36. 웹스크래핑 결과 저장하기

자, 인제 응용을 해보자!

 

from bs4 import BeautifulSoup
import requests
from pymongo import MongoClient
client = MongoClient("localhost", 27017)
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.nhn?sel=pnt&date=20200303', headers=headers)

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

trs = soup.select(
    "#old_content > table > tbody > tr")

for tr in trs:
    a_tag = tr.select_one("td.title > div > a")
    if a_tag is not None:
        title = a_tag.text
        rank = tr.select_one("td:nth-child(1) > img")["alt"]
        star = tr.select_one("td.point").text
        doc = {

            "rank": rank,
            "title": title,
            "star": star

        }

        db.movies.insert_one(doc)

 

이런식으로, 하되 insert_one으로도 각 하나씩 데이터를 집어넣는다. 걍 insert_one을 많이 쓴다고 기억하자!