Check your browsing history for sites using Cloudflare

chrome.py

import sqlite3
import tldextract

history_domains = set()
cf_domains = None

print("Loading domains from Chrome browsing history...")

# Copy history from ~/Library/Application Support/Google/Chrome/Default/History
conn = sqlite3.connect('History')
c = conn.cursor()
for url in c.execute("SELECT url FROM urls"):
    history_domains.add(tldextract.extract(url[0]).registered_domain)

print("Added %d domains." % len(history_domains))

print("Loading Cloudflare domains...")

# Get domains here: https://github.com/pirate/sites-using-cloudflare
cf_domains = set(domain.strip() for domain in open('sorted_unique_cf.txt'))

print("Added %d domains." % len(cf_domains))

print("Processing intersection...")
intersection = history_domains.intersection(cf_domains)

print("------------------------------")
for domain in sorted(intersection):
    print(domain)
print("------------------------------\nOK: %d domains found." % len(intersection))

firefox.py

import sqlite3
import tldextract

history_domains = set()
cf_domains = None

print("Loading domains from Firefox browsing history...")

# Copy history from ~/Library/Application Support/Firefox/Profiles/*YOUR PROFILE*/places.sqlite
conn = sqlite3.connect('places.sqlite')
c = conn.cursor()
for url in c.execute("SELECT url FROM moz_places"):
    history_domains.add(tldextract.extract(url[0]).registered_domain)

print("Added %d domains." % len(history_domains))

print("Loading Cloudflare domains...")

# Get domains here: https://github.com/pirate/sites-using-cloudflare
cf_domains = set(domain.strip() for domain in open('sorted_unique_cf.txt'))

print("Added %d domains." % len(cf_domains))

print("Processing intersection...")
intersection = history_domains.intersection(cf_domains)

print("------------------------------")
for domain in sorted(intersection):
    print(domain)
print("------------------------------\nOK: %d domains found." % len(intersection))

requirements.txt

tldextract

safari.py

import sqlite3
import tldextract

history_domains = set()
cf_domains = None

print("Loading domains from Safari browsing history...")

# Copy history from ~/Library/Safari/History.db
conn = sqlite3.connect('History.db')
c = conn.cursor()
for url in c.execute("SELECT url FROM history_items"):
    history_domains.add(tldextract.extract(url[0]).registered_domain)

print("Added %d domains." % len(history_domains))

print("Loading Cloudflare domains...")

# Get domains here: https://github.com/pirate/sites-using-cloudflare
cf_domains = set(domain.strip() for domain in open('sorted_unique_cf.txt'))

print("Added %d domains." % len(cf_domains))

print("Processing intersection...")
intersection = history_domains.intersection(cf_domains)

print("------------------------------")
for domain in sorted(intersection):
    print(domain)
print("------------------------------\nOK: %d domains found." % len(intersection))

@sinnfeinn
check out this:
http://stackoverflow.com/questions/28126140/python-sqlite3-operationalerror-no-such-table

Here is what I had to do to get safari.py working on a relatively new OS X 10.11.6 install:

1. sudo easy_install pip

2. sudo pip install tldextract

3. curl https://raw.githubusercontent.com/pirate/sites-using-cloudflare/master/sorted_unique_cf.txt --output /Users/YOUR_USERNAME/Desktop/sorted_unique_cf.txt

4. In safari.py, change
   conn = sqlite3.connect('History')
   to
   conn = sqlite3.connect('/Users/YOUR_USERNAME/Library/Safari/History.db')
   and
   sorted_unique_cf.txt
   to
   /Users/YOUR_USERNAME/Desktop/sorted_unique_cf.txt

@tinyapps, @Payuing, @skypather

Thanks! Changing it to the following worked:
conn = sqlite3.connect('/Users/YOUR_USER/Library/Application Support/Google/Chrome/Default/History')
and
cf_domains = set(domain.strip() for domain in open('/Users/YOUR_USER/Desktop/sorted_unique_cf.txt'))