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')
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&ymd=20200403&hh=23&rtm=N&pg=1
지니 차트 크롤링 연습.
어렵지 않았음
.strip() 을 넣어준다 꼭 괄호까지 써야함!
(title.text) --> print(title.text.strip())
나중에 .text.strip()은 윗줄 끝으로 옮겨줘도 됨
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')
tbody > tr:nth-child...어쩌구 나오는데 tr까지만 입력.
trs = soup.select('copy_selector복사') << ' 필수
반복하게 할 때 for tr in trs:
copy_seletor에서 특정 줄만 출력하고 싶을 때
split('')[0] 은 문자열을 나눔
str[0:5] 0부터 5번째 글자까지.
rank = tr.select_one('td.number').text[0:2].strip()
이런식으로 사용