3주차 과제 비교
15 Zeilen
## 웹 크롤링에 필요한 세팅: requests와 bs4 패키지
import requests
import requests
from bs4 import BeautifulSoup
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'}
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)
data = requests.get('https://www.genie.co.kr/chart/top200?ditc=M&rtm=N&ymd=20210701',headers=headers)
soup = BeautifulSoup(data.text, 'html.parser')
soup = BeautifulSoup(data.text, 'html.parser')
trs = soup.select('#body-content > div.newest-list > div > table > tbody > tr')
## 지니뮤직의 1~50위 곡의 순위/곡명/가수를 스크래핑해보자
# 순위
#body-content > div.newest-list > div > table > tbody > tr:nth-child(1) > td.number
# 곡명
#body-content > div.newest-list > div > table > tbody > tr:nth-child(1) > td.info > a.title.ellipsis
# 가수
#body-content > div.newest-list > div > table > tbody > tr:nth-child(1) > td.info > a.artist.ellipsis
# 공통부분:
#body-content > div.newest-list > div > table > tbody > tr
for tr in trs:
title = tr.select_one('td.info > a.title.ellipsis').text.strip()
# 최종 정리:
rank = tr.select_one('td.number').text[0:2].strip()
musics = list(soup.select("#body-content > div.newest-list > div > table > tbody > tr"))
artist = tr.select_one('td.info > a.artist.ellipsis').text
for music in musics:
rank = music.select_one("td.number").text[:2].replace('\n', ' ')
title = music.select_one("td.info > a.title.ellipsis").text.strip()
artist = music.select_one("td.info > a.artist.ellipsis").text.strip()
print(rank, title, artist)
print(rank, title, artist)