Created
May 7, 2016 07:40
-
-
Save zupo/593f8fea2bc26afd0f5dafb3daa45b4a to your computer and use it in GitHub Desktop.
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
#!/usr/bin/python | |
"""How many Alexa top 1 million sites are using self-hosted nameservers? | |
top.csv is downloaded from Alexa: http://s3.amazonaws.com/alexa-static/top-1m.csv.zip | |
""" | |
import gevent.monkey | |
gevent.monkey.patch_all() | |
import gevent | |
from gevent import Greenlet | |
from gevent.pool import Pool | |
import dns.resolver | |
import random | |
count = 0 | |
skipped = 0 | |
failed = 0 | |
pool = Pool(100) | |
def fetch(id_, domain): | |
global count | |
try: | |
for record in dns.resolver.query(domain, 'NS'): | |
if domain in record.to_text(): | |
count += 1 | |
print('[{}/{}] Found domain with self-hosted NS: {}'.format( | |
count, id_, domain)) | |
return | |
except (dns.resolver.NoAnswer, dns.resolver.NXDOMAIN, dns.resolver.NoNameservers): | |
global skipped | |
skipped += 1 | |
except Exception: | |
global failed | |
failed += 1 | |
raise | |
def asynchronous(): | |
domains = [] | |
with open('top.csv') as f: | |
domains = [(line.strip('\n').split(',')[0], line.strip('\n').split(',')[1]) for line in f.readlines()] | |
threads = [pool.spawn(fetch, id_, domain) for id_, domain in domains] | |
pool.join() | |
print('ALL: {}, COUNT: {}, SKIPPED: {}, FAILED: {}'.format( | |
domains[-1][0], count, skipped, failed)) | |
asynchronous() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment