BeautifulSoup로 웹 일부분 추출하기

extract_chart_1.py

# -*- coding: UTF-8 -*-
from bs4 import BeautifulSoup
import codecs

def get_html():
    with codecs.open('melon_weekly.html', 'r', "utf-8") as f:
        html = f.read()
    return html
    
def extract_chart():
    html = get_html() # 저장된 파일을 사용합니다.
    
    # BeautifulSoup 로 파싱
    soup = BeautifulSoup(html)
    
    # div 태그 중 id가 top50, top100인 것을 찾아냄
    top50  = soup.find('div', id='tb_list')
    top100 = soup.find('tr', id='lst100')
    
    with codecs.open('top50.html', 'w', "utf-8") as f:
        f.write(top50.prettify())

    with codecs.open('top100.html', 'w', "utf-8") as f:
        f.write(top100.prettify())
    
if __name__ == '__main__':
    extract_chart()