Python Script for Getting Data You Need From Domain Names Lists
Tips for Using the Domains Index’s Lists
Today I would want to show you an interesting way of getting the data you need for your сustomized request. It is super easy!
For example, if you need to have the list with all domain names which contain in their names the word “domains”, using the script below and any of our domain lists you want to analyze, you can get a bunch of files with scattered statistics and selected data. Just install the script and put “your request description” and a domain list you recently bought from us (for example, the whole ccTLD list CSV file) into the script:
| #the word/phrase or combination we are looking for in domain names | |
| query = "domains" | |
| #specify the list name | |
| domain_list = "cctld.csv" | |
| import pandas as pd | |
| import numpy as np | |
| query_full = [] | |
| query_entries = [] | |
| tlds = [] | |
| from collections import defaultdict | |
| counter_full = defaultdict(int) | |
| counter_entries = defaultdict(int) | |
| with open(domain_list,'rb') as f: | |
| for x in f: | |
| if x.count('.') == 1: | |
| tld = x.split(".",1)[1].rstrip('\r\n') | |
| dname = x.split(".",1)[0].rstrip('\r\n') | |
| #looking for the domain names fully equal to the query and marking the TLDs with such names in dictionary, creating a list of tuples (name,tld) | |
| if query == dname: | |
| counter_full[tld] = 1 | |
| query_full.append((dname,tld)) | |
| #looking for the domain names with the query string and marking the TLDs with such names in dictionary, creating a list of tuples (name,tld) | |
| if query in dname: | |
| counter_entries[tld] += 1 | |
| query_entries.append((dname,tld)) | |
| #creating a total list of TLDs found un domain_list | |
| if tld in tlds: | |
| pass | |
| else: | |
| tlds.append(tld) | |
| #adding zeros to the dictionary values for TLDs without fully equal to the query domains. | |
| for tld in tlds: | |
| if tld in counter_full: | |
| pass | |
| else: | |
| counter_full[tld] = 0 | |
| import pandas as pd | |
| import numpy as np | |
| #creating dataframe from dictionary | |
| count_query_entries = pd.DataFrame(counter_full, index=[query]) | |
| count_query_entries.head() | |
| tld_with_max = max(counter_entries.iterkeys(), key=lambda k: counter_entries[k]) | |
| print "{} maximum names with - {} - are in - {} - TLD".format(counter_entries[tld_with_max], query, tld_with_max) | |
| import pylab as pl | |
| import numpy as np | |
| X = np.arange(len(counter_entries)) | |
| pl.bar(X, counter_entries.values(), align='center', width=0.5) | |
| pl.xticks(X, counter_entries.keys()) | |
| ymax = max(counter_entries.values()) + 1 | |
| pl.ylim(0, ymax) | |
| pl.show() | |
| #adding zeros to the dictionary values for TLDs without query in a names | |
| for tld in tlds: | |
| if tld in counter_entries: | |
| pass | |
| else: | |
| counter_entries[tld] = 0 | |
| import pandas as pd | |
| import numpy as np | |
| #append dataframe with counter_entries | |
| count_query_entries = count_query_entries.append(pd.DataFrame(counter_entries, index=['has "{}" in name'.format(query)])) | |
| count_query_entries.tail() | |
| #saving query usage statistics in domain names to a csv file | |
| fname = 'usage_of_{}_statistics.csv'.format(query) | |
| count_query_entries.to_csv(fname, sep='\t', encoding='utf-8') | |
| #saving the list of tld's without registred query domain names | |
| tld_with_0 = [] | |
| for tld in counter_full: | |
| if counter_full[tld] == 0: | |
| tld_with_0.append(tld) | |
| fname = 'list_of_tlds_without_{}.csv'.format(query) | |
| save_f = open(fname, 'w') | |
| for item in tld_with_0: | |
| save_f.write("%s\n" % item) | |
| #saving the list of domain names consists only from query string | |
| fname = 'list_of_tlds_with_full_{}.csv'.format(query) | |
| save_f = open(fname, 'w') | |
| for name,tld in query_full: | |
| save_f.write('{}.{}\n'.format(name,tld )) | |
| #saving the list of domain names includes query string | |
| fname = 'list_of_tlds_with_partially_{}.csv'.format(query) | |
| save_f = open(fname, 'w') | |
| for name,tld in query_entries: | |
| save_f.write('{}.{}\n'.format(name,tld )) |
The results of the script are combined in four CSV files:
1. List of domain names consisting from query keyword(sample list_of_tlds_with_full_domains):
2. List of domain names containing a query keyword (sample list_of_tlds_with_partially_domains):
3. List of zones (TLDs), were domains names are consisting from the whole keyword are still available for registration (sample list_of_tlds_withoutdomains):
4. Statistical information for all TLDs about names consisting or containing query keyword (sample usage_of_domains_statistics):
So, you simply could have very helpful information with alive names according to your demand.
Enjoy and give us your feedback about how useful do you find it and how you used it in everyday tasks.
Thanks and have a good one!