青空文庫の「我輩は猫である」を形態素解析して４文字以上の名詞の出現頻度の高い順にベスト30を表示

wagahaiwa_nekodearu.py

import io
import re
import collections
import zipfile
import requests
from janome.tokenizer import Tokenizer

r = requests.get('http://www.aozora.gr.jp/cards/000148/files/789_ruby_5639.zip')
f = zipfile.ZipFile(io.BytesIO(r.content)).open('wagahaiwa_nekodearu.txt')

text = f.read().decode('cp932')

text = re.sub('《[^》]+》', '', text)
text = re.sub('｜', '', text)
text = re.sub('［.+?］', '', text)
text = re.sub('-----[\s\S]*-----', '', text)
text = re.split('底本：',text)[0]

t = Tokenizer()
wordcount = collections.Counter([
    token.base_form
        for token in t.tokenize(text)
        if token.part_of_speech.split(',')[0] == '名詞' and len(token.base_form) > 3
])

for e in wordcount.most_common(30):
    print(e)