/officialputuid/KangProxy/KangProxy/socks5/socks5.txt
+	https://raw.githubusercontent.com/prxchk/proxy-list/main/socks4.txt
+	https://raw.githubusercontent.com/prxchk/proxy-list/main/socks5.txt
+	https://raw.githubusercontent.com/rdavydov/proxy-list/main/proxies/socks4.txt
+	https://raw.githubusercontent.com/rdavydov/proxy-list/main/proxies/socks5.txt
+	https://raw.githubusercontent.com/rdavydov/proxy-list/main/proxies_anonymous/socks4.txt
+	https://raw.githubusercontent.com/rdavydov/proxy-list/main/proxies_anonymous/socks5.txt
+	https://raw.githubusercontent.com/roosterkid/openproxylist/main/SOCKS4_RAW.txt
+	https://raw.githubusercontent.com/roosterkid/openproxylist/main/SOCKS5_RAW.txt
+	https://raw.githubusercontent.com/RX4096/proxy-list/main/online/socks4.txt
+	https://raw.githubusercontent.com/RX4096/proxy-list/main/online/socks5.txt
+	https://raw.githubusercontent.com/saschazesiger/Free-Proxies/master/proxies/socks4.txt
+	https://raw.githubusercontent.com/saschazesiger/Free-Proxies/master/proxies/socks5.txt
+	https://raw.githubusercontent.com/ShiftyTR/Proxy-List/master/socks4.txt
+	https://raw.githubusercontent.com/ShiftyTR/Proxy-List/master/socks5.txt
+	https://raw.githubusercontent.com/TheSpeedX/PROXY-List/master/socks4.txt
+	https://raw.githubusercontent.com/TheSpeedX/PROXY-List/master/socks5.txt
+	https://raw.githubusercontent.com/UptimerBot/proxy-list/main/proxies/socks4.txt
+	https://raw.githubusercontent.com/UptimerBot/proxy-list/main/proxies/socks5.txt
+	https://raw.githubusercontent.com/Zaeem20/FREE_PROXIES_LIST/master/socks4.txt
+	https://raw.githubusercontent.com/Zaeem20/FREE_PROXIES_LIST/master/socks5.txt
+	https://raw.githubusercontent.com/zevtyardt/proxy-list/main/socks4.txt
+	https://raw.githubusercontent.com/zevtyardt/proxy-list/main/socks5.txt
+	https://spys.me/socks.txt
+	https://spys.one/en/socks-proxy-list/

