Seaborn 활용 2

환경

전 포스팅 참조

사전 세팅

전 포스팅 참조

패키지

전 포스팅 참조

    import requests as rq
    from bs4 import BeautifulSoup
    user_agent = {'User-Agent': 'Mozilla/5.0 bla bla bla bla'}
    import time
    from collections import Counter

실행

    # CRAWL
    cnt = Counter()
    idx = 0
    while idx < 11: # 11 페이지만
        res = rq.get(f'https://qna.programmers.co.kr/?page={idx}', user_agent)
        time.sleep(1)
        parsed = BeautifulSoup(res.text, 'html.parser')
        ul = parsed.find('ul', 'question-list')
        lists = ul.find_all('li', 'question-list-item')
        for li in lists:
            lis = li.find_all('li', 'label-tag')
            for l in lis:
                cnt[l.text.strip()] += 1
        idx += 1
    print(cnt)

    # PLOT
    # 폰트
    %rm ~/.cache/matplotlib -rf
    font_path = './NanumGothicCoding.ttf'
    font_prop = fm.FontProperties(fname=font_path)
    print(font_prop.get_name())
    plt.rcParams['font.family'] = font_prop.get_name()

    # 카운터 상위 10 컷
    top_ten = cnt.most_common(10)

    # plot setup
    plt.figure(figsize=(8, 4)) # this goes before sns
    sns.barplot(x=[e[0] for e in top_ten], y=[e[1] for e in top_ten])
    plt.title('Thread topics')
    plt.xlabel('Names')
    plt.ylabel('Frequency')
    plt.show()

출력 정상 확인