[3주차]웹스크래핑(크롤링), pymongo로DB조작

• 패키지 설치(여기서는 request로 요청하고 bs4로 보기 좋게 솎아냄)

pycharm/file/settings/project:pythonprac/python interpreter

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.nhn?sel=pnt&date=20200303',headers=headers)

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

 

• 크롤링 예시

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.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:
        rank = tr.select_one('td:nth-child(1) > img')['alt']
        title = a_tag.text
        point = tr.select_one('td.point').text
        print(rank, title, point)

 

• pymongo 기본코드

from pymongo import MongoClient
client = MongoClient('localhost', 27017)
db = client.dbsparta

# 코딩 시작

 

• insert / find / update / delete

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

# 한 개 찾기 - 예시
user = db.users.find_one({'name':'bobby'})

# 여러개 찾기 - 예시 ( _id 값은 제외하고 출력)
same_ages = list(db.users.find({'age':21},{'_id':False}))

# 바꾸기 - 예시
db.users.update_one({'name':'bobby'},{'$set':{'age':19}})

# 지우기 - 예시
db.users.delete_one({'name':'bobby'})