pythonproxy.md

@@ -0,0 +1,126 @@
+# Proxy usage with Python
+
+## [aiosocks](https://pypi.org/project/aiosocks/)
+
+```python
+import asyncio
+import aiosocks
+
+async def proxy_example(proxy: str, use_ssl:  bool = False):
+    '''Proxy can be in IP:PORT format or USER:PASS@IP:PORT format'''
+
+    auth = proxy.split('@')[0].split(':') if '@' in proxy else None
+    proxy_ip, proxy_port = proxy.split('@')[1].split(':') if '@' in proxy else proxy.split(':')
+
+    options = {
+        'proxy'      : aiosocks.Socks5Addr(proxy_ip, proxy_port),
+        'proxy_auth' : aiosocks.Socks5Auth(*auth) if auth else None,
+        'dst'        : (host, port),
+        'limit'      : 1024,
+        'ssl'        : ssl._create_unverified_context() if use_ssl else None,
+        'family'     : 2 # 2 = IPv4 | 10 = IPv6
+    }
+
+    reader, writer = await asyncio.wait_for(aiosocks.open_connection(**options), 15) # 15 second timeout
+
+    while True:
+        data  = await asyncio.wait_for(reader.readuntil(b'\r\n'), 300) # 5 minute timeout on no data received
+        print(data.decode().strip()) # Print the response from the server
+```
+
+## [aiohttp](https://pypi.org/project/aiohttp)
+```python
+import asyncio
+import aiohttp
+
+async def proxy_example(proxy: str, url: str):
+    '''Proxy can be in IP:PORT format or USER:PASS@IP:PORT format'''
+
+    async with aiohttp.ClientSession() as session:
+        async with session.get('https://google.com', proxy=f'http://{proxy}', timeout=15) as response:
+            if response.status == 200: # 200 = success
+                print(response.text()) # Print the response from the server
+```
+
+## [http.client](https://docs.python.org/3/library/http.client.html)
+I really don't use this library much at all, so this is some LM generated function...
+
+```python
+import base64
+import http.client
+
+def proxy_example(proxy: str, url):
+    '''Proxy can be in IP:PORT format or USER:PASS@IP:PORT format'''
+
+    auth = proxy.split('@')[0].split(':') if '@' in proxy else None
+    proxy_host, proxy_port = proxy.split('@')[1].split(':') if '@' in proxy else proxy.split(':')
+
+    scheme, rest = url.split('://', 1)
+    host, path = rest.split('/', 1)
+    path = '/' + path
+    
+    if scheme == 'https':
+        conn = http.client.HTTPConnection(proxy_host, proxy_port)
+        conn.request('CONNECT', host)
+        response = conn.getresponse()
+        if response.status != 200:
+            print("Failed to establish a tunnel via proxy.")
+            print(response.status, response.reason)
+            return
+                conn = http.client.HTTPSConnection(proxy_host, proxy_port, context=None)
+        conn.set_tunnel(host)
+    else:
+        conn = http.client.HTTPConnection(proxy_host, proxy_port)
+        path = url
+
+    headers = {}
+    if auth:
+        auth = base64.b64encode(f'{auth[0]}:{auth[1]}'.encode()).decode()
+        headers['Proxy-Authorization'] = f'Basic {auth}'
+
+
+    conn.request('GET', path, headers=headers)
+    response = conn.getresponse()
+    print(response.status, response.reason)
+    if response.status == 200:
+        data = response.read()
+        print(data.decode())
+
+    conn.close()
+```
+
+## [requests](https://pypi.org/project/requests/)
+```python
+import requests
+
+def proxy_example(proxy: str, url: str):
+    '''Proxy can be in IP:PORT format or USER:PASS@IP:PORT format'''
+
+    proxy_handler = {'http': 'http://'+proxy, 'https': 'https://'+proxy}
+    response = requests.get(url, proxies=proxies)
+    print(response.text)
+```
+
+## [urllib.request](https://docs.python.org/3/library/urllib.html)
+```python
+import urllib.request
+
+def proxy_example(proxy: str, url: str):
+    '''Proxy can be in IP:PORT format or USER:PASS@IP:PORT format'''
+
+    proxy_handler = urllib.request.ProxyHandler({'http': proxy, 'https': proxy})
+    opener = urllib.request.build_opener(proxy_handler)
+
+    if '@' in proxy: # Handle authentication
+        creds, address = proxy.split('@')
+        username, password = creds.split(':')
+        auth_header = urllib.request.HTTPBasicAuthHandler()
+        auth_header.add_password(realm=None, uri=proxy, user=username, passwd=password)
+        opener.add_handler(auth_header)
+
+    urllib.request.install_opener(opener)
+
+    response = urllib.request.urlopen(url, timeout=15)
+    if response.code == 200:
+        print(response.read().decode())
+```

shellscrape

@@ -1,20 +0,0 @@
-#!/bin/env bash
-# shellscrape - developed by acidvegas (https://git.acid.vegas/proxytools)
-
-URLS=(
-	"https://raw.githubusercontent.com/ALIILAPRO/Proxy/main/socks4.txt"
-	"https://raw.githubusercontent.com/ALIILAPRO/Proxy/main/socks5.txt"
-	"https://raw.githubusercontent.com/B4RC0DE-TM/proxy-list/main/SOCKS4.txt"
-	"https://raw.githubusercontent.com/B4RC0DE-TM/proxy-list/main/SOCKS5.txt"
-	"https://raw.githubusercontent.com/hookzof/socks5_list/master/proxy.txt"
-	"https://raw.githubusercontent.com/HyperBeats/proxy-list/main/socks4.txt"
-	"https://raw.githubusercontent.com/HyperBeats/proxy-list/main/socks5.txt"
-)
-
-[ -f proxies.txt ] >proxies.txt
-for URL in "${URLS[@]}"; do
-    echo "Downloading from $URL"
-    curl -s $URL >> proxies.txt &
-done
-sort -u -o proxies.txt proxies.txt
-echo "done"

