네이버 영화
https://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829
검사, copy, copy selector
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://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829',headers=headers)
soup = BeautifulSoup(data.text, 'html.parser')
print(soup)
beautifulsoup 사용방법
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://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829',headers=headers)
soup = BeautifulSoup(data.text, 'html.parser')
title = soup.select_one('#old_content > table > tbody > tr:nth-child(2) > td.title > div > a')
print(title['href'])
하나만 할때
ㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡ
네이버 영화 제목가져오기
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://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829',headers=headers)
soup = BeautifulSoup(data.text, 'html.parser')
#old_content > table > tbody > tr:nth-child(3) > td.title > div > a
#old_content > table > tbody > tr:nth-child(4) > td.title > div > a
movies = soup.select('#old_content > table > tbody > tr')
for movie in movies:
a = movie.select_one('td.title > div > a')
if a is not None:
print(a.text)
ㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡㅡ
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://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829',headers=headers)
soup = BeautifulSoup(data.text, 'html.parser')
#old_content > table > tbody > tr:nth-child(3) > td.title > div > a
#old_content > table > tbody > tr:nth-child(4) > td.title > div > a
movies = soup.select('#old_content > table > tbody > tr')
for movie in movies:
a = movie.select_one('td.title > div > a')
if a is not None:
title = a.text
rank = movie.select_one('td:nth-child(1) > img')['alt']
star = movie.select_one('td.point').text
print(rank, title, star)
순위, 제목, 점수 가져오기
지니음악 차트 불러오기
import requests
from bs4 import BeautifulSoup
from pymongo import MongoClient
client = MongoClient('mongodb+srv://son-gyeong-ah:Rhddk114@cluster0.jduknc6.mongodb.net/cluster0?retryWrites=true&w=majority')
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=M&rtm=N&ymd=20210701',headers=headers)
soup = BeautifulSoup(data.text, 'html.parser')
#body-content > div.newest-list > div > table > tbody > tr:nth-child(1) > td.info > a.title.ellipsis
#body-content > div.newest-list > div > table > tbody > tr:nth-child(2) > td.info > a.title.ellipsis
#body-content > div.newest-list > div > table > tbody > tr:nth-child(1) > td.info > a.artist.ellipsis
#body-content > div.newest-list > div > table > tbody > tr:nth-child(1) > td.number
music = soup.select('#body-content > div.newest-list > div > table > tbody > tr')
for song in music:
rank = song.select_one('td.number').text[0:2].strip()
title = song.select_one('td.info > a.title.ellipsis').text.strip()
artist = song.select_one('td.info > a.artist.ellipsis').text
print(rank,title,artist)
