4주차_14([나홀로메모장] - 조각 기능 구현해보기-수업)

1

import requests
from bs4 import BeautifulSoup

url = 'https://movie.naver.com/movie/bi/mi/basic.nhn?code=171539'

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(url,headers=headers)

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

# 여기에 코딩을 해서 meta tag를 먼저 가져와보겠습니다.

2

import requests
from bs4 import BeautifulSoup

url = 'https://movie.naver.com/movie/bi/mi/basic.nhn?code=171539'

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(url,headers=headers)

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

print(soup)

3. head 안에 있음

import requests
from bs4 import BeautifulSoup

url = 'https://movie.naver.com/movie/bi/mi/basic.nhn?code=171539'

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(url,headers=headers)

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

title = soup.select_one('head > meta:nth-child(9)')
print(title)
# 여기에 코딩을 해서 meta tag를 먼저 가져와보겠습니다.

※이렇게 하면 나오지 않음 브라우저에 들어가서 얻는 메타 태그의 순서와 우리가 쓰는 메타 태그의 순서가 달라서

간혹 안 나올때가 있음

방법

import requests
from bs4 import BeautifulSoup

url = 'https://movie.naver.com/movie/bi/mi/basic.nhn?code=171539'

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(url,headers=headers)

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

title = soup.select_one('meta[property="og:title"]')
print(title)
# 여기에 코딩을 해서 meta tag를 먼저 가져와보겠습니다.

그 중에서 content

import requests
from bs4 import BeautifulSoup

url = 'https://movie.naver.com/movie/bi/mi/basic.nhn?code=171539'

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(url,headers=headers)

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

title = soup.select_one('meta[property="og:title"]')
print(title['content'])
# 여기에 코딩을 해서 meta tag를 먼저 가져와보겠습니다.

content를 title옆에 둬서 상관없음

import requests
from bs4 import BeautifulSoup

url = 'https://movie.naver.com/movie/bi/mi/basic.nhn?code=171539'

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(url,headers=headers)

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

title = soup.select_one('meta[property="og:title"]')['content']
print(title)
# 여기에 코딩을 해서 meta tag를 먼저 가져와보겠습니다.

4

import requests
from bs4 import BeautifulSoup

url = 'https://movie.naver.com/movie/bi/mi/basic.nhn?code=171539'

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(url,headers=headers)

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

title = soup.select_one('meta[property="og:title"]')['content']
image = soup.select_one('meta[property="og:image"]')['content']
desc = soup.select_one('meta[property="og:description"]')['content']

print(title,image,desc)


# 여기에 코딩을 해서 meta tag를 먼저 가져와보겠습니다.