3주차 지니뮤직 크롤링하기

이재윤·2021년 7월 20일
0
import requests
from bs4 import BeautifulSoup

from pymongo import MongoClient
client = MongoClient('localhost', 27017)
db = client.dbsparta

headers = {'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'}
data = requests.get('https://www.genie.co.kr/chart/top200?ditc=D&rtm=N&ymd=20210719',headers=headers)

soup = BeautifulSoup(data.text, 'html.parser')

trs = soup.select('#body-content > div.newest-list > div > table > tbody > tr')
for tr in trs :
    title = tr.select_one('td.info > a.title.ellipsis').text.strip()
    rank = tr.select_one('td.number').text[0:2].strip()
    artist = tr.select_one(' td.info > a.artist.ellipsis').text
    print(rank, title, artist)

https://www.genie.co.kr/chart/top200?ditc=D&rtm=N&ymd=20210719

profile
장기적으론 낙관주의, 단기적으론 현실주의

0개의 댓글