shellsocked

@@ -0,0 +1,34 @@
+#!/bin/env bash
+# shellsocked - developed by acidvegas (https://git.acid.vegas/proxytools)
+
+# Probably the most basic proxy scraper ever made, pure POSIX, no dependencies, no bullshit.
+# Duplicate proxies are removed and the output is sorted and saved to a file.
+# Feed it a single URL or a file with a list of URLs to scrape.
+
+scrape_url() {
+    local url="$1"
+    local proxies=$(curl -s -A "ShellSocked/1.0" "$url" | grep -Eo '[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+:[0-9]+' | awk '!seen[$0]++')
+    local count=$(echo "$proxies" | wc -l)
+    PROXIES="${PROXIES}${proxies}"
+    echo -e "Found \033[32m${count}\033[0m proxies on \033[33m${url}\033[0m"
+}
+
+if [ -n "$1" ]; then
+    PROXIES=""
+    if [ -f "$1" ]; then
+        while IFS= read -r url; do
+            scrape_url "$url"
+        done < "$1"
+    else
+        scrape_url "$1"
+    fi
+else
+    echo "Usage: $0 <input_file | single_url>"
+    exit 1
+fi
+
+PROXIES=$(printf "%s\n" "$PROXIES" | sort -u)
+printf "%s\n" "$PROXIES" > proxies.txt
+
+total_count=$(echo "$PROXIES" | wc -l)
+echo "Grand Total: ${total_count} proxies"

sockhub.py

@@ -1,111 +1,72 @@
 #!/usr/bin/env python
 # SockHub Proxy Scraper - Developed by acidvegas in Python (https://git.acid.vegas/proxytools)
 
+'''
+There is a file in this repository called proxy_sources.txt which contains a list of URLs to scrape for proxies.
+This list it not maintained and may contain dead links or links to sites that no longer contain proxies.
+'''
+
+import concurrent.futures
+import logging
 import os
 import re
 import urllib.request
 
