Practice. MongoDB

Let's update Web crawling data from the previous practice

code

import requests
from bs4 import BeautifulSoup

# 타겟 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
# soup이라는 변수에 "파싱 용이해진 html"이 담긴 상태가 됨
# 이제 코딩을 통해 필요한 부분을 추출하면 된다.
soup = BeautifulSoup(data.text, 'html.parser')

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)

---

• let's add the basic structure of Pymongo under BeautifulSoup.

from pymongo import MongoClient
client = MongoClient('여기에 URL 입력')
db = client.dbsparta

import requests
from bs4 import BeautifulSoup

from pymongo import MongoClient
client = MongoClient('mongodb+srv://test:sparta@cluster0.grgzlle.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')

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)

• delete print(rank, title, star) since we are not using print() but updating the data in MongoDB.

Adding to Mongo

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

-add doc = {}

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 values should be in 'title'

  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
        }
  

import requests
from bs4 import BeautifulSoup

from pymongo import MongoClient
client = MongoClient('mongodb+srv://test:sparta@cluster0.grgzlle.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')

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
        }

import requests
from bs4 import BeautifulSoup

from pymongo import MongoClient
client = MongoClient('mongodb+srv://test:sparta@cluster0.grgzlle.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')

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)