Python script to do some chat analytics

stat.py

import datetime
import os
import re
import urllib.error
import urllib.request


def download_log_files(date_obj):
    today = datetime.datetime.now()
    today = today.replace(hour=0, minute=0, second=0, microsecond=0)

    first_half_url = date_obj.strftime('%B%%20%Y')
    second_half_url = date_obj.strftime('%Y-%m-%d')
    log_file = f'data/{second_half_url}.txt'

    if not os.path.exists(log_file):
        if date_obj < today:
            url = f'https://overrustlelogs.net/Singsing%20chatlog/{first_half_url}/{second_half_url}.txt'

            try:
                req = urllib.request.Request(url, headers={
                    # masquerade as IE6 KEK
                    'User-Agent': 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1)',
                })

                with urllib.request.urlopen(req) as r, open(log_file, 'wb') as f:
                    f.write(r.read())

            except urllib.error.HTTPError:
                pass


chat_regex = re.compile(r'\[(.+?)\] (.+?): (.+)')


def parse_log_files(date_obj):
    chat_data = []
    log_file_path = f'data/{date_obj.strftime("%Y-%m-%d")}.txt'

    try:
        with open(log_file_path, 'r', encoding='utf-8') as f:
            for line in f:
                match = chat_regex.search(line)

                if match and len(match.groups()) == 3:
                    chat_date = datetime.datetime.strptime(match.group(1), '%Y-%m-%d %H:%M:%S UTC')
                    chat_user = match.group(2)
                    chat_message = match.group(3)

                    chat_data.append({
                        'date': chat_date,
                        'user': chat_user,
                        'message': chat_message,
                    })
                # else:
                #     raise Exception('Corrupted message format!')

    except FileNotFoundError:
        pass

    return chat_data


def create_date_iterator(from_date, to_date=None):
    from_date = datetime.datetime.strptime(from_date, '%Y-%m-%d')
    from_date -= datetime.timedelta(days=1)

    if to_date:
        to_date = datetime.datetime.strptime(to_date, '%Y-%m-%d')
    else:
        to_date = datetime.datetime.now()
        to_date = to_date.replace(hour=0, minute=0, second=0, microsecond=0)
        to_date -= datetime.timedelta(days=1)

    while from_date < to_date:
        from_date += datetime.timedelta(days=1)
        yield from_date


def get_top_100_for_dict(input_dict):
    def _sort_fn(kv):
        return kv[1]

    output_list = sorted(input_dict.items(), key=_sort_fn, reverse=True)
    return output_list[:100]


date_list = create_date_iterator('2018-08-01', '2018-08-31')
emote_list = ('PepeLaugh', 'Kekk', )
emote_regex = re.compile(f'(?:^| )({"|".join(emote_list)})(?: |$)')

for date_obj in date_list:
    # used to download the log file
    download_log_files(date_obj)

    # parse the data
    chat_data = parse_log_files(date_obj)
    user_dict = {}
    cmd_dict = {}
    emote_dict = {}

    for i in chat_data:
        if i['user'] not in user_dict:
            user_dict[i['user']] = 0

        user_dict[i['user']] += 1

        if i['message'].startswith('!'):
            cmd = i['message'].split(' ')[0]

            if cmd not in cmd_dict:
                cmd_dict[cmd] = 0

            cmd_dict[cmd] += 1

        em_match = emote_regex.search(i['message'])
        if em_match:
            for em in em_match.groups():
                if em not in emote_dict:
                    emote_dict[em] = 0

                emote_dict[em] += 1

    if chat_data:
        emote_dict = get_top_100_for_dict(emote_dict)
        print(emote_dict)