데이터 공부를 기록하는 공간

# version_2 import requests from bs4 import BeautifulSoup import pandas as pd import datetime today = datetime.datetime.now().strftime("%Y%m%d") #################################################################### ########################### 산 업 부 ################################ #################################################################### 산업부 = "https://www.motie.go.kr/motie/ne/presse/p..

http://epsis.kpx.or.kr/epsisnew/ 전력수급 > 실시간 전력수급 데이터 화면(아래)를 크롤링 from selenium import webdriver from bs4 import BeautifulSoup import numpy as np import pandas as pd driver = webdriver.Chrome("./chromedriver") #3초 기다려주기, 웹페이지 로딩까지 driver.implicitly_wait(3) driver.get("http://epsis.kpx.or.kr/epsisnew/selectEkgeEpsMepRealChart.do?menuId=030300") soup = BeautifulSoup(driver.page_source, 'html.parser..

- 크롬 웹드라이버 다운로드 : https://chromedriver.chromium.org/downloads - 크롤링 시, 크롬-개발자도구 - copy select 기능 활용 from flask import Flask, render_template, request app = Flask(__name__) import requests from bs4 import BeautifulSoup import time # 엑셀 쓰기 위한 준비 from openpyxl import Workbook write_wb = Workbook() write_ws = write_wb.active from selenium import webdriver @app.route('/') def hello_world() : return r..

강의 출처 : 인프런 - 실시간트렌드홈페이지개발(크롤링+flask) 강의에서는 다음, 오늘, 클리앙인데 다음이 크롤링이 잘 되지 않아 나머지만 실행함 from flask import Flask, render_template app = Flask(__name__) import crawling @app.route('/') def hello(): list_clien, list_clien_href = crawling.clien() list_today, list_today_href = crawling.today() return render_template("index.html", clien = list_clien, today = list_today, clien_href = list_clien_href, today..