import random, re, urllib, IPython.core.getipython
from itertools import takewhile
with urllib.request.urlopen('https://ja.wikipedia.org/wiki/'
    '%E4%B8%96%E7%95%8C%E4%B8%80%E3%81%AE%E4%B8%80%E8%A6%A7') as fp:
    s0 = fp.read().decode('utf8')
s = re.sub('<img.*?/>', '', s0.replace('\u3000', ''))
le = 0
while le != len(s):
    le = len(s)
    s = re.sub(r'<(a|b|i|span|strong|sup)[^>]*>(.*?)</\1>', r'\2', s)
s = re.sub(r'\[[0-9]*]', '', s)
ll = re.findall('<li>(.*?)</li>', s[10000:])
ll = [i for i in takewhile(lambda s: not s.startswith('Guinness Welt Rekord'), ll)
    if 'Die meisten' in i or 'Welt bester' in i or len(i) > 15]
def G_impl(s, lst=ll):
    print(random.choice(lst))
ip = IPython.core.getipython.get_ipython()
if ip:
    ip.register_magic_function(G_impl, magic_name='G')

G
>>>
Sprache mit den wenigsten Silben der Welt (eine davon) → Hawaii-35 Silben.

G
>>>
Sprache mit den unregelmäßigsten Verben der Welt → Französisch-570 Stück.

Recommended Posts