-# Can be any URL containing a list of IP:PORT proxies (does not have to be socks5)
-# The current list contains proxy sources that are updated frequently with new proxies
-# Almost all of the Github repos pull from the same place & contain duplicates (which are removed)
-urls = set((
-	'https://api.openproxylist.xyz/socks4.txt',
-	'https://api.openproxylist.xyz/socks5.txt',
-	'https://api.proxyscrape.com/?request=displayproxies&proxytype=socks4',
-	'https://api.proxyscrape.com/v2/?request=displayproxies&protocol=socks4',
-	'https://api.proxyscrape.com/?request=displayproxies&proxytype=socks5',
-	'https://api.proxyscrape.com/v2/?request=displayproxies&protocol=socks5',
-	'https://proxy-list.download/api/v1/get?type=socks4',
-	'https://proxy-list.download/api/v1/get?type=socks5',
-	'https://proxyscan.io/download?type=socks4',
-	'https://proxyscan.io/download?type=socks5',
-	'https://proxyspace.pro/socks4.txt',
-	'https://proxyspace.pro/socks5.txt',
-	'https://raw.githubusercontent.com/ALIILAPRO/Proxy/main/socks4.txt',
-	'https://raw.githubusercontent.com/ALIILAPRO/Proxy/main/socks5.txt',
-	'https://raw.githubusercontent.com/B4RC0DE-TM/proxy-list/main/SOCKS4.txt',
-	'https://raw.githubusercontent.com/B4RC0DE-TM/proxy-list/main/SOCKS5.txt',
-	'https://raw.githubusercontent.com/hookzof/socks5_list/master/proxy.txt',
-	'https://raw.githubusercontent.com/HyperBeats/proxy-list/main/socks4.txt',
-	'https://raw.githubusercontent.com/HyperBeats/proxy-list/main/socks5.txt',
-	'https://raw.githubusercontent.com/jetkai/proxy-list/main/online-proxies/txt/proxies-socks4.txt',
-	'https://raw.githubusercontent.com/jetkai/proxy-list/main/online-proxies/txt/proxies-socks5.txt',
-	'https://raw.githubusercontent.com/manuGMG/proxy-365/main/SOCKS4.txt',
-	'https://raw.githubusercontent.com/manuGMG/proxy-365/main/SOCKS5.txt',
-	'https://raw.githubusercontent.com/mmpx12/proxy-list/master/socks4.txt',
-	'https://raw.githubusercontent.com/mmpx12/proxy-list/master/socks5.txt',
-	'https://raw.githubusercontent.com/monosans/proxy-list/main/proxies/socks4.txt',
-	'https://raw.githubusercontent.com/monosans/proxy-list/main/proxies/socks5.txt',
-	'https://raw.githubusercontent.com/monosans/proxy-list/main/proxies_anonymous/socks4.txt',
-	'https://raw.githubusercontent.com/monosans/proxy-list/main/proxies_anonymous/socks5.txt',
-	'https://raw.githubusercontent.com/MuRongPIG/Proxy-Master/main/socks4.txt',
-	'https://raw.githubusercontent.com/MuRongPIG/Proxy-Master/main/socks5.txt',
-	'https://raw.githubusercontent.com/officialputuid/KangProxy/KangProxy/socks5/socks4.txt',
-	'https://raw.githubusercontent.com/officialputuid/KangProxy/KangProxy/socks5/socks5.txt',
-	'https://raw.githubusercontent.com/prxchk/proxy-list/main/socks4.txt',
-	'https://raw.githubusercontent.com/prxchk/proxy-list/main/socks5.txt',
-	'https://raw.githubusercontent.com/rdavydov/proxy-list/main/proxies/socks4.txt',
-	'https://raw.githubusercontent.com/rdavydov/proxy-list/main/proxies/socks5.txt',
-	'https://raw.githubusercontent.com/rdavydov/proxy-list/main/proxies_anonymous/socks4.txt',
-	'https://raw.githubusercontent.com/rdavydov/proxy-list/main/proxies_anonymous/socks5.txt',
-	'https://raw.githubusercontent.com/roosterkid/openproxylist/main/SOCKS4_RAW.txt',
-	'https://raw.githubusercontent.com/roosterkid/openproxylist/main/SOCKS5_RAW.txt',
-	'https://raw.githubusercontent.com/RX4096/proxy-list/main/online/socks4.txt',
-	'https://raw.githubusercontent.com/RX4096/proxy-list/main/online/socks5.txt',
-	'https://raw.githubusercontent.com/saschazesiger/Free-Proxies/master/proxies/socks4.txt',
-	'https://raw.githubusercontent.com/saschazesiger/Free-Proxies/master/proxies/socks5.txt',
-	'https://raw.githubusercontent.com/ShiftyTR/Proxy-List/master/socks4.txt',
-	'https://raw.githubusercontent.com/ShiftyTR/Proxy-List/master/socks5.txt',
-	'https://raw.githubusercontent.com/TheSpeedX/PROXY-List/master/socks4.txt',
-	'https://raw.githubusercontent.com/TheSpeedX/PROXY-List/master/socks5.txt',
-	'https://raw.githubusercontent.com/UptimerBot/proxy-list/main/proxies/socks4.txt',
-	'https://raw.githubusercontent.com/UptimerBot/proxy-list/main/proxies/socks5.txt',
-	'https://raw.githubusercontent.com/Zaeem20/FREE_PROXIES_LIST/master/socks4.txt',
-	'https://raw.githubusercontent.com/Zaeem20/FREE_PROXIES_LIST/master/socks5.txt',
-	'https://raw.githubusercontent.com/zevtyardt/proxy-list/main/socks4.txt',
