In [171]:

    

import re
from csv import writer
from urllib.parse import unquote

from furl import furl


    

In [189]:

    

URL_QUERY_PARAM = re.compile(r'\"(https\:\/\/osf\.io\/share\/?\?[^\"]*)')


    

In [190]:

    

with open('log') as f:
    matches = list(map(lambda x: furl(x[0]), filter(lambda x: x, [URL_QUERY_PARAM.findall(line) for line in f])))


    

In [191]:

    

matches = list(map(dict, {tuple(match.args.items()) for match in matches if len(match.args) > 1}))


    

In [192]:

    

keys = ['q', 'optional', 'required', 'sort']


    

In [198]:

    

lines = [keys] + list(map(get(match), keys) for match in matches)


    

In [199]:

    

with open('logs.csv', 'w') as f:
    csv_writer = writer(f)
    csv_writer.writerows(lines)


    

In [197]:

    

def get(match):
    return lambda key: match.get(key, '').strip()


    

In [ ]: