관리 메뉴

나의 개발일지(김지헌)

크롤링 본문

코드 및 잡다

크롤링

코딩이좋아요 2022. 9. 4. 17:40
import requests
from bs4 import BeautifulSoup

url = 'https://movie.naver.com/movie/bi/mi/basic.naver?code=191597'

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)

 

 

 

크롤링 할때 필요한거 requests, bs4 설치하기 app.py 에 붙히기

def movie_post():
    url_receive = request.form['url_give']
    star_receive = request.form['star_give']
    comment_receive = request.form['comment_give']

    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_receive, 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']

    doc = {
        'title':title,
        'image':image,
        'desc':desc,
        'star':star_receive,
        'comment':comment_receive

    }
    db.movies.insert_one(doc)
    return jsonify({'msg':'저장완료'})