Clickstream_parser

parser.py

# License: MIT
import gzip


def search(name, i):
    result = []
    with gzip.open('clickstream-enwiki-2017-12.tsv.gz','rb') as f:
        for line in f:
            line = line.decode('utf-8').replace('\n', '')
            if line.split('\t')[i] == name:
                result.append(line)
    result.sort(key=lambda t: int(t.split('\t')[3]), reverse=True)
    total = sum([int(t.split('\t')[3]) for t in result])
    print('\n'.join(result[:20]))
    print('Total: ' + str(total))


all_ = ['Hassan_Rouhani', 'Iran', 'Ali_Khamenei', 'Alexis_Texas', 'Homosexuality', 'Same-sex_marriage']
for case in all_:
    search(case, 0)
    print('-------')
    search(case, 1)
    print('-------')