스파르타코딩클럽 3주차
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&ymd=20200403&hh=23&rtm=N&pg=1',headers=headers)
soup = BeautifulSoup(data.text, 'html.parser')
genie_music = soup.select('#body-content > div.newest-list > div > table > tbody > tr')
for music in genie_music:
music_rank = music.select_one('td.number').text.split('\n')[0]
music_title = music.select_one('td.info > a.title.ellipsis').text.strip()
music_artist = music.select_one('td.info > a.artist.ellipsis').text
print(music_rank, music_title, '-', music_artist)
결과
2020년 4월 3일 지니차트 크롤링