크롤링_멜론 음원 차트 수집(실습)

import requests as req
import pandas as pd
from bs4 import BeautifulSoup as bs

url ='https://www.melon.com/chart/index.htm'

# 서버에게 브라우저로 접속했다라는 것을 인지시키기 위한 헤더
header = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36'}
res = req.get(url, headers=header).text

html = bs(res, 'lxml')

# 하나만 가져오기 select_one
# select를 이용하면 반환하는 값은 리스트
rank = html.select_one('td span.rank')
albumlmg = html.select_one('a.image_typeAll > img')
songNm = html.select_one('div.ellipsis.rank01 > span')
artist = html.select_one('div.ellipsis.rank02 span')

print(rank.text)

# print(albumlmg.get('alt')), print(albumlmg.get('width'))
print(albumlmg.get('src'))

print(songNm.text)
print(artist.text)

 

# select를 이용해서 여러개 값 구하기
ranks = html.select('td span.rank')
albumlmgs = html.select('a.image_typeAll > img')
songNms = html.select('div.ellipsis.rank01 > span > a')
artists = html.select('div.ellipsis.rank02 span')

ranklist = []
albumimglist = []
songNmlist = []
artistlist = []

for i in range(len(ranks)):
    ranklist.append(ranks[i].text)
    albumimglist.append(albumlmgs[i].get('src'))
    songNmlist.append(songNms[i].text)
    artistlist.append(artists[i].text)
    
#     print(ranks[i].text)
#     print(albumlmgs[i].get('src'))
#     print(songNms[i].text)
#     print(artists[i].text)
#     print('-' * 20)

melon_dic = {
    '순위' : ranklist,
    '곡명' : songNmlist,
    '아티스트' : artistlist,
    '이미지URL' : albumimglist
}

melon_df = pd.DataFrame(melon_dic)
melon_df.head()

 

# melon_top100.csv 파일로 저장하기
melon_df.to_csv('melon_top100.csv', encoding = 'euc-kr')