In [ ]:

    

from urllib2 import HTTPError

import urllib2
import urllib
import os
import shutil

import zipfile


    

In [ ]:

    

get_html = lambda url: urllib2.urlopen(url).read()
download_file = lambda url, fout: urllib.urlretrieve(url, fout)


    

In [ ]:

    

for i in xrange(50, 409):
    print i
    try:
        raw = get_html('http://mnemosyne-proj.org/node/%d' % i)
    except HTTPError:
        continue
    for s in raw.split('.cards"')[:-1]:
        fin = s.split('href="')[-1]
        deck = fin.split('/')[-1]
        print deck
        download_file(fin + '.cards', os.path.join('shared_decks', deck + '.zip'))


    

In [ ]:

    

fs = [x for x in os.listdir('shared_decks') if '.zip' in x]
for f in fs:
    abs_f = os.path.join('shared_decks', f)
    try:
        with zipfile.ZipFile(abs_f, 'r') as g:
            g.extractall(abs_f.replace('.zip', ''))
            os.rename(os.path.join(abs_f.replace('.zip', ''), 'cards.xml'), abs_f.replace('.zip', '.xml'))
            shutil.rmtree(abs_f.replace('.zip', ''))
    except:
        pass


    

In [ ]: