[Python] 벅스 날짜별 크롤링

벅스 날짜별 크롤링

 

import requests
from bs4 import BeautifulSoup
import csv
from time import sleep

def song_info(tr):
    rank = tr.find('strong').text
    try:
        title = tr.find('p', {'class': 'title'}).find('a').text
    except:
        title = tr.find('p', {'class': 'title'}).find('span','').text
    artist = tr.find('p', {'class': 'artist'}).find('a').text
    try:
        album = tr.find('a', {'class': 'album'}).text
    except:
        album = tr.find('p', {'class': 'album'}).find('span','').text
    row = [rank, title, artist, album]
    # print(rank) # 몇번째 순위의 노래가 오류인지를 확인
    return row

def save_csv(filename, rows):
    file = open(filename, 'w', encoding='utf-8-sig', newline='')
    csvfile = csv.writer(file)
    csvfile.writerow(['rank', 'title', 'artist', 'album'])
    csvfile.writerows(rows)
    file.close()

def bugs_chart_date(date):
    url = f"https://music.bugs.co.kr/chart/track/day/total?chartdate={date}"
    response = requests.get(url)
    #print(response.headers['Content-Type'] #헤더의 Content-Type 식별하기.
    text = response.text #text타입이므로 reponse.text를 text라는 변수에 넣는다.
    html = BeautifulSoup(text,'html.parser')
    tr_list = html.find('table', {'class':'list'}).find('tbody').find_all('tr')

    #순위태그, 제목태그 찾기
    rows = []
    for tr in tr_list:
        rows.append(song_info(tr))

    return rows


year = 2018
month = 3
for day in range(1,6):
    date = f'{year}{month:0>2}{day:0>2}'
    rows = bugs_chart_date(date)
    filename = f'bugs_chart_{date}.csv'
    save_csv(filename, rows)
    sleep(2)