[Python] Google 크롬 검색 기록에서 WordCloud를 생성하고 Streamlit에서 시각화하는 방법 참고

사전 준비

  pip install pandas
  pip install streamlit
  pip install janome
  pip install matplotlib
  pip install wordcloud

  C:\Users\XXXXXXXX\AppData\Local\Google\Chrome\User Data\Default\History

C:/Windows/Fonts/...

코드

import streamlit as st
from janome.tokenizer import Tokenizer
import collections
import pandas as pd
import sqlite3
from contextlib import closing
import matplotlib.pyplot as plt
from wordcloud import WordCloud

history = './History'

# ブラウザ履歴データを検索
def search_history():
    browser_history_text = ''

    with closing(sqlite3.connect(history)) as conn:
        c = conn.cursor()
        statements = "select title LONGVARCHAR from 'urls'"
        results= c.execute(statements)
        for result in results:
            browser_history_text += result[0]
    return browser_history_text 


# ブラウザ履歴データを形態素解析
def analyze_history(history: str):
    t = Tokenizer()

    # 頻出単語を取得
    freq_of_words = collections.Counter(token.base_form for token in t.tokenize(history)
                            if token.part_of_speech.startswith('名詞,固有名詞'))
    return freq_of_words 

# WordCloud生成
def generate_wordcloud(analyze_result: str):
    dic_result = dict(analyze_result)
    # フォントファイル名指定
    wordcloud = WordCloud(background_color='white',
                          font_path='C:/Windows/Fonts/...',
                          width=800, height=600).fit_words(dic_result)
    return wordcloud


if __name__ == "__main__":
    browser_history_text = search_history()
    freq_of_words = analyze_history(browser_history_text)
    wordcloud = generate_wordcloud(freq_of_words)
    st.title('ブラウザ検索履歴 分析')

    # Wordcloud描画時の警告を非表示にするため
    st.set_option('deprecation.showPyplotGlobalUse', False)

    # WordCloud 表示
    plt.axis("off")
    plt.tight_layout()
    plt.imshow(wordcloud, interpolation='bilinear')
    st.pyplot()

    # 頻出検索単語表 表示
    df = pd.DataFrame(freq_of_words.most_common()[:10], columns=['単語', '回数'])
    st.dataframe(df)

동작 확인

streamlit run wc.py

You can now view your Streamlit app in your browser.

  Local URL: http://localhost:8501
  Network URL: http://10.4.113.198:8501

참고 정보