지니 크롤링

leehowook·2022년 4월 28일
0
post-custom-banner

import requests
from bs4 import BeautifulSoup

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=M&rtm=N&ymd=20210701',headers=headers)

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

trs = soup.select('#body-content > div.newest-list > div > table > tbody > tr')

for tr in trs:
rank = tr.select_one('td.number').text[0:2].strip()
title = tr.select_one('td.info > a.title.ellipsis').text.strip()
if '19금' in title:
title = '19금 ' + tr.select_one('td.info > a.title.ellipsis').text.strip().lstrip('19금').strip()
artist = tr.select_one('td.info > a.artist.ellipsis').text

print(rank,title,artist)
profile
be higher
post-custom-banner

0개의 댓글