-	'https://raw.githubusercontent.com/zevtyardt/proxy-list/main/socks5.txt',
-	'https://spys.me/socks.txt',
-	'https://spys.one/en/socks-proxy-list/'
-))
-
-def get_source(url: str) -> str:
-	''' Get the source of a URL using a Googlebot user-agent. '''
-	req = urllib.request.Request(url)
-	req.add_header('User-Agent', 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)')
-	source  = urllib.request.urlopen(req, timeout=15)
-	return source.read().decode()
-
-# Main
-print('#'*56)
-print('#{0}#'.format(''.center(54)))
-print('#{0}#'.format('SockHub Proxy Scraper'.center(54)))
-print('#{0}#'.format('Developed by acidvegas in Python'.center(54)))
-print('#{0}#'.format('https://git.acid.vegas/proxytools'.center(54)))
-print('#{0}#'.format(''.center(54)))
-print('#'*56)
-total = 0
+# Global
 proxies = list()
-proxy_file = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'proxies.txt')
-print('scanning \033[35m{0:,}\033[0m urls from list...'.format(len(urls)))
-for url in urls: # TODO: Maybe add concurrent.futures support for using larger lists
+
+def find_proxies(url: str) -> str:
+	'''
+	Check a URL for IP:PORT proxies.
+
+	:param url: The URL to check for proxies.
+	'''
 	try:
-		source = get_source(url)
-	except:
-		print('found \033[31m0\033[0m new proxies on \033[34m{0}\033[0m \033[30m(failed to load)\033[0m'.format(url))
-	else:
-		total+= len(source.split())
-		found = set([proxy for proxy in re.findall('[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+:[0-9]+', source, re.MULTILINE) if proxy not in proxies])
-		if found:
-			proxies += found
-			print('found \033[32m{0:,}\033[0m new proxies on \033[34m{1}\033[0m'.format(len(found), url))
+		source = urllib.request.urlopen(urllib.request.Request(url, headers={'User-Agent': 'SockHub/1.0'})).read().decode()
+		if source:
+			found = set(re.findall('[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+:[0-9]+', source, re.MULTILINE))
+			if (new_proxies := [proxy for proxy in found if proxy not in proxies]):
+				proxies += new_proxies
+				print(f'found \033[32m{len(found):,}\033[0m new proxies on \033[34m{url}\033[0m')
 		else:
-			print('found \033[31m0\033[0m new proxies on \033[34m{0}\033[0m \033[30m(duplicates)\033[0m'.format(url))
-if proxies:
-	if len(proxies) < total:
-		print('found \033[32m{0:,}\033[0m total proxies! \033[30m({1:,} duplicates removed)\033[0m'.format(len(proxies), total-len(proxies)))
+			logging.warning(f'found \033[31m0\033[0m new proxies on \033[34m{url}\033[0m \033[30m(source is empty)\033[0m')
+	except Exception as ex:
+		logging.error(f'found \033[31m0\033[0m new proxies on \033[34m{url}\033[0m \033[30m({ex})\033[0m')
+
+
+if __name__ == '__main__':
+	import argparse
+	parser = argparse.ArgumentParser(description='SockHub Proxy Scraper - Developed by acidvegas in Python (https://git.acid.vegas/proxytools)')
+	parser.add_argument('-i', '--input',  help='input file containing a list of URLs to scrape (one per line) or a single URL')
+	parser.add_argument('-o', '--output', help='output file to save proxies to', default='proxies.txt')
+	parser.add_argument('-c', '--concurrency', help='number of concurrent threads to use (default: 10)', default=10, type=int)
+	args = parser.parse_args()
+
+	logging.basicConfig(format='%(message)s', level=logging.INFO)
+
+	if not os.path.isfile(args.input):
+		if args.input.startswith('https://') or args.input.startswith('http://'):
+			logging.info('using input as a single url...')
+			proxy_sources = [args.input]
+		else:
+			logging.fatal('input file does not exist!')
+
+	proxy_sources = open(args.input, 'r').read().split('\n')
+
+	if not proxy_sources:
+		logging.fatal('proxy sources input file is empty!')
+
+	logging.debug('scanning \033[35m{len(urls):,}\033[0m urls from list...')
+
+	with concurrent.futures.ThreadPoolExecutor(max_workers=args.concurrency) as executor:
+		futures = [executor.submit(find_proxies, url) for url in proxy_sources]
+	concurrent.futures.wait(futures)
+
+	if proxies:
+		logging.info('found \033[32m{len(proxies):,}\033[0m total proxies!')
+		proxies.sort()
+		with open (args.output, 'w') as output_file:
+			for proxy in proxies:
+				output_file.write(proxy + '\n')
 	else:
-		print('found \033[32m{0:,}\033[0m total proxies!'.format(len(proxies)))
-	proxies.sort()
-	with open (proxy_file, 'w') as proxy__file:
-		for proxy in proxies:
-			proxy__file.write(proxy + '\n')
+		logging.warning('no proxies found!')

