Filters.py

import re


class Filters(object):

    config = {}

    def __init__(self, obj):
        self.config = obj

    def is_select_tld(self, domain):
        for tld in self.config['tlds']:
            pattern = '(?:[a-zA-Z0-9-]+\.)%s' % tld
            match = re.match(pattern, domain)
            if match is not None:
                return True
        return False

    def is_proper_length(self, domain, include_tld=False):
        if include_tld is True:
            if len(domain) <= self.config['maxDomainLength']:
                return True
            else:
                return False
        else:
            name = domain.split('.')[0]
            if len(name) <= self.config['maxDomainLength']:
                return True
            else:
                return False

    def number_of_characters(self, domain, include_tld=False):
        if include_tld is True:
            return len(domain)
        else:
            name = domain.split('.')[0]
            return len(name)

    def contains_keyword(self, domain):
        tld = domain.split('.')[1]
        for keyword in self.config['keywords']:
            pattern = '(?:[a-zA-Z0-9-]+)?%s(?:[a-zA-Z0-9-]+)?(?:\.%s)$' % (keyword, tld)
            match = re.match(pattern, domain)
            if match is not None:
                return True
        return False

main.py

import os.path
import json

import requests
import arrow
import progressbar
from lib.Filters import Filters


local = arrow.now("America/New_York")
tomorrow = local.shift(days=1).format("M-DD-YYYY")

url = "http://www.namejet.com/download/%s.txt" % tomorrow
# csv = "https://snapnames.com/search_dl.sn?type=12"

filename = tomorrow + ".txt"

fp = open("config.json", "r")
config = json.load(fp)
fp.close()

def download_file(url, filename):
    response = requests.get(url, stream=True)
    if response.status_code is 200:
        if not os.path.exists("tmp"):
            os.makedirs("tmp")
        fx = open(os.path.join('tmp', filename), 'wb')
        file_size = int(response.headers['Content-Length'])
        chunk = 1
        num_bars = file_size / chunk
        bar = progressbar.ProgressBar(maxval=num_bars).start()
        i = 0
        for chunk in response.iter_content():
            fx.write(chunk)
            bar.update(i)
            i += 1
        fx.close()
        print("Done.")
    else:
        print("Couldn\'t get file.")


def filter_domains(domains):
    for domain in domains:
        filter = Filters(config)
        a = filter.is_select_tld(domain)
        b = filter.is_proper_length(domain)
        c = filter.contains_keyword(domain)

        if not os.path.exists("results"):
            os.makedirs("results")
        fx = open(os.path.join('results', 'results_%s' % filename), 'a')
        if a is True and b is True and c is True:
            print(domain)
            fx.write(domain + '\n')
        fx.close()


def main():
    if os.path.isfile(os.path.join('tmp', filename)):
        pass
    else:
        print("Downloading tomorrow\'s list of expiring domains...")
        download_file(url, filename)

    print("Filtering domains according to your specified conditions...")
    domains = [line.rstrip('\n') for line in open(os.path.join('tmp', filename))]
    filter_domains(domains)


if __name__ == '__main__':
    main()