#! /usr/bin/env python3
import urllib
import urllib.request
import bs4
import re
import sys
import time

months = ['January','February','March','April',
          'May','June','July','August','September',
          'October','November','December']

years = ['2012', '2013', '2014','2015', 
         '2016', '2017', '2018']

urlbody = "https://afnog.org/pipermail/afnog/" 
generated = 'This archive was generated by'
nameset = set()
count_instances = dict()
mails_total = 0

# Create timestamp 
ts = time.strftime("%Y%m%d-%H%M-%S")

# Find names function

def find_names(*args):
    counter = 0
    url = args[0]
    beautiful = urllib.request.urlopen(url).read()
    soup = bs4.BeautifulSoup(beautiful, 'html.parser')
    tags = soup('i')

    for tag in tags:
        for match in re.findall(r'<i>(.*)', str(tag)):
            if '</i>' in match or generated in match:
                pass
            else:
                counter += 1
                nameset.add(match)
    return(counter)

    # End function

# Get the year 
year = input('Enter the year [2012 - 2018| all]: ')
year = year.lower()

# Define output files 
names_file_txt = '{}-AfNOG-names-{}.txt'.format(ts, year)
names_file_csv = '{}-AfNOG-names-{}.csv'.format(ts, year)

if year == 'all' or year in years:
    pass
else:
    print('Not a valid year.') 
    sys.exit(1)

if year.lower() != 'all':
    years = [year]

# Process years
for y in years:
    print()
    sys.stdout.write('Processing {} - '.format(y))
    sys.stdout.flush()
    # Process months
    for month in months:
        try:
            url = urlbody + y + '-' + month + '/author.html'
            count = find_names(url)
            count_instances[month] = count
        except:
            print('\nNo {} detail in {} yet'.format(month, y))
            break

        sys.stdout.write('{} '.format(month[0:3]))
        sys.stdout.flush()

# Print summary details to console
print('\nSummary')
print('-' * len('Summary'))
print()

for y in years:
    for k, v in count_instances.items():
        # Uncomment for mail per month details
        # print(v, 'mails in', k, y)
        mails_total += v

print ('{} unique users wrote {} mails'
       .format(len(nameset),mails_total))
print()

# Open file for username output
fh_txt = open(names_file_txt, mode='w', encoding='utf-8')
fh_csv = open(names_file_csv, mode='w', encoding='utf-8')

# Print usernames to file
fh_txt.write('Users names for ')
fh_txt.write(year)
fh_txt.write('\n')
dash_length = len('Users names for ') + len(year)
fh_txt.write('-' * dash_length)
fh_txt.write('\n')

pad = len(max(nameset, key=len)) + 3
 
for c, name in enumerate(nameset):
    if (c % 2 == 0):
        fh_txt.write('\n')
    txt = '{}{}'.format(name, ' ' * (pad - len(name)))
    fh_txt.write(txt)
    csv = '{},'.format(name)
    fh_csv.write(csv)

fh_txt.close()
fh_csv.close()

# End
sys.exit(0)