torglass.py

@@ -1,7 +1,11 @@
 #!/usr/bin/env python
 # Tor Glass - Developed by acidvegas in Python (https://git.acid.vegas/proxytools)
 
-import json
+'''
+A simple script to pull a list of all the Tor relays / exit nodes & generate a json database.
+
+The example below will generate a map of all the Tor relays / exit nodes using the ipinfo.io API.
+'''
 
 try:
 	import stem.descriptor.remote
@@ -52,25 +56,31 @@ def get_descriptors() -> dict:
 			tor_map['relay'].append(data)
 	return tor_map
 
+
 if __name__ == '__main__':
+	import json
+
 	print('loading Tor descriptors... (this could take a while)')
 	tor_data = get_descriptors()
+	
 	with open('tor.json', 'w') as fd:
 		json.dump(tor_data['relay'], fd)
 	with open('tor.exit.json', 'w') as fd:
 		json.dump(tor_data['exit'], fd)
+
 	print('Relays: {0:,}'.foramt(len(tor_data['relay'])))
 	print('Exits : {0:,}'.format(len(tor_data['exit'])))
+
 	try:
 		import ipinfo
 	except ImportError:
-		print('missing optional library \'ipinfo\' (https://pypi.org/project/ipinfo/) for map visualization')
-	else:
-		try:
-			handler = ipinfo.getHandler('changeme') # put your ipinfo.io API key here
-			print('Relay Map: ' + handler.getMap([ip['address'] for ip in tor_data['relay']]))
-			print('Exit  Map: ' + handler.getMap([ip['address'] for ip in tor_data['exit']]))
-		except ipinfo.errors.AuthorizationError:
-			print('error: invalid ipinfo.io API key (https://ipinfo.io/signup)')
-		except Exception as ex:
-			print(f'error generating ipinfo map ({ex})')
+		raise ImportError('missing optional library \'ipinfo\' (https://pypi.org/project/ipinfo/) for map visualization')
+	
+	try:
+		handler = ipinfo.getHandler('changeme') # put your ipinfo.io API key here
+		print('Relay Map: ' + handler.getMap([ip['address'] for ip in tor_data['relay']]))
+		print('Exit  Map: ' + handler.getMap([ip['address'] for ip in tor_data['exit']]))
+	except ipinfo.errors.AuthorizationError:
+		print('error: invalid ipinfo.io API key (https://ipinfo.io/signup)')
+	except Exception as ex:
+		print(f'error generating ipinfo map ({ex})')

tortest.py

@@ -19,8 +19,12 @@ EXIT_FINGERPRINT = '379FB450010D17078B3766C2273303C358C3A442' # https://metrics.
 SOCKS_PORT = 9050
 CONNECTION_TIMEOUT = 30  # timeout before we give up on a circuit
 
-def query(url):
-    ''' Uses pycurl to fetch a site using the proxy on the SOCKS_PORT. '''
+def query(url: str):
+    '''
+    Uses pycurl to fetch a site using the proxy on the SOCKS_PORT.
+    
+    :param url: the url to fetch
+    '''
     output = io.StringIO.StringIO()
     query = pycurl.Curl()
     query.setopt(pycurl.URL, url)
@@ -36,7 +40,12 @@ def query(url):
         raise ValueError("Unable to reach %s (%s)" % (url, exc))
 
 def scan(controller, path):
-    ''' Test the connection to a website through the given path of relays using the given controller '''
+    '''
+    Test the connection to a website through the given path of relays using the given controller.
+    
+    :param controller: the controller to use
+    :param path: a list of fingerprints, in order, to build a path through
+    '''
     circuit_id = controller.new_circuit(path, await_build = True)
     def attach_stream(stream):
         if stream.status == 'NEW':
@@ -54,12 +63,13 @@ def scan(controller, path):
         controller.reset_conf('__LeaveStreamsUnattached')
 
 # Main
-with stem.control.Controller.from_port(port=9056) as controller:
-    controller.authenticate('loldongs')
-    relay_fingerprints = [desc.fingerprint for desc in controller.get_network_statuses()]
-    for fingerprint in relay_fingerprints:
-        try:
-            time_taken = scan(controller, [fingerprint, EXIT_FINGERPRINT])
-            print('%s => %0.2f seconds' % (fingerprint, time_taken))
-        except Exception as exc:
-            print('%s => %s' % (fingerprint, exc))
+if __name__ == '__main__':
+    with stem.control.Controller.from_port(port=9056) as controller:
+        controller.authenticate('CHANGEME') # Change this to your Tor control password
+        relay_fingerprints = [desc.fingerprint for desc in controller.get_network_statuses()]
+        for fingerprint in relay_fingerprints:
+            try:
+                time_taken = scan(controller, [fingerprint, EXIT_FINGERPRINT])
+                print('%s => %0.2f seconds' % (fingerprint, time_taken))
+            except Exception as exc:
+                print('%s => %s' % (fingerprint, exc))