mailinglist-mirror.py

import urllib.request
import os


archive = 'https://mail.python.org/pipermail/numpy-discussion'
months = ('January', 'February', 'March', 'April', 'May', 'June', 'July',
          'August', 'September', 'October', 'November', 'December')
output = 'mirror'

if not os.path.isdir(output):
    os.mkdir(output)

for year in range(2000, 2019):
    for month in months:
        thread = f'{archive}/{year}-{month}/thread.html'
        print(f'Fetching {thread}')
        with urllib.request.urlopen(thread) as response:
            html = response.read()
            with open(f'{output}/{year}-{month}.html', 'wb') as f:
                f.write(html)