嵐の歌詞を分析して可視化してみる。

import requests
import pandas as pd
import time
from bs4 import BeautifulSoup

#データを入れるリスト
list_df = pd.DataFrame(columns=['歌詞'])

for page in range(1, 3):
   base_url = 'https://www.uta-net.com'

    #歌詞一覧ページ
    url = 'https://www.uta-net.com/artist/3891/0/' + str(page) + '/'
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'lxml')
    links = soup.find_all('td', class_='side td1')
    for link in links:
        url = base_url + (link.a.get('href'))

        #歌詞詳細ページ
        response = requests.get(url)
        soup = BeautifulSoup(response.text, 'lxml')
        song_lyrics = soup.find('div', itemprop='lyrics')
        song_lyric = song_lyrics.text
        song_lyric = song_lyric.replace('\n','')
        #1秒待機
        time.sleep(1)

        #取得した歌詞を表に追加
        tmp_se = pd.DataFrame([song_lyric], index=list_df.columns).T
        list_df = list_df.append(tmp_se)

#保存
list_df.to_csv('list.csv', mode = 'a', encoding='cp932')

import pandas as pd
import re
from janome.tokenizer import Tokenizer

#lファイルを読み込み
file = pd.read_csv('list.csv', encoding='cp932')

song_lyrics = file['歌詞'].tolist()

t = Tokenizer()

results = []

for s in song_lyrics:
    tokens = t.tokenize(s)
    r = []

    for tok in tokens:
        if tok.base_form == '*':
            word = tok.surface
        else:
            word = tok.base_form

        ps = tok.part_of_speech

        parts_of_speech = ps.split(',')[0]

        if parts_of_speech in ['名詞', '形容詞', '動詞', '副詞']:
            r.append(word)

    rl = (' '.join(r)).strip()
    results.append(rl)
    #余計な文字コードの置き換え
    result = [i.replace('\u3000','') for i in results]
    print(result)

text_file = 'list.txt'
with open(text_file, 'w', encoding='utf-8') as fp:
    fp.write("\n".join(result))

from wordcloud import WordCloud

file = open('list.txt', encoding='utf-8')
text = file.read()

#無意味な単語除去
delete_words = ['そう', 'ない', 'いる', 'する', 'まま', 'よう', 'てる', 'なる', 'こと', 'もう', 'いい', 'ある', 'ゆく', 'れる']

#日本語のフォントパス
font = 'ここにフォントのファイルパスをいれる'

wordcloud = WordCloud(background_color='white',
    width=800, height=600,  font_path=font,  stopwords=set(delete_words)).generate(text)

#画像を保存
wordcloud.to_file('./ARASHI_song_lyrics.png')