크롤링 예제

* 영화 순위, 제목, 별점 순으로 불러오기

- 크롤링 코드
#old_content > table > tbody > tr:nth-child(3) > td.title > div > a
#old_content > table > tbody > tr:nth-child(4) > td.title > div > a

#old_content > table > tbody > tr:nth-child(2) > td:nth-child(1) > img
#old_content > table > tbody > tr:nth-child(3) > td:nth-child(1) > img

#old_content > table > tbody > tr:nth-child(2) > td.point
#old_content > table > tbody > tr:nth-child(3) > td.point


- 작성 코드 
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')
(↓작성부분)
movies = soup.select('#old_content > table > tbody > tr')

for movie in movies:
      a = movie.select_one('td.title > div > a')
      b = movie.select_one('td:nth-child(1) > img')
      c = movie.select_one('td.point')
      if a is not None:
          title = a.text
          rank = b['alt']
          star = c.text
          print(rank, title, star)
        
        
혹은 더 세련되게


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')
(↓작성부분)
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)