[MongoDB] pymongo 이용하여 파이썬으로 웹스크래핑 결과 저장하기

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')

# 코딩 시작

#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)

 

기존에 웹 스크래핑으로 만들어 놓았던

 

2022.12.29 - [𝔻𝕖𝕧𝕖𝕝𝕠𝕡/웹 스크래핑 크롤링] - [웹 스크래핑 크롤링] 웹스크래핑(크롤링) 연습

[웹 스크래핑 크롤링] 웹스크래핑(크롤링) 연습

 

해당 코드를 이용해보자

 

이 데이터를 MongoDB에 저장할거다

 

pymongo 기본코드 넣어주기

 

from pymongo import MongoClient
client = MongoClient('mongodb+srv://sparta:0000@cluster0.5fhqjdx.mongodb.net/?retryWrites=true&w=majority')
db = client.dbsparta

 

import requests
from bs4 import BeautifulSoup

from pymongo import MongoClient
client = MongoClient('mongodb+srv://sparta:0000@cluster0.5fhqjdx.mongodb.net/?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://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829',headers=headers)

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

# 코딩 시작

#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)

 

여기다가 프린트 할 이유는 없으니 print는 없애주자

 

그리고 컬렉션 넣는 방법은?

 

바로 전에 배운 내용이다.

 

저장코드 넣어주기

 

# 저장 - 예시
doc = {'name':'bobby','age':21}
db.users.insert_one(doc)

 

기입해주자

 

import requests
from bs4 import BeautifulSoup

from pymongo import MongoClient
client = MongoClient('mongodb+srv://sparta:0000@cluster0.5fhqjdx.mongodb.net/?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://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829',headers=headers)

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

# 코딩 시작

#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

        doc = {
            'title':title,
            'rank':rank,
            'star':star
        }
        db.movies.insert_one(doc)

 

해당 코드를 입력하면

 

 

 

이런식으로 컬렉션에 데이터들이 DB로 들어간것을 볼 수 있다.

 

-끝-