accept-language.py

#!/usr/bin/python3

import csv
import math
import random

rows_by_logrank = {}

with open('majestic_million.csv', 'r') as csvfile:
    majestic = csv.DictReader(csvfile)
    for row in majestic:
        rank = int(row['GlobalRank'])
        logrank = int(math.log10(rank))
        if logrank in rows_by_logrank:
            rows_by_logrank[logrank].append(row)
        else:
            rows_by_logrank[logrank] = [row]

for logrank, rows in rows_by_logrank.items():
    if len(rows) < 10:
        continue
    subset = random.sample(rows, 10)
    print(f'# Logrank {logrank}')
    for row in subset:
        domain = row['Domain']
        rank = row['GlobalRank']
        print(f'## {domain} ({rank})')