3-13 웹스크래핑 결과 저장/insert 하기

1. beautiful soup을 이용해서 만든 아래 웹스크래핑 코드에

import requests
from bs4 import BeautifulSoup

# URL을 읽어서 HTML를 받아오고,
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)

# HTML을 BeautifulSoup이라는 라이브러리를 활용해 검색하기 용이한 상태로 만듦
soup = BeautifulSoup(data.text, 'html.parser')

# select를 이용해서, tr들을 불러오기
movies = soup.select('#old_content > table > tbody > tr')

# movies (tr들) 의 반복문을 돌리기
for movie in movies:
    # movie 안에 a 가 있으면,
    a_tag = movie.select_one('td.title > div > a')
    if a_tag is not None:
        rank = movie.select_one('td:nth-child(1) > img')['alt'] # img 태그의 alt 속성값을 가져오기
        title = a_tag.text                                      # a 태그 사이의 텍스트를 가져오기
        star = movie.select_one('td.point').text                # td 태그 사이의 텍스트를 가져오기
        print(rank,title,star)

 

2. pymongo 기본 세팅 코드를 넣고

 

 

import requests
from bs4 import BeautifulSoup

from pymongo import MongoClient
client = MongoClient('mongodb+srv://test:sparta@cluster0.55vah.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://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829',headers=headers)

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

movies = soup.select('#old_content > table > tbody > tr')

for movie in movies:
    # movie 안에 a 가 있으면,
    a_tag = movie.select_one('td.title > div > a')
    if a_tag is not None:
        rank = movie.select_one('td:nth-child(1) > img')['alt']
        title = a_tag.text                                     
        star = movie.select_one('td.point').text               
        print(rank,title,star)

 

3. 도큐먼트 만들어 하나씩 insert 하기

import requests
from bs4 import BeautifulSoup

from pymongo import MongoClient
client = MongoClient('mongodb+srv://test:sparta@cluster0.55vah.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://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829',headers=headers)

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

movies = soup.select('#old_content > table > tbody > tr')

for movie in movies:

    a_tag = movie.select_one('td.title > div > a')
    if a_tag is not None:
        rank = movie.select_one('td:nth-child(1) > img')['alt'] 
        title = a_tag.text                                      
        star = movie.select_one('td.point').text                
        doc = {
            'rank': rank,
            'title': title,
            'star': star
        }
        db.movies.insert_